Most of a KYC case is preparation: reading documents, typing fields, walking a registry, screening names, adding up risk points and writing a memo. Very little of it is judgement. That makes KYC a good fit for AI agents, and a dangerous one, because the small part that is judgement is exactly what a supervisor will ask about. The design question isn’t whether agents can do the work. It is which decisions they must never take, and how that is enforced rather than promised.

In short

  • Give each agent one job on the case. Ten agents, each with a narrow role: read documents, walk the registry, screen, rate, draft the memo, and so on.
  • Agents prepare; people decide. Anything that reaches the customer, clears a match, waives a check or decides the case is a prepared decision a person accepts, rejects or questions.
  • Autonomy is a dial with a ceiling. Every action starts at “Draft”. It can move up only on evidence that people agree with it, and never above the tenant’s ceiling.
  • Facts come from the case, not the model. Every figure an agent writes must exist in the case’s facts, or the model’s answer is rejected and the agent falls back to its rules.

Ten agents, one case

InsightKYC runs ten agents. Nine work a case in order; the tenth watches the customer book.

AgentWhat it doesWhat it can prepare for a person
IntakeChecks the documents the case needs against what the customer suppliedA request to the customer for what is missing
Document readerReads passports, licences, proofs of address and company papers into fields, each quoted from its lineDocuments it couldn’t read, for review
OwnershipWalks the registry to find beneficial owners at the threshold and compares them with the declarationA request about undisclosed owners or officers
VerificationRuns identity, address and company checks: expiry, name, date of birth, MRZ check digits, registry statusA request to fix what failed
ScreeningScreens every party against sanctions, PEP and adverse media and proposes a disposition for each matchIts proposed dispositions, never for a strong sanctions match
RiskRates the customer on the points model— (rating is deterministic; a lead overrides)
EDDDecides whether enhanced due diligence is needed and what to askA source-of-funds and source-of-wealth request
Case writerDrafts the memo from the checks, screening, ownership and riskThe memo, for the analyst to accept or edit
SupervisorReads the controls and says whether the case is ready, and what is in the waySubmitting the case for a decision
MonitoringReads active customers’ transactions against what they declaredOpening reviews for the alerts it raised
The agent catalogue: the KYC agents grouped by collect and read, verify and screen, rate and decide, and monitor the book, each with what it does, the action it prepares, its starting level, and what it never invents
The catalogue. Each agent’s job, the action it prepares, the level it starts at, and the one thing it never invents.

What no agent does

The line between preparing and deciding is drawn around actions with consequences outside the case, or that a regulator would expect a named person to own:

ActionWhoWhy
Send anything to the customerA person, from a held requestWhat the bank asks a customer is a communication on its behalf
Clear a strong sanctions matchA person, with a reasonThe cost of a wrong clearance is the highest in the programme
Waive a failed checkA person, with a reasonA waiver is a judgement that the evidence is good enough
Override a risk ratingA lead, with a reasonThe rating sets the diligence and the approver
Approve or decline a caseAn analyst, or a second lead for high risk and PEPsThe decision is the bank’s, and it goes on the decision record

Enforced in code, not in a prompt

These actions aren’t forbidden by telling the model not to do them. The agents simply have no way to do them: the functions that send, waive, override and decide take a person as the actor, and the routes check the person’s role.

A prepared decision

When an agent finds something only a person can act on, it prepares a decision: a title, the lines of evidence, why it thinks so, and the action that will happen if the person accepts. The person has three answers.

Accept

Reject

Ask

Agent finds
something to act on

Prepared decision
evidence, reason, proposed action

A person answers

The action runs
e.g. request drafted and held

Nothing happens
the rejection is recorded

A question goes on the case
the agent can be run again

Decision record
who answered, when, what

Every answer, including a rejection, is recorded. Rejections are how the agents’ autonomy is held down.

The Agents tab on a case: prepared decisions waiting on the analyst, such as asking the customer for enhanced due diligence evidence, using the drafted memo and disposing of a screening match, each with Accept, Reject and Ask, and the last run's steps on the right
The Agents tab. What is waiting on you, with Accept, Reject and Ask, and beside it what each agent did on the last run.

Even accepting doesn’t send anything to a customer. Accepting the intake agent’s request creates a request held for review on the Requests tab, where the analyst edits the wording and sends it. Two deliberate steps, because a message to a customer is hard to take back.

Autonomy is earned, per action

Each action has a level, and every action starts at the lowest:

LevelNameWhat happens
L1DraftThe agent prepares a draft; a person does the work
L2Ask firstThe agent prepares the decision and asks a person before it acts
L3Act and tellThe agent acts and tells the person, who can pull it back
L4ActThe agent acts on its own

In InsightKYC the tenant’s ceiling is L2, so no KYC agent acts on its own whatever its record. Within the ceiling, an action moves up only when people have agreed with at least 90% of its last 20 prepared decisions, and moves down at once if agreement falls below 70%. An administrator can lower the ceiling further for any agent.

The autonomy page: how much the agents may do, the tenant ceiling of L2 Ask first, the L1 to L4 levels with L3 and L4 locked, and each agent's actions with their current level and agreement over 30 days
Autonomy. The ceiling, the levels above it locked, and each action’s level with the agreement that would move it.

The model is optional; the facts are not

Each agent has a rules path that works with no language model at all: the demo runs with the model switched off, and every screenshot here comes from that mode. When a model is switched on, it can phrase the reasoning and the memo better, but its answer is checked: every number and name it writes must exist in the facts the agent gave it. An answer that introduces a figure the case doesn’t contain is rejected, the rules answer is used instead, and the step is marked so a person can see it happened.

GENERATIVE The model writes the memo

Fluent, and occasionally wrong: a percentage that isn’t in the registry, a date that isn’t on the passport. Nobody can tell which sentences to trust.

GROUNDED The model phrases facts the case already holds

Every figure is checked against the case’s facts. An ungrounded answer is discarded and the rule-based draft is shown instead.

Who does what on a case

A case with the agents runningOwners in the tag
1
Run the agentsanalyst

The nine case agents run in order; each records what it did, what it found and how long it took.

2
Answer what was preparedanalyst

Accept, reject or ask on each prepared decision. Answers go on the decision record and count towards each action’s agreement rate.

3
Do the judgement workanalyst

Dispose of matches, waