The right partnership
makes eleven.
We diagnose how your firm actually runs, then build the AI systems the diagnosis supports — and every improvement compounds.
You bring the question. We draw the machine behind it.
Nobody hires us for AI. They hire us because something takes eleven days that should take two, and no one can say which of those days is judgment. The diagnostic finds out.
We build into your stack. We don’t ask you to leave it.
Agents read from and write to the systems your team already lives in: ledgers, portals, practice management, the drive, the inbox. No migration required.
All logos, product names and company names are trademarks of their respective owners, shown solely to identify systems we integrate with. No affiliation, partnership, sponsorship, or endorsement is implied.
A.G.E.N.T. takes a workflow from “this is slow” to “this is proven.”
Every engagement runs the same playbook, in the same order, with an artifact at the end of each stage. The playbook isn't ours. It comes from The agent-centric enterprise in the Harvard Data Science Review, and we hold ourselves to it.
Priced to the work we scope together. A national rollout and a six-person practice are never the same quote.
Of listed businesses never sell, and messy financials are a leading killer. We fix that before it costs you.
Source: IBBA Market Pulse reporting
Actively licensed US CPAs remain, down from ~1.9M in 2019. We built for the shortage: agents do volume, CPAs review and approve.
Source: AICPA Trends · NASBA
Built for the firms that run Main Street.
The leverage that used to take an enterprise budget now fits a bakery, a welding shop, a café — and the professional firms that serve them. That shift is generational, and it is the reason this firm exists.
Every system we build is the same five-stage engine.
Signal
Watch the sources that matter: dockets, deadlines, ledgers, portals. The signal layer is the moat.
Enrich
Pull the context that turns a raw event into a fact about your business.
Score
Decide if it matters, how much, and how confident we are. In numbers, not vibes.
Compose
Draft the artifact: the reconciliation, the filing, the follow-up, the report.
Act
File it, chase it, escalate it, or hand it to a human. The tier decides.
Solutions compound when each agent holds a narrow scope and works inside a system. One well-bounded step earns the next.
Only two things change between a legal docket watcher and a bookkeeping close agent: what stage one watches and what stage five may do. Every engagement hardens the same spine.
Your people stop retyping and start ideating, because the machine carries the volume and hands them the exceptions worth thinking about.
Everything we sell carries one of four labels.
Each label is a front door, not a fence. When the diagnosis calls for something beyond the named services — an AI receptionist on the phones, a vision model reading documents, software built to fit — the same firm delivers it, with the tools we run in-house and the specialists we bring in for the rest.
Bespoke · by engagementConsulting
Diagnose how the firm runs and fix what the findings support.
Learn more →
Productized · monthlyAgents
Run one repeatable task end to end, measured against day one.
Learn more →
Recurring · your internal intelligenceDashboards
Ask your own data anything and get a sourced answer.
Learn more →
Enablement · the other half of elevenTraining
Train your team against the workflows you actually run.
Learn more →The Front-End Patch.
Your vendor system stays exactly as it is — contract untouched, back end unopened. We study it read-only, then ship a front-side layer that fixes what your people actually fight: search, intake, dashboards, reporting. Bounded, reversible, and small enough to approve without a committee.
Where firms start.
The playing field has shifted in a generation: firms that move now can compete for ground that used to belong to the biggest players. Pick your world, or the function that hurts. Each tab shows what we take off a team's plate first, and the playbook behind it.
We stay current,
so you don’t have to.
- Because the options are limitless. Voice, vision, code, agents — new capabilities land monthly, and part of our job is knowing which one is right. We watch all of it so our clients compete with the best technology available.
- A monthly ecosystem review. What the model and open-source ecosystem now makes possible, examined on a schedule — not when a headline forces it.
- Solutions re-examined as standards move. On every maintained engagement, what we’ve shipped is checked against what changed — and nothing switches without a human approving it.
- You hear about it in the Letter. Once a month: what changed, and what we would do about it. Subscribe here.
Trust is a promise we designed for.
It runs on your subscription and your storage — fire us and keep everything. Nothing trains on your data. Licensed sign-off on everything regulated. Sourced answers or a refusal.
Built for governments that
answer to everyone.
Government work is where careful AI matters most, and where it is already working: permitting prescreens that cut months to days, constituent services in dozens of languages, records processing that keeps pace with the law. We bring that discipline to agencies nationwide.
Pilot-sized by design
Diagnostics and pilots scoped to government small-purchase processes. Proof before procurement; no seven-figure platform bets.
Framework-aligned
Deployments follow the NIST AI Risk Management Framework and state guidance, with human approval, audit trails, and records-retention awareness built in from day one.
Equity, tested
Public systems must serve everyone. Bias and disparate-impact testing is standard in our deployments: an engineering step, not an afterthought.
Records-aware
FOIA and public-records obligations shape the architecture: what's logged, what's retained, what's producible. Decided before the first document moves.
Start where the queue is longest.
- Permitting triage and prescreen
- Housing program intake and eligibility
- FOIA and records-request processing
- 311 and constituent services
- Grants management and reporting
- Forms digitization and legacy intake
The queue the public feels.
Permits, records requests, constituent service — work people stand in line for. Pilots are sized to small-purchase processes and tested for disparate impact as an engineering step, because public systems must serve everyone.
Public agencies, nationwide.
Wherever housing, growth, and service delivery are moving faster than staff capacity. The founder's background spans affordable-housing finance, compliance, and the rooms where initiatives move.
Built for firms where
a wrong answer has a docket number.
Law firms don’t need convincing that AI matters — they need the fears named accurately and answered with architecture. Assembly is not judgment: our agents assemble the file, the chronology, the reconciliation; the attorney owns every judgment, signature, and dollar.
What defense firms actually worry about — answered, not soothed.
“It trains on our clients.”
No training on client data, contractually, in any tier — an entry in a prohibited-actions register enforced by tests, not a line in marketing copy.
“Our data leaves the building.”
The work runs on your firm’s own subscription and your own storage, with no vendor server in the loop. The party holding the data is the firm — as it always was.
“The logs are a second copy of the file.”
Run records name sources as identifiers, never their contents. The fields that would carry prompt and output text exist in the standard and are left empty by rule.
“We’re locked in once we start.”
The confidentiality answer is also an exit clause: when an engagement ends there is nothing to migrate and nothing to ransom.
ABA Formal Opinion 512, mapped to architecture.
The opinion’s duties are the committee’s checklist. Each one lands on something checkable here, not a policy PDF.
- Confidentiality. Per-client isolation of credentials, storage, and memory; contractual no-training; client-owned instances, so privileged material never sits on our infrastructure.
- Competence. A tier ladder assigns each task an autonomy ceiling by risk, and the training curriculum teaches the boundary — what may be assembled, what must be judged.
- Supervision. One named seat that can stop any workflow, every agent action logged, and nothing unreviewed ever reaches a court, regulator, or counterparty.
Trust accounting, done the way an exam wishes it were.
A practicing defense partner’s unprompted read of the market: law-firm accounting is “a huge untapped portion… this should all be completely automated.” The Counsel × Close desk is that work, productized.
Three-way reconciliation
Bank statement vs. trust ledger vs. client ledgers, recomputed independently every cycle. Every discrepancy itemized with sources, never netted away.
Pre-bill hygiene
Time entries checked for narrative quality, guideline conflicts, and trust-vs-operating classification before invoices go out. Exceptions listed for the biller, never fixed silently.
Disbursement preparation
The settlement disbursement sheet assembled from statement, lien ledger, and fee agreement, every figure sourced. Preparation for a disbursement — never the disbursement. A human moves every dollar.
Exam-ready by default
Licensed CPA review on financial deliverables, disclosed in the engagement letter. Every run leaves a record — the trust-exam answer is a folder, not a scramble.
The same desk pattern runs across the whole Ledger Suite — legal is where the bar-discipline stakes make it sharpest.
Nine law workflow boards, mapped step by step.
Employment, personal injury, corporate, civil litigation, tax controversy, white collar, estates, immigration, and defense case evaluation — each mapped through every step and branch, with how far autonomy may go and the seat that can stop it. One board is free, permanently.
A curriculum written for lawyers, not adapted for them.
Four quarters — The Boundary, Data Hygiene, Confidentiality and Privilege, Verification Discipline — anchored to your own matters, and structured to support CLE where your jurisdiction permits.
The AI Committee Briefing.
Fifty minutes for the whole committee: the fears named, the boundary, the tier ladder, the named seat, and what to do Monday. Enablement, not a pitch — it books directly, no diagnosis required.
Six desks. One engine.
Your subscription, your storage.
Productized desks for the recurring work a practice must do perfectly and does manually. Each runs on your own AI subscription and your own Drive — no server of ours in the loop — with a weekly research robot, a client desk for calls and notes, a market watch, and a packaging studio.
One engine, six verticals.
A new vertical costs one research-and-generate cycle on the same engine — which is why the suite covers this much ground.
Ledger OS
The flagship — the engine itself, for firms whose vertical isn’t listed yet.
Ground
Real estate — the deal file, the diligence trail, the recurring closes.
Counsel
Legal — matters, deadlines, and the accounting a bar exam actually checks.
Close
Accounting — reconciliation and close discipline for firms that sell it, and firms that need it.
Stewardship
Wealth management — the review cadence, the meeting file, the evidence of care.
Practice
Healthcare delivery — the operational spine behind the clinical work, never the clinical work.
Counsel × Close: the trust-accounting desk.
Three-way trust reconciliation recomputed independently every cycle, pre-bill hygiene, settlement-disbursement preparation, and an exception watch — agents assemble and reconcile, licensed CPAs review, and a human moves every dollar. The same pattern — recurring run, sourced figures, human checkpoints — is what every desk in the suite delivers for its own vertical. See it in the legal practice →
The maintained retainer, itemized.
- The weekly run. The desk’s recurring work, delivered on cadence, every figure sourced or refused.
- Model and capability currency. A nightly scout watches AI releases and capability changes; anything material to your system is flagged to your administrator with cost and benefit attached. You decide — nothing switches itself.
- Maintenance and repair. When a connected system or model changes underneath the desk, we fix the desk — that is what the retainer is for.
- Everything stays yours. Your subscription, your Drive, your instance. End the retainer and the desk keeps working as-built; there is nothing to migrate and nothing to ransom.
One-time build, or desk + retainer.
Sold as a one-time productized deliverable, or as desk + customization + the maintained weekly retainer. Priced to the firm and the scope of work, quoted after a conversation — never templated.
Software teammates,
run to a standard.
An agent engagement puts a software teammate on one repeatable task, end to end — and we start where your workflow map ends, so nothing ships that the diagnosis didn’t support.
What they run
The recurring work a firm must do perfectly and does manually: the close, eligibility checks, document intake, deadline monitoring, follow-up that never lapses. One bounded task per agent, chosen by the diagnosis.
What ships with every one
A Guardian agent that watches the others, autonomy tiers assigned per task by risk, licensed CPA review on financial deliverables, and a log of every action. Not on request — on every engagement.
How they’re measured
Your baseline is recorded on day one. At day 30 you get a one-page before-and-after against it, every number sourced or absent, and the delta monthly after that. What proves out, scales; what doesn’t, we stop.
The engine underneath is the same five stages every time — watch it run on the method page. The boundaries are contractual, in writing on the assurance page.
Behind every agent is a network: when a solution needs a capability beyond the tools we run in-house — a voice model, a vision pipeline, custom software — specialists are assembled for it, per engagement, under the same written standard. And every maintained engagement carries 24/7 support from a team on retainer across time zones; every fix lands in a repository of resolutions, the raw material for clearing routine issues faster every month.
Small crews, one direction.
Each agent is a crew with one bounded job, run end to end and measured against day one. A Guardian watches every one of them — and the fleet moves in the same direction because the diagnosis set the course.
What moved here lately.
Where this connects.
GovernanceThe boundaries an agent runs inside, delivered as your firm’s written standard.
Learn more →DashboardsThe same firm data your agents work from, queryable in plain English.
Learn more →
Data FoundationThe assessment that clears the base before an agent is proposed.
Learn more →Strategy ConsultingThe diagnosis that decides which task deserves an agent at all.
Learn more →Name the task that eats the most hours.
Thirty minutes, free. You leave knowing whether it’s agent work — including when the honest answer is a checklist and one hire.
Your own data,
answered or refused.
Ask your business a question in plain English and get an answer with its sources shown — or an honest refusal when the data can’t carry one. Never a guess dressed as an answer.
On top of what you run
The dashboard connects by API to the systems you already trust — ledger, practice management, CRM, drive. We never migrate a source of truth; the answers cite the system they came from.
Sourced or refused
Every answer names its records. Below the confidence threshold the response is a question back to you, not a plausible-sounding sentence — the same house rule that governs everything we ship.
Yours, isolated
Per-client credentials, storage and memory; nothing you share trains any model, contractually. Where the zero-infrastructure pattern fits, it runs on your own subscription and your own storage.
Numbers that answer for themselves.
The board question that used to take a week of assembly becomes a question you type. Every answer arrives with the records behind it — or as an honest refusal, which is its own kind of answer.
What moved here lately.
Where this connects.
AgentsWhen the answer to a question should become an action, run to a standard.
Learn more →GovernanceWho may ask what, and what the answers may touch — in writing.
Learn more →
The Efficiency AuditMeasure what your current tools actually return before adding another.
Learn more →Data FoundationWhat a citation is worth depends on the layer it cites.
Learn more →Bring the question you can’t answer today.
If your systems hold the data, we’ll show you what it takes to make it answerable. If they don’t, we’ll say that instead.
Adopt fast.
Answer for it.
The board wants AI moving this quarter; the regulator, the carrier and the client want proof of control. One unreviewed output in front of the wrong reader costs more than the program saved — so we deliver the controls as a service, and we start where your data governance ends, so you’re not building from scratch.
Your written standard
Autonomy tiers per task, a prohibited-actions register, examiner-never-builder review, and logging — drafted for your firm, in your language, signed into your engagements. The architecture we run ourselves, published here, becomes yours.
Framework-aligned
NIST AI RMF alignment, disparate-impact testing as an engineering step, records-retention and FOIA awareness where the public is the client. The committee question — “what governs this?” — gets a document, not a promise.
For the seat that answers
Built for the managing partner, compliance officer or administrator whose name is on the outcome: one accountable seat named in writing on day one, and every boundary printed before work begins.
Easy to adopt. Hard to answer for.
When the regulator, the client or the board asks how AI is controlled here, the answer is your own written standard — autonomy tiers, a prohibited-actions register, logs a reviewer can actually read.
What moved here lately.
Where this connects.
AgentsThe systems these controls govern, shipped with a Guardian on every one.
Learn more →DashboardsAccess and audit questions answered from your own records.
Learn more →The Efficiency AuditWhere ungoverned tools are already running, find them first.
Learn more →Strategy ConsultingGovernance decisions made at board level, before the build.
Learn more →Bring the question your committee keeps asking.
Thirty minutes, free. You leave with the shape of the answer — and the assurance page above is the standard we’d hold your build to.
The diagnosis
is the strategy.
Bespoke, judgment-heavy work done with you: how the firm runs, where the margin leaks, what to fix first and what to leave alone — written down, priced to scope, with a ceiling that holds.
Diagnosis & redesign
Intake and diagnosis, workflow redesign, GAAP and compliance interpretation. The map of how work actually flows is a deliverable you keep, whether or not you continue.
Exit readiness
The Books Ladder from clean records to diligence-ready, add-backs evidenced, a data room that survives the request list. Engaged by the owner, welcomed by their broker — no referral fees in either direction.
Board-level advisory
Led by a founder with an economics degree, an MBA in finance and entrepreneurship, a banking innovation award won at a top-ten US bank, and national leadership roles across AAREP, ULI and HAND.
And when the diagnosis recommends a capability we haven’t delivered before, sourcing it is our job — our own tools where they fit, specialists from the network where they don’t. The recommendation is never limited to what we already have on the shelf.
Diagnosis before prescription.
The proposal contains only what the diagnosis supports — including when the honest answer is a checklist and one hire, not agents. Strategy work here starts at that altitude: what the firm is for, what the numbers say, and what to leave alone.
What moved here lately.
Where this connects.
AgentsWhere the diagnosis finds repeatable work, an agent carries it.
Learn more →Data FoundationThe layer the strategy stands on, measured before anything is proposed.
Learn more →GovernanceThe control questions a board should settle before the build.
Learn more →The Efficiency AuditWhen AI is already in the building, start by measuring it.
Learn more →One process. One accountable seat. One month, measured.
That’s the engagement shape, in writing on day one. The conversation that starts it is free.
Already running AI?
Find the missing margin.
The tell is everywhere: the tool got adopted, everyone says it helps, and no line on the P&L moved. The Efficiency Audit finds the gap between what your firm spends on AI and what the numbers show for it.
What gets measured
Every AI tool in the building against the workflow it was bought for: what it costs, who touches it, what changed on the P&L, and where the work re-routed around it instead of through it.
Why tools stall
Powerful engines bolted onto processes shaped by human limits — the eight-hour shift, the sequential handoff, the approval that waits for Monday. The fix is a redesign of the road, not another engine. The full argument is here.
What you keep
Written findings, a ranked fix list with what each is worth, and an honest verdict on every tool: fix the process around it, renegotiate it, or drop it. Credited toward whatever engagement follows — if any does.
When the fix list names a capability new to us — a voice agent, a vision model, a custom build — sourcing it is part of the job, through the network the firm keeps for exactly that. The audit is never limited to recommending what we already sell.
Findings ranked by what they’re worth.
Every tool in the building gets an honest verdict — fix the process around it, renegotiate it, or drop it — with the value of each fix attached, so Monday’s priority list writes itself.
What moved here lately.
Where this connects.
Data FoundationWhen tools underperform, the base layer is the first suspect.
Learn more →DashboardsKeep the measurement running after the audit ends.
Learn more →GovernanceThe controls that keep the fixed version fixed.
Learn more →Strategy ConsultingWhen the finding is bigger than a tool, the diagnosis takes over.
Learn more →Name the tool you’re least sure about.
Thirty minutes, free. If the honest answer is “keep it and change nothing,” you’ll hear that too.
Your stack is only as smart
as its dirtiest data.
An agent system is layers: your records at the bottom, the assembled context in the middle, the agents on top. Every layer inherits the one beneath it — which means you are only ever as ready as your weakest foundational layer.
One dirty field. Watch it climb.
Everything above inherits the base. That is the whole argument for starting there.
The Data Foundation Assessment.
A stage of the Audit, run before any agent is proposed: data hygiene measured, not assumed.
What it checks
Duplicates, unreconciled balances, undated and unowned records, fields that disagree between systems, and who can touch what. The base layer, examined the way an auditor examines it.
What you keep
A written findings list ranked by what each fix unlocks — because a deduplicated client file is not housekeeping, it is what makes every layer above it trustworthy.
Why it comes first
No agent is proposed onto a base the assessment hasn’t cleared. Fixing the base costs less than fixing everything it corrupts — and it is the least glamorous work in the stack, which is why it gets skipped.
What moved here lately.
Where this connects.
AgentsWhat a clean base makes possible — and a dirty one sabotages.
Learn more →DashboardsSourced answers need a base worth citing.
Learn more →The Efficiency AuditWhere underperforming tools get measured against what they cost.
Learn more →Strategy ConsultingThe diagnosis that decides which layer to fix first.
Learn more →Ask us what your base layer would score.
Thirty minutes, free. Bring one report you don’t fully trust and we’ll trace the doubt to its layer.
Careful by promise,
and by architecture.
Most firms answer trust questions with adjectives. We answer with both a promise and the architecture that keeps it: constraints built in, written down, checkable.
You own it. All of it.
Everything we build for you runs on your own AI subscription, in your own Drive, and — where structured memory earns its keep — in your own database instance, under your keys. No server of ours holds your client data, which makes this the confidentiality answer, the lock-in answer, and the exit answer at once: when an engagement ends there is nothing to migrate and nothing to ransom. (This website’s own membership accounts are the one thing we do hold — the privacy policy lists exactly what and where.)
Your data, isolated
Per-client credentials, storage, and memory. Agents read only sources you approve. Nothing you share trains any AI model, contractually. Every agent action is logged.
Compliance built in
HIPAA Business Associate Agreements before any patient data moves. Confidentiality-first architecture for legal clients. Records-retention and FOIA awareness for public-sector work.
Licensed humans sign off
Financial deliverables are prepared by our agent systems, then reviewed and approved by licensed CPAs in our delivery network — and cybersecurity and advisory oversight protects how your systems are touched. Disclosed plainly in every engagement letter.
Sourced answers or a refusal
Our dashboards and research agents cite what they know and say so when they don't. No guesses dressed as answers, in your business or in ours.
Your firm’s immune system, in 55 seconds.
How an agent system stays safe — told the way biology does it: a watcher, the specialists, and a memory that only grows.
Read the film as text
What keeps an agent system safe isn’t hope — it’s architecture, and it behaves like biology. The failure mode is the plausible guess: confident, fluent, unsourced. Every AI system eventually produces one; ours is built to expect it. First responder: the Guardian — a separate agent, shipped on every engagement, that watches every action the other agents take and flags anything weird before it leaves the building. Then the specialists arrive: the Examiner, who is never the builder and checks every system against test sets with known answers; the Second Sum, an independent computation that re-derives every recomputable number; and the Licensed Reviewer — CPAs who review and approve financial deliverables, disclosed in every engagement letter. The refusal register only grows: thirty-six classes of refused action today — it ratchets up and never shrinks. And it never forgets: logs, register, baseline, boundaries. When the same failure tries again, it is refused automatically, and the refusal is logged. Careful by promise. And by architecture.
Every agent ships against a reliability standard you can read.
Not a marketing page. An engineering document that governs every build.
- Autonomy tiers, per task. Each task carries an explicit tier, from fully checked to fully autonomous, assigned by risk.
- A prohibited-actions register. Thirty-six classes of action our agents are built to refuse, from signing filings to touching payments. It grows; it never shrinks.
- The examiner is never the builder. Every system is checked by someone who didn't build it, against test sets with known answers.
- Measured against day one. Your baseline is recorded at the start. At day 30 you receive a one-page before-and-after against it — every number sourced or absent, estimates labeled — and the delta monthly after that.
- Recomputable output. Where the work is arithmetic, a second, independent computation checks the first.
Boundaries you get in writing.
- Filings carry a human signature — always. Tax returns, government filings and legal documents are assembled by agents and signed by licensed people.
- Money moves only on a human’s button. Payment initiation, transfers and payroll runs keep a person on approval, every time.
- Judgment stays with licensed professionals. Tax positions and valuation opinions are theirs, never an agent’s.
- External release is a human decision. Nothing unreviewed leaves for a regulator, court or counterparty.
- Below the confidence threshold, the answer is a question. A sourced answer or an honest ask — never a plausible-sounding guess.
- Every number we publish traces to a real engagement record. No claims we can’t reproduce, in your business or in ours.
The myths, examined.
The evidence, cited.
The concerns we hear most from operators and public officials, answered with primary sources. AI is already trusted where the stakes are highest: medicine, law, government, finance.
"AI will replace my people."
The Yale Budget Lab examined 33 months of labor data after ChatGPT's release and found no discernible disruption to overall employment. The Dallas Fed and RAND report the same, with more businesses adding jobs from AI than cutting them. The pattern is augmentation: AI absorbs volume; people keep judgment, relationships, and accountability.
How we handle itOur engagements are designed around your team, not instead of it. People are the other half of eleven.
"AI makes things up too much to trust with real work."
Unsupervised AI does invent, which is why serious deployments never run unsupervised. The FDA has authorized over 1,400 AI-enabled medical devices under formal validation. Courts require human verification of AI-assisted work. The fix is structure, not hope.
How we handle itThe same structure: agents do volume, licensed professionals review financial deliverables, every answer is sourced or refused, and a human approves anything that leaves the building.
"Our data will end up training some model, or leaking."
That risk is real with consumer tools and absent with properly configured enterprise deployments: contractual no-training terms, tenant isolation, encryption, and audit logs are standard. California's court system draws exactly this line: confidential data prohibited in public AI systems, permitted in managed internal ones.
How we handle itPer-client isolation, allowlisted sources only, no training on your data ever, and a written security posture you can hand to your counsel.
"AI is too legally risky for government."
Government frameworks don't prohibit AI; they govern it. NIST's AI Risk Management Framework, federal agency guidance, South Carolina's state AI strategy, and the SC judiciary's generative-AI policy all chart responsible adoption. Cities are already deploying: permitting prescreens, multilingual constituent services, records automation.
How we handle itFramework-aligned deployments with human approval, audit trails, records-retention awareness, and bias testing as standard, pilot-sized to fit procurement realities.
"It's a fad."
Legal AI reached in three years the adoption level cloud computing took a decade to hit. FDA authorizations of AI medical devices grew from a handful a year to nearly three hundred in 2025 alone. Nearly a third of practicing lawyers now use generative AI. Regulated professions are the slowest adopters by design, and they have adopted.
How we handle itWe don't sell momentum; we sell diagnosed fit. If AI isn't the answer to your problem, that's the report you'll get.
"We're too small, or not technical enough, for this."
The organizations winning with AI aren't the most technical. They're the ones that paired with people who know the terrain. Pilots stand up in weeks, not years.
How we handle itYou don't need in-house engineers. The diagnosis tells us what fits your size and budget; a written ceiling means no surprises; and our enablement work leaves your team able to run what we build.
"AI in public systems invites bias and civil-rights problems."
The risk is documented: a state attorney general reached a $2.5 million settlement with a lender whose underwriting model disadvantaged Black and Hispanic applicants. The same case defines the fix. Test for disparate impact, keep humans on decisions, document everything.
How we handle itDisparate-impact testing, human approval on consequential decisions, and full audit trails are standard in our public-sector and lending-adjacent work, not add-ons.
"AI consultants are just reselling tool tutorials."
Many are, which is why so many AI pilots die within a year. Deployments fail when nobody maps the workflow first.
How we handle itWe're a consulting firm that uses AI, not an AI vendor with a pitch. The diagnostic is a real deliverable you keep either way, the proposal contains only what the diagnosis supports, and every claim we make in public traces to a real engagement.
Built by an operator,
not a demo reel.
The name is the thesis: with the right partner, a business doesn't add capability, it compounds it. One and one makes eleven.
Leon Fields, Founder
An economist by training, an operator by habit, and a builder by conviction. Leon studied economics and community development at Howard University, earned his MBA at William & Mary with a dual specialization in finance and in entrepreneurship & Innovation, and is completing advanced professional studies in agentic AI at Harvard.
Before founding the firm, he earned a banking innovation award for process improvement at one of the ten largest US banks, worked inside affordable-housing finance and LIHTC compliance, and used AI to successfully resolve two legal disputes of his own, including a federal matter opposite a major national law firm.
He has sat on your side of the table.
- Howard University · economics & Community development
- William & Mary MBA · finance, entrepreneurship & Innovation
- Harvard · advanced professional studies, agentic AI
- Banking innovation award · top-ten US bank
- Affordable-housing finance & LIHTC compliance
Some problems are operational. Some are technical. Some move only when the right people are in the room.
Operations
Workflow mapping, process redesign, the diagnosis itself. The lane everything else depends on.
Automation
The agents, dashboards, and systems, built to the written standard and measured against day one.
Relationships
Policy rooms, procurement processes, the introductions that move initiatives. Compounding requires every gear turning.
One habit runs under all three lanes: a monthly review of what the AI ecosystem now makes possible, so the advice never ages quietly.
One accountable firm. A network built to deliver anything AI.
The delivery network
Founder-led, never founder-limited: a licensed CPA review network for regulated deliverables, a cybersecurity advisor on the architecture, and specialist advisors, consultants and ad-hoc expert hires assembled per engagement.
No AI ask out of scope
Voice AI and AI calling, computer vision, sales and marketing automation, custom software, managed AI subscriptions for a whole team — the tools we run in-house carry the core, and the network carries the rest. Finding the right capability is what you hire us for.
Support that keeps running
Every maintained engagement and membership carries 24/7 support from a retainer team across time zones — and every fix lands in a shared repository, so the same issue gets resolved faster each time it appears.
AI has leveled the playing field in a generational way. We exist so small and middle-market firms can strategize, compete and scale in ways they never could — capturing market share and influence like never before.
Let's make eleven.
Step one is a free thirty-minute conversation: bring the one process you already know is broken, and leave knowing whether it is worth pursuing — including when the answer is no.
Three commitments, made before any work begins.
Not a platform, not a pilot program, not a twelve-month roadmap. One process, one accountable person, one month of running both ways and timing them.
Not a platform. One workflow: audited, redesigned, governed, measured. If it does not survive measurement, we say so.
Named before we start: the person who can stop it. That authority exists on day one, in writing.
Run the manual way and the agent way side by side, and time both. The comparison is against what would have happened anyway, not a flattering baseline.
Want to arrive prepared? The Workflow Builder turns the process that hurts into a map in ten minutes — no account, nothing stored until you send it. It becomes the pre-call assessment.
Open the builder →
Enter where you actually are.
Rung one is a valid place to stand — messy books, a manual process, a tool nobody measures. The method meets the firm where it is and climbs one step at a time, with an artifact you keep at every stage.
Scoped before it is priced.
We do not publish a rate card, because the work is never the same twice. Pricing a national rollout and a six-person practice from the same template would be dishonest to one of them.
We scope the work before anyone quotes it
The diagnostic is quoted to the size of your firm and the ground it covers, and it is credited toward whatever engagement follows. You keep the written map either way, including the version that says you need a checklist and one hire, not agents.
The number is agreed before work begins
Your proposal names the scope, the price, and a ceiling that holds for the term. Nothing is billed that was not scoped, and nothing is scoped that the diagnosis did not support. Executive briefings book directly, no diagnosis required.
The conversation is free.
The diagnosis is where it starts.
Every session — the conversation, Audit scoping, the AI Committee Briefing — books from one page, each with what it is for and what it costs (they are free).
Rather write than book?
Built for the way your
industry actually works.
The same five-stage engine, tuned to the documents, deadlines, and regulators of your world. Every engagement starts with the diagnosis. These are the worlds where our playbooks run deepest.
Real Estate & Affordable Housing
Run the operational spine of a portfolio on time, every month.
- Rent rolls and ledgers reconciled monthly, variances named
- Delinquency queues worked with escalation built in
- Development draw packages assembled from source documents
- Lease-up pipelines and unit turns tracked to the day
- Vendor invoices checked against the contracts that govern them
- Computer-vision reads of inspection and unit-turn photo sets
- Resident communications drafted for a person to send
LIHTC Compliance
Keep the credit by keeping the file — before the auditor asks.
- Income certifications assembled and second-checked
- Recertification calendars that never slip
- Tenant-file completeness sweeps ahead of agency audits
- Placed-in-service and compliance-period deadlines watched
- Agency reporting packages drafted for review
- Year-15 files built as the years happen, not at the end
General Compliance, Any Industry
Track every obligation from the source document to the evidence.
- Obligation registers extracted from regulations and contracts
- Evidence collected continuously, not the week before the audit
- License and filing renewals on a calendar with margins
- Policy-to-practice gap reviews with findings ranked
- Regulator correspondence drafted for sign-off
- Incident logs kept audit-ready as they happen
Healthcare & Adjacent Practices
Recover the front-office hours that eligibility and claims consume.
- Eligibility verified before every visit, not after the claim bounces
- Claims assembled, scrubbed and chased to payment
- Denials worked by root cause, not one at a time
- Recall and reactivation outreach that actually goes out
- Voice AI on the front-desk phones — reminders, scheduling, overflow
- Intake digitized before the patient arrives
- Credentialing and license files kept current
Legal
Protect the hours you bill and the deadlines you cannot miss.
- Billable hours reconstructed from the file, not from memory
- Intake in days, not weeks: conflicts, engagement paper, matter setup
- Deadline calendars read from the documents themselves
- Work routed between attorney and assistant at the right rate
- Demand and discovery drafts assembled for attorney review
- Conflicts checks run before the first call back
Lobbying
Know what moved in the record before your client asks.
- Legislative and regulatory monitoring fused with the client book
- Hearing and comment-deadline calendars kept ahead of the docket
- Position summaries drafted from the actual bill text
- Stakeholder and committee maps kept current
- Client reports assembled weekly, sourced line by line
- Disclosure filings prepared for a human signature
Restaurants & Hospitality
Defend the margin line by line, week by week.
- Supplier invoices checked against agreed prices, every line
- Inventory variance flagged weekly with the receipts attached
- Prime-cost reporting from the POS you already run
- Licenses, permits and inspections renewed with time to spare
- Labor schedules checked against forecasted covers
- AI phone answering for reservations and orders, tuned to your menu
- Delivery-platform and chargeback reconciliation
Government
Move the queues residents feel — pilot-sized and procurement-aware.
- Permitting prescreens that cut review queues from months to days
- Program intake and eligibility with a human on every decision
- FOIA and records requests processed on the statutory clock
- Grants managed and reported without the scramble
- 311 and constituent-service routing with context attached
- Legacy paper intake digitized form by form
Owner-Led Firms Preparing To Sell
Arrive at diligence with numbers a buyer can trust.
- A recast P&L with every add-back evidenced
- A data room assembled early and kept current
- Working-capital and revenue-quality analyses run in advance
- Customer-concentration exposure mapped honestly
- Sales and CRM automation that documents revenue quality as it runs
- Diligence request lists answered from the file, fast
- Engaged by the owner, welcomed by their broker
And if the ask is AI and it isn’t on a list above, it is still ours to deliver: the tools we run in-house carry the core, and a vetted network of advisors, consultants and specialist hires carries everything beyond it — voice, vision, automation, custom software. Finding and running the right capability is part of the engagement, not a referral elsewhere.
Proof of range, not a fence.
The founder’s first vertical was affordable housing — LIHTC compliance, where every tenant file faces an agency audit and every number must survive an exam. Every engagement since, in every industry, inherits that discipline.
Three things stay constant.
Audit first
The Audit maps your workflow before anything is proposed. If the honest answer is advice, not software, that's the report you get.
A written ceiling
Scope and price are agreed before work begins, and the ceiling holds for the term. No industry, no exception.
Measured against day one
Your baseline is recorded at the start; at day 30 you get a one-page before-and-after against it, then the delta monthly.
Asked by operators in every industry.
Do you only work in these industries?
No. Makes Eleven is a general consultancy: any firm, any industry, case by case. These are the verticals where our playbooks already run deepest. If yours isn't listed, the diagnostic works exactly the same way. The same goes for capabilities: if it touches AI — voice, vision, software, security — it is in scope, delivered with our own tools and a vetted specialist network.
What does an industry engagement actually start with?
The diagnostic. You get a written map of how work flows through your firm, what to automate, what to fix first, and what to leave alone. It is scoped to your firm, credited toward whatever follows, and it is a deliverable you keep whether or not you continue.
Who reviews the regulated output?
Licensed professionals. Financial deliverables are prepared by our agent systems and reviewed and approved by licensed CPAs in our delivery network, disclosed plainly in every engagement letter. Agents never sign, file, or pay; that's contractual.
Will this replace the systems we already use?
No. The agent layer sits on top of your existing systems by API. We never migrate your ledger, your practice management system, or your CRM; the agents work between them.
How is pricing set?
By scope, never by template. We do not publish a rate card, because a national rollout and a single-office practice are not the same work. The diagnosis establishes what the work actually is; the proposal names the price and a written ceiling that holds for the term.
Book the conversation. Free, 30 minutes.
Bring the one process you already know is broken. You leave knowing whether it is worth mapping — including when the answer is no.
Every function of the business.
One engine underneath.
No function leads and none is an afterthought. The same five-stage machine runs any of them where documents move, deadlines bind, and follow-up decides outcomes.
Industries are who you are; functions are the work itself. The engagement can enter through either door. Browse by industry instead →
Every function of the business runs on the same five stages.
Accounting, finance, HR, operations, compliance, legal: the same signal → enrich → score → compose → act spine, tuned to the documents and deadlines of that function. Agents assemble; licensed professionals review anything regulated; every step is measured against your day-one baseline.
Accounting
Clean records, reconciled accounts, and a close that happens on a date. Agents assemble; licensed CPAs review and approve. The Books Ladder below shows the rungs.
Finance & FP&A
A 13-week cash forecast that reconciles to the ledger, not to hope. Variance flagged with sources attached.
HR & People
Onboarding and offboarding chases that never lose a step; credential and license expiry watched continuously.
Operations
The exception board: one queue for everything stuck, with an owner and a clock on every item.
Marketing & Growth
First-party lifecycle triggers on consented channels only. Relevance from your own data. No scraping, no purchased lists.
Sales & CRM
Pipeline hygiene enforced automatically; quote-to-close follow-up that's polite, relentless, and logged.
IT & Data
Access reviews on schedule, unused licenses reclaimed, backups verified by restoring them, not by trusting the checkbox.
Compliance & Risk
Obligations tracked from the governing documents, filings calendared with margins, evidence collected as the year happens.
Legal & Contracts
Renewal and notice dates computed from the contracts themselves; obligations surfaced before they bite.
Customer Service & Front Office
Intake triaged, routine questions answered from approved sources, the rest routed to a human with context attached.
Procurement & Vendors
Invoices reconciled against contracts and price lists; vendor documents chased; renewals never auto-renewed unseen.
Data & Reporting
Numbers assembled, sourced, and explained on schedule. Your own data, queryable in plain English.
These are starting points, not the menu. If it touches AI, it is in scope — voice AI on the phones, computer vision on the documents, sales automation in the CRM, managed AI subscriptions for the whole team — delivered through our own toolset and the specialist network behind it.
Five rungs. You enter wherever your books actually are.
How function engagements work.
Can we start with just one function?
That's the recommended path. The diagnosis picks the function where proof is fastest, we run it to a measured result, and expansion follows evidence, never enthusiasm.
Do you favor one function over the others?
No. The diagnosis picks the function where proof lands fastest for your firm. Accounting shows up often because bookkeeping is recomputable, so a second independent calculation can verify every number, but that is a property of the work, not a ranking of our services.
Do these connect to our existing tools?
Yes, by API, on top of what you already run. We never migrate your ledger or CRM; the agents work between your systems and leave the source of truth where it is.
What never gets automated?
Signatures, filings, and payments; tax positions and valuation opinions; anything leaving for a regulator, court, or counterparty without human review. The full list is on the assurance page, and it is contractual, not just stated.
Book the conversation. Free, 30 minutes.
Name the function that hurts and we will tell you honestly whether an agent system helps — and when a checklist and one hire beats it.
Measured against
day one.
Every engagement records its baseline before anything is built, so every result here is a before-and-after — anonymized to protect the client, and verified against the engagement record before it appears.
Results are specific to each firm’s baseline, workflows and adoption; they describe what happened there, not a promise of what will happen for you. The diagnosis is how we find out what your number would be.
The first number we measure is yours.
Day one records how long the work takes now. Day 30 shows the same work against it — every number sourced or absent.
Report it once.
It stays fixed.
Every maintained engagement and membership carries 24/7 support. Report an issue here and it becomes a numbered ticket with the support team — staffed across time zones, so somebody is always on the clock.
How a report travels
Your report becomes a ticket the moment you send it — you get the number back on this page and by email. The team answers from [email protected], and the ticket number keeps the thread in one place.
Who picks it up
A support team on retainer, spread across time zones. Signed in, your firm and workspace ride along with the ticket automatically; signed out, your email address is all we need to find you.
Why fixes stick
Every resolution lands in a repository of past fixes and the reasoning behind them, so the same issue gets resolved faster each time it appears — and the routine ones get faster every month.
What broke, and what you expected.
A sentence or two is enough — screenshots and files can go in a reply to the confirmation email.
It’s in the queue.
Your ticket is — a confirmation is on its way to your inbox. Replies come from [email protected]; keep the ticket number in the subject line if you write back.
The Help Desk covers maintained engagements and memberships. Not a client yet? Start a conversation instead — this queue can’t quote new work.
The Makes Eleven
Letter.
Once a month: what changed in AI for regulated work, and what we would do about it. Short, specific, written to be acted on — and everything in it follows the house rule: sourced answers or a refusal.
The Makes Eleven Letter
Once a month: what changed in AI for regulated work and what we would do about it. Short, specific, no filler.
It moves whether you watch it or not.
The ecosystem shifts weekly; your practice shouldn’t have to chase it. We do the watching, and once a month the Letter tells you what actually changed and what we would do about it — sourced, or not said.
Positions, in writing.
Why the diagnosis comes first, and why there is no rate card
Most AI engagements fail before the first line of configuration, because nobody mapped the workflow the software was supposed to run.
Read the note
Every failed automation project I've examined shares one property: the prescription came before the diagnosis. A tool was chosen, then a problem was found for it. We run the arrow the other way. Nothing gets proposed until we have mapped how work actually moves through the firm, and the map is a written deliverable you keep whether or not you continue.
That sequence is also why there is no rate card on this site. A published number is a promise made before the work is understood, and it fails in both directions: a national firm auditing every entity gets quoted as though it were a single office, or a six-person practice gets quoted as though it were an enterprise. Both are wrong. The scope has to exist before the number does, so we scope first and price to what we find.
What replaces the rate card is a discipline, not a mystery. The diagnosis is quoted up front and credited toward whatever follows. The proposal names the scope, the price, and a ceiling that holds for the term. Nothing gets billed that was not scoped, and nothing gets scoped that the diagnosis did not support.
The honest finding ("you don't need agents, you need a checklist and one hire") costs us the engagement and still gets written down. It appears in more diagnostics than you would think. If a proposal ever contains something the diagnosis doesn't support, you're holding the wrong proposal. That's the whole method.
We built for the CPA shortage on purpose
Roughly 650,000 actively licensed CPAs remain in the US, down from about 1.9 million in 2019. That is an architecture problem, not a staffing problem.
Read the note
The profession isn't coming back to its old headcount, and every firm that needs reviewed financials is competing for the same shrinking bench. You can pay more for the same hours, or change what the hours are spent on.
Our architecture does the second thing. Agents do the volume: categorization, reconciliation, assembly, chase. Licensed CPAs do what only they can: review, judge, approve, sign. The disclosure is printed in every engagement letter, because the model only works if the client knows exactly who did what.
The shortage is the market evidence for the whole design. A CPA reviewing agent-prepared workpapers covers a multiple of the clients they could serve preparing everything by hand, and the work they keep is what their license was for.
GAAP is a ladder, not a leap
Full GAAP on day one is over-prescription for most owner-led firms. The honest version is five rungs and an honest stopping point.
Read the note
GAAP is the reference standard buyers, lenders, and bonding agents actually use, which is exactly why it gets oversold. A firm with no exit on the horizon, no institutional financing, and no outside investors doesn't need ASC 842 workpapers; it needs reconciled accounts and a close that happens on a date.
So we sell a ladder: records → reconciled → accrual → GAAP-ready → diligence-ready. Clients enter wherever their books actually are, and full GAAP is triggered by something real (an exit inside two years, a covenant, a bond, an investor), not defaulted. No trigger? Stopping at rung three is the "never sell what you don't need" doctrine, applied to our own accounting build.
The rungs above stay lit for the day something real turns on. That's the difference between a ladder and a leap: you can stand on a ladder.
The news moves faster than a month.
The News page carries what we are reading as it lands — primary sources and measured data only.
What moved,
as it moves.
The developments and primary sources behind the positions we take — dated, sourced, and updated as the ecosystem moves. Curation rule: primary sources and measured data only. No vendor decks, no hype cycles.
Loading the news…
The Letter carries what it means.
News is what happened; the Letter is what we would do about it. Subscribe on the Letter page.
The engine arrived. The road didn't change.
Almost every firm has bought the tools. Very few have changed the work. That gap, not the technology, is the story of the last three years. It is why a small firm can now outrun a large one.
Rockets on a horse.
“We are, in many cases, bolting a jet engine onto a horse carriage — and wondering why it doesn’t fly.”
This is what most AI adoption looks like. The model is genuinely powerful. It is strapped onto a process shaped entirely by human limits: an eight-hour shift, a sequential handoff, an approval that waits for Monday.
The thrust is real. The animal underneath it is the constraint. You get a faster horse, a louder one, and an expensive one. The finish line does not move.
The tell is easy to spot in your own firm: the tool got adopted, everyone says it helps, and no line on the P&L moved.
A Formula One engine in city traffic.
“The engine’s power is there, but the full potential is squandered by the limits of the road.”
Suppose the technology is right and the deployment is competent. It still sits inside a process with a red light at every intersection: a queue, a weekly meeting, a shared inbox, a person who has to notice.
An agent that can work through the night is worth nothing if the next step waits until someone opens a folder on Tuesday. Throughput is set by the slowest gate, not the fastest actor. That is why pilots post a real speed gain on one step and no change in cycle time.
This is the diagnosis most firms never get: not which tool, but which intersection.
Fig. 02 · Throughput is set by the gate, not the engine
This is not a hunch. It is the most consistent finding in the field.
Three independent bodies of research, all pointing at the same gap between adoption and earnings. We publish the sources so you can check them.
Of organizations report using AI in at least one business function, up from 78% the year before. The tools are, effectively, everywhere. Source: McKinsey Global Survey on AI, 2025
Report any measurable effect on enterprise-level EBIT. Among those, most attribute under 5% of it to AI. Widespread use, narrow result. Source: McKinsey Global Survey on AI, 2025
Of enterprise generative-AI pilots studied delivered no measurable P&L impact. The authors attribute the divide to approach, not to model quality. Source: MIT Project NANDA, The GenAI Divide: State of AI in Business 2025
Two operating models, six design decisions apart.
Every firm sits somewhere on this table. Which model you bought matters far less than how the work was shaped before it arrived.
Comparison and the reported productivity ranges from Hofmann & Kruhse-Lehtonen, “The agent-centric enterprise,” Harvard Data Science Review, citing Noy & Zhang (2023), Riedl et al. (2023), OECD (2025), McKinsey (2025) and BCG (2025). The second column is the destination, not a promise. Which row you can honestly move is what a diagnosis is for.
Rebuild the road.
Nothing above is an argument against the technology. It is an argument about where the work happens. When the process itself is redesigned so an agent can act, with data reachable and gates placed deliberately, the same engine finally gets to run.
That redesign is a specific, ordinary, repeatable exercise. It has five moves, it takes weeks rather than quarters, and it starts with one workflow, not a transformation program.
It also has a boundary that never moves: the gates you keep are the ones that carry judgment, liability, or a signature. Those are not inefficiencies to be removed. They are the reason anyone trusts the output.
The point was never headcount. It was where your best people spend Tuesday.
This is the generational part: the engine that used to take an enterprise budget now answers to a firm of six, and the gap between what a small firm can field and what the market leader fields has never been narrower. The options keep multiplying — which is exactly why we stay on every trend, so our clients compete with the best technology available.
When agents handle routine execution, people move up to problem framing, trade-offs, stakeholder alignment, and leadership under uncertainty. You hired them to think, not to retype.
Manual work varies. A designed workflow sets a floor that holds no matter who is out. Consistency is worth more to a regulated firm than raw speed.
The measure shifts from return on investment to return on inference: what each unit of machine reasoning actually produced. Harder to fake than a license count, which is why we track it.
Autonomy is how much a system may do alone. Agency is how much your people can direct it. We build for agency and raise autonomy only where the evidence earns it. Never the reverse, never quietly.
Then it is worth thirty minutes.
Book the free conversation and bring the one workflow this page made you think about. We will tell you honestly whether it is a good candidate — including when the answer is no.
Audit. Gauge. Engineer.
Navigate. Track.
Five moves that take a workflow from “this is slow and nobody knows why” to “this is measurably better and the CEO believes the number.” Every engagement runs them in this order. Each stage ends in an artifact you keep.
The playbook doesn’t start with a workflow. It starts with what the business is for.
Picking a workflow first is how firms end up automating something that works fine. Four questions come before Audit, and they take an afternoon, not a quarter.
What is the firm actually trying to do this year? Everything downstream has to trace back to a line on this list or it doesn't get built.
What role should machines play here, and where should they not. This is where refusals get written.
Systematically, across the value chain, not from a vendor list. The biggest pain points are usually common knowledge; the work is confirming which are tractable.
Strategically important, but safe enough to experiment on. One workflow, chosen deliberately, not a transformation program.
Audit
“What is actually happening, and why does it fail?”
Understand how the work is done today and what outcome really matters, not what the process document says. Everything downstream inherits whatever this stage got wrong.
- Map goals, data, systems, roles
- Interview users; capture pain points
- Document desired outcomes, not just outputs
- Sit with the people doing the work, not only the people managing it
- Start from the relevant Workflow Atlas board so you edit a draft rather than face a blank page
- Record the gates that exist by design and the ones that exist by accident
A written picture of the as-is and the target outcome. Useful even if you stop here.
Gauge
“What would success look like for the business?”
Evaluate each workflow on impact, repeatability, complexity and outcome potential. This is the stage that decides what we will not build. A step that is high-risk, low-volume and dependent on judgment is a step that should stay exactly where it is.
- Score steps on repeatability and risk
- Estimate outcome upside
- Every step lands in one of five categories: automate, draft & Review, assurance, watch & Alert, or human-always
- The human-always register is written before anything is built, and it may grow but never shrink
- The success number is picked here: one number, agreed in writing, before work starts
A prioritized shortlist of agent opportunities, and a documented list of what we declined to touch.
Engineer
“If you started fresh with AI, what would this look like?”
Redesign and build the flow so an agent can act: data accessible, decisions explicit, handoffs deliberate. This is where the road gets rebuilt rather than repaved, and where most programs quietly skip ahead to tooling.
- Refactor the process for straight-through flow
- Build or configure the agent
- Define success metrics and guardrails
- Everything is built on the same five-stage spine: signal, enrich, score, compose, act
- Autonomy is set per task against our written reliability standard, not per system
- A separate examiner checks what the builder built; licensed professionals review anything regulated
A working agent-first process ready to pilot, with measurable success criteria attached to it.
Navigate
“Who decides what, and what happens when AI is wrong?”
Shape the human–agent relationship: transparency, intervention paths, governance. Assume the system will be wrong at some point, and design the moment of being wrong before it happens rather than after.
The framing that matters here: the system is not doing the regulated work. It is preparing expert work for controlled approval, which is why accountability stays where the risk is created.
- Add explainer UI, override and escalation paths
- Train staff on the new oversight roles
- Embed compliance checks
- Every output carries its sources, its confidence and the record of what it touched
- Signatures, filings and payments stay human. Printed in the contract, not just implied
- The people who will supervise the agents are in the room while it is designed, not briefed afterward
- Human review is a catalyst, not a brake: validated output earns a system more autonomy later
Human control that holds as autonomy rises, because the escalation path was built, not promised.
Track
“Would your CEO believe these numbers?”
Prove value against the outcome chosen in Gauge. Show the honest comparison: not just before and after, but what would have happened anyway.
- Instrument KPIs and dashboards
- Run A/B or before-and-after comparisons
- Feed learnings into the next Audit cycle
- Measured against your day-one baseline — a one-page before-and-after at day 30, then monthly
- A short dashboard on purpose: source, freshness, confidence, exceptions needing a human
- What proves out scales; what doesn't, we stop. Proof, then scale
Outcome gains that fund the next move, or a documented reason to stop. Both are results.
Five kinds of agent. The question is never “where can we use AI.”
It is “which kind of agent should own this step, and where does a human stay in control.” A taxonomy connects the technology to your actual pain points. Without one, every conversation collapses into tool shopping.
Taxonomy adapted from Hofmann & Kruhse-Lehtonen, “The agent-centric enterprise,” Harvard Data Science Review. The Guardian row is where our reliability standard lives: a separate examiner checks what the builder built.
The engine, in 43 seconds.
The five stages, run on one real workflow — watch what moves, where every number gets a weight, and where the human gate sits.
Read the film as text
Every agent we ship runs the same five moves — Signal, Enrich, Score, Compose, Act. Only two things ever change: what it watches, and what it may do. It starts with a signal: a recertification due in 45 days. Enrich: the file assembles itself from the tenant file, the prior certification, and the agency rule. Score: every claim gets a weight — 0.92 and 0.87 proceed; 0.41 falls below the threshold, so the answer is a question to a human. Compose: a draft that shows its sources, line by line. Act — only as far as the gate allows: the filing is sent by a person, never by the agent. The same engine, tuned to your firm, measured against day one.
Diagnose. Propose. Deliver. Compound.
The five stages above run inside a simple commercial arc — and every stage of it produces something you keep.
Diagnose
We map how work actually flows through your firm and put it in writing: what to automate, what to fix first, what to leave alone.
Propose
A written proposal with package options — only what the diagnosis supports. You choose; we never choose for you.
Deliver
Built to our written reliability standard, examined by someone other than the builder, reviewed by licensed professionals where the work is regulated.
Compound
Measured monthly against your day-one baseline. What proves out, scales. What doesn't, we stop.
Governed by design: every engagement ships with its boundaries in writing — the full architecture is on the assurance page.
And Track never really ends: a monthly review of what the ecosystem now makes possible feeds back into every engagement we run.
Support runs the same way — 24/7 on every maintained engagement, from a team on retainer staffed across time zones. Every fix is recorded in a repository of resolutions: the base we are building toward agents that clear routine issues before they reach a person, with the escalations staying human.
People are the other half of eleven.
The AI Committee Briefing — 50 minutes
For the committee that has to govern this: the fears named, the boundary between assembly and judgment, the autonomy tier ladder, the named seat, and what to do Monday. Built for law firms, useful to any regulated practice. Books directly; no diagnosis required.
Book it on the consultations page →
Workflow-anchored training
Built on your diagnosis and what we implement, so your people learn on their own work. Governance, acceptable-use policy, and standing office hours where the diagnosis supports them.
We build capability; we don’t certify it.
One workflow. Roughly eight weeks. Then you decide again.
The published sprint runs in three phases. We keep that shape because it forces a visible result early, while the people who will live with the system are still in the room.
Identify the high-value workflow, map its current state, and find where the time actually goes. Choose the one number that will decide whether this worked.
Build and deploy the first agent workflow, with attention on data accuracy and the routine work that consumes the day. Guardrails ship with it, not after it.
Scale what works, learn from what didn't, wire the oversight, prove the number. Then repeat on the next workflow.
Sprint structure adapted from Hofmann & Kruhse-Lehtonen, “The agent-centric enterprise,” Harvard Data Science Review. Scope, duration, and price are set per engagement; a six-person practice and a national rollout are never the same shape.
The Audit starts with a map.
The Workflow Builder is the first half hour of Audit, run by you, for free — and the free conversation is where the map becomes a plan.
Sign in to your
practice’s workspace.
Your firm’s atlas, its portal, and the four training quarters — in one place, for everyone on the membership.
Sign in
Use an email address and a password of your own.
Signing in confirms who you are. What it opens depends on what your firm has bought — see plans and refunds. By continuing you agree to the terms and the privacy policy.
Free without an account
The Workflow Mapper and one board in every vertical of the Workflow Atlas stay open to everyone, forever. No sign-in, no email, no trial clock.
One membership, the whole practice
A membership belongs to the firm, not to a person. Colleagues on your work domain join it themselves; nobody has to be provisioned a seat by hand.
No membership on this address yet.
You’re signed in — there just isn’t a membership attached to or to your firm. If a colleague bought one, ask them to add your address, or check you’re using your work account.
- A vertical. Its full atlas, its portal, and four quarters of training against your own work. Up to ten seats.
- Enterprise. Every vertical, including the ones added after you buy. Unlimited seats.
- Fourteen days to change your mind. On a first purchase, no questions asked.
Your workspace.
Choose a new
password.
This link works once. Setting a password here signs out every device that was signed in, including whichever one prompted you to do this.
That link is incomplete.
Open the link from your email in full — it carries a token that this page needs. If it has expired, ask for a new one.
Done.
Your password is set and every device has been signed out. Sign in with it.
What a conversation costs,
before you book one.
Every session is free to book. What costs money is the Audit itself — priced to your firm and the scope of the work, named in the session that carries its name and held to a written ceiling. How pricing works is here, not hidden on a calendar.
Piloting: say it so
the machine can carry it.
Nine fields, each one a lesson. Fill them honestly and the Studio assembles a production-grade prompt — test it here, copy it anywhere, and save the good ones to your firm’s shared library.
The Studio is free with an account.
Create a free account to use the nine-field composer and run five trial drafts against a model — enough to feel what a well-built prompt does. A membership opens drafting within the daily quota, your firm’s shared prompt library, and the portal behind it.
Ask your boards
Answered only from the workflow boards your membership opens — with the passage behind every claim, so you can check it before you use it.
Join your firm’s
membership.
A colleague has added you to their firm’s Makes Eleven membership.
Sign in first.
The invitation is tied to the email address it was sent to, so sign in with that address — or create an account on it — and then open your invitation link again.
Accept below and everything the firm’s membership opens is yours too.
Settings, membership
and how you sign in.
What your firm holds, who is on it, and the details that are yours to change.
You are not signed in.
Your account settings are behind sign-in, for the obvious reason.
Profile
Membership & billing
Password
This account has no password — you sign in with a provider, or you were invited. You can add one without losing the way you sign in now.
One portal.
The whole firm.
A membership belongs to the firm, not to seats. Everyone in it inherits what the firm bought — the full workflow atlas for your vertical, the portal's processes, four training quarters and the Prompt Studio.
Loading plans…
Nothing is on sale yet.
The catalogue is empty, which means no payment processor is configured on this deployment. Everything free stays free in the meantime: the Workflow Mapper, and one board in every vertical of the Workflow Atlas.
What every membership includes
- The full atlas for your vertical. Every board, not the one open board.
- The portal. Its processes, each with how far autonomy may go and the seat that can stop it.
- The Prompt Studio, shared across the firm. Prompts composed once, kept in a firm library, reused by everyone.
- Four training quarters, against your own work. Audit, Gauge, Engineer, Navigate & Track — and in the Law vertical, a profession-specific curriculum (The Boundary · Data Hygiene · Confidentiality and Privilege · Verification Discipline), structured to support CLE where your jurisdiction permits.
- Up to ten seats on a single vertical; unlimited on enterprise. Colleagues on your work domain join themselves.
- No trial clock. The free material is permanently free, so you can judge it before paying rather than during.
Prices in US dollars, billed per firm. By subscribing you agree to the terms, the privacy policy and the practice disclaimer — which says plainly that this is operational guidance for running a practice, not legal, tax, accounting or compliance advice.
Trained on your work, not on slides.
Four quarters run against your own workflows — the boards in your atlas, the prompts in your firm’s library. What a team learns on its own work, it keeps.
Terms of service.
What a Makes Eleven membership is, what it isn’t, and what each of us owes the other.
Last updated 20 August 2026. These terms govern memberships bought at makeseleven.com. Your engagement letter, if you have one, governs consulting work and takes precedence where the two disagree.
1. Who is agreeing
“We” and “Makes Eleven” mean Makes Eleven Consulting, a District of Columbia entity. “You” means the firm or organisation that buys the membership. If you accept these terms on behalf of a firm, you are confirming you may bind it. Individuals who sign in under that membership are covered by it and bound by it.
2. What a membership grants
A membership is a limited, non-exclusive, non-transferable licence to use the atlases, portals, training material, specifications and templates in the scope you bought, for the internal business of your own firm, for as long as the membership is active.
Scope is the vertical or verticals you paid for. An enterprise membership covers every vertical, including verticals published after your purchase, while it stays active.
3. What it does not grant
- No right to republish, resell, sublicense, or distribute the material outside your firm — including to clients, in a product, or in a deliverable sold on.
- No right to use the material, in whole or in part, as training data, fine-tuning data, or retrieval corpus for any machine learning model or AI system, whether yours or a third party’s.
- No right to bulk-extract, scrape, or mirror the material, or to build a competing atlas, portal or training product from it.
- No right to share sign-in credentials, or to use one seat to give access to people outside the firm.
Reading, adapting and using a workflow inside your own practice is exactly what the membership is for. Handing the material to someone who has not bought one is not.
4. Seats and administration
A single-vertical membership carries up to ten seats. An enterprise membership carries unlimited seats. A seat is one named person; seats are not shared or rotated between people on the same day.
The first person to buy becomes the firm’s owner and administers it: inviting colleagues by email address, or opening automatic joining to anyone on a verified work email domain, and removing people who leave. Consumer email domains cannot be used for automatic joining. Removing a person frees their seat.
5. Who owns what
We own the atlases, the portals, the training, the agent specifications, the method and everything on this site, along with all improvements to them. You own what you make with them: your maps, your registers, your configurations, the systems you build, and your data.
If you send us feedback, we may use it to improve the product without owing you anything for it. We will not publish your firm’s name as a customer without asking you first.
6. This is not professional advice
The material is operational guidance for running a practice. It is not legal, tax, accounting, audit, compliance, investment or medical advice, and buying a membership does not create an attorney–client, accountant–client, fiduciary or any other professional relationship.
You stay responsible for your own regulatory and professional obligations, for the confidentiality of your clients’ information, and for everything that leaves your building. Where a workflow touches a filing, a signature, a payment, a tax position or a client deliverable, a qualified human at your firm decides — which is the same rule we build every system to, and the reason each process names the seat that can stop it. See the practice disclaimer.
7. Acceptable use
Don’t attack the service, don’t try to reach content your membership doesn’t cover, don’t misrepresent your firm or your seat count, and don’t use the material to build something that harms the people whose work it describes. We may suspend access for any of these, and will tell you why.
8. Payment
Memberships are billed monthly or annually in advance through Stripe, and renew automatically until cancelled. Prices are per firm, not per seat. We may change prices for future terms with at least thirty days’ notice; your current term is never repriced mid-term. Taxes are yours where they apply. Refunds are covered by the refund policy, which forms part of these terms.
9. Ending it
You may cancel at any time, from your billing page or by email; access continues to the end of the period you have paid for. We may end a membership for a material breach of these terms, after telling you what the breach is and giving you fourteen days to fix it, or immediately for the attacks and misuse described in section 7.
When a membership ends, access to paid material ends with it. Your own account data and training progress are exported on request and deleted within thirty days of the request. Anything you built with the material remains yours to keep using.
10. Availability
We aim to keep the service up and will give notice of planned maintenance where we can, but we do not promise a specific uptime figure, and we would rather say that plainly than publish one we cannot hold to. The material is provided as it is; we do not warrant that any particular workflow will suit your firm.
11. Liability
To the extent the law allows, neither of us is liable to the other for indirect, incidental, special or consequential loss, or for lost profits, revenue, data or goodwill. Our total liability arising from a membership is limited to the fees you paid in the twelve months before the claim. Nothing here limits liability for fraud, or for anything that cannot lawfully be limited.
12. Changes to these terms
We may update these terms. If a change materially reduces what you get, we will tell you by email at least thirty days before it takes effect, and you may cancel and take a pro-rated refund of the unused term rather than accept it. The date at the top always reflects the current version.
13. Governing law
These terms are governed by the laws of the District of Columbia, without regard to its conflict-of-laws rules, and the state and federal courts sitting in the District of Columbia have exclusive jurisdiction over any dispute arising from them. Makes Eleven Consulting is organised in the District of Columbia; we work nationwide, but this is where a disagreement gets settled.
14. Contact
Questions about these terms: get in touch.
Privacy policy.
Short, because there is little to declare. We collect what a membership needs to work, and nothing to sell.
Last updated 20 August 2026.
What we collect
- Your account. Email address, name, and firm — whatever the provider you sign in with (Google, Microsoft, Apple, LinkedIn, or a firm’s own identity provider) returns, or what you type if you use an email and password instead. We do not receive your password from any provider.
- Your membership. What your firm bought, when, and whether it is active. Card details go straight to the payment processor — Stripe or PayPal, whichever you choose — and we never see or store them.
- Your progress. Which training modules you have completed, minutes recorded, and certificates issued.
- What you map. Anything you build in the Workflow Mapper stays in your own browser unless you choose to send it to us. Sending is a form you fill in deliberately — your email address and, if you include it, the map itself — and it goes into our own database, nowhere else.
- What you send us. A newsletter signup, a message from the contact form, or a map you chose to share: the address and the message, kept until you ask us to delete them, used to reply and for nothing else. No list is sold, shared or enriched.
- Server logs. Cloudflare keeps short-lived request logs, as any host does.
What we do not collect
No analytics. No advertising pixels. No third-party trackers. No session recording, heatmaps or fingerprinting. No cross-site profiles. This is unusual enough to be worth stating, and you can verify it — open your browser’s network panel on any page of this site and there is nothing to see beyond Cloudflare’s Turnstile challenge on the sign-in and submission forms, which exists to keep bots out and identifies nobody.
Cookies
One cookie, m11_sess, which keeps you signed in across makeseleven.com and its portals. It is HttpOnly, Secure and SameSite=Lax, and it holds a random token, not your identity. A second short-lived cookie exists only during the seconds a sign-in is in flight, and is deleted when it completes. That is the entire list.
Why we hold it
To let you in, to know what your firm has bought, to keep your training progress, to take payment, and to answer you when you write to us. We do not sell personal data, and we do not share it for advertising — there is no advertising.
Who else processes it
- Cloudflare — hosting, the database your account lives in, and the Turnstile bot check on forms.
- Stripe or PayPal — payments and billing, whichever processor you choose at checkout.
- Google, Microsoft, Apple, LinkedIn, or your firm’s own identity provider — only the one you choose to sign in with, and only to confirm it is you.
- Our AI model provider (or, where a firm connects its own key, that firm’s chosen provider) — only when a member uses the AI drafting and ask-your-boards features; the prompt and the answer pass through, and our provider agreements do not permit training on them. The name of the provider currently in use is available on request.
When we send email — a password reset, a receipt, a reply to something you sent — it goes through Resend, a transactional email provider, which sees the address and the message it is delivering and nothing else.
That is the complete list of processors. If it changes, this page changes with it.
How long we keep it
Account and progress data while the membership is active, then for thirty days after it ends, then deleted. Payment records are kept as long as tax and accounting law requires. Sign-in sessions expire on their own.
Your choices
Ask us and we will show you what we hold, correct it, export it, or delete it. Deletion removes your account, your identities and your progress; it does not remove the invoices we are required to keep. Depending on where you live you may have these rights by law — we extend them to everyone regardless.
Children
This is a product for professional practices. It is not directed at anyone under 18 and we do not knowingly collect their data.
Contact
Any privacy question, including a deletion request: write to us and a person will answer.
Refunds and cancellation.
Stated here and on the plans, so nobody discovers it after paying.
Last updated 20 August 2026. This policy forms part of the terms of service.
Fourteen days, no questions
If a membership is your firm’s first purchase and it isn’t what you expected, tell us within fourteen days of the charge and we refund it in full. You do not have to justify it, and we will not try to talk you out of it. The refund reaches your card within five to ten business days, depending on your bank.
After fourteen days
Cancel whenever you like. Access continues to the end of the period you have already paid for, and nothing further is charged. We do not pro-rate an annual term back to you part-way through — annual is priced at ten months for twelve, and that discount is the trade for committing to the year.
What we will always refund
- A duplicate or mistaken charge, in full, as soon as you point it out.
- A renewal you did not intend, if you tell us within thirty days of it and have not used the membership in that period.
- The unused part of a term, pro-rated, if we materially reduce what a membership includes or end it for a reason that isn’t your breach of the terms.
Why there is no free trial
Because a trial clock is a worse offer than what is already open. One board in every vertical of the Workflow Atlas — fourteen boards — and the whole Workflow Mapper are free permanently, with no account and no email address. Look at those first. If they are not useful to you, a membership will not be either.
How to ask
Write to us from the address on the membership, or cancel from your billing page at any time. A person reads it, and a person answers.
The practice disclaimer.
The one that matters most, given who is reading. Guidance for running a practice is not advice about practising.
Last updated 20 August 2026. This disclaimer forms part of the terms of service and applies to this site, the Workflow Atlas, the Workflow Mapper, every portal, and all training material.
Not professional advice
Everything we publish describes how work moves through a practice — where a file goes, who checks it, which steps repeat, where a system could help. It is operational guidance.
It is not legal advice, not tax advice, not accounting or audit advice, not investment advice, not compliance advice, and not medical advice. It does not tell you what position to take, what to file, what to sign, what to advise a client, or how a rule applies to a set of facts. Those are professional judgments, and they belong to a qualified person who knows the matter.
No professional relationship
Reading this material, buying a membership, mapping a workflow, or completing the training creates no attorney–client relationship, no accountant–client relationship, no fiduciary duty and no engagement of any kind. Nothing you send through this site is privileged or confidential in the professional sense. If you need advice, retain someone to give it to you.
Your obligations stay yours
Your bar, your board, your regulator, your insurer and your clients hold you to your duties — competence, supervision, confidentiality, conflicts, record retention, client communication and the rest. Adopting a workflow from us does not transfer any of it. Where a duty and a workflow disagree, the duty wins, and we would rather you changed our workflow than bent your obligation.
The human is always the last step
Every process we publish names the seat that can stop it, and sets how far autonomy may go and no further. That is not decoration. Nothing built from this material should sign a filing, take a tax position, move money, issue an opinion, or send work to a regulator, a court or a counterparty without a qualified human deciding. The register of what our systems refuse to do grows; it never shrinks.
What the numbers mean
Where we cite results — from published case studies or from practitioners — they are labelled as what they are: reported by the people who ran them, not measured by us, and not a forecast for your firm. Our own claims are always a delta against a baseline recorded at the start of the work, shown to the client who owns it. We publish no statistic we cannot source.
Borrowed frameworks are attributed
Parts of the method sit on published work by other people — among them Hofmann and Kruhse-Lehtonen’s writing on the agent-centric enterprise in the Harvard Data Science Review. Where we teach someone else’s framework we say whose it is. The credibility is in running a published standard well, not in claiming to have invented one.
Accuracy
We keep this material current and correct it when we find it wrong. Practice rules change, technology changes faster, and something here will eventually be out of date before we notice. Check anything you are about to rely on.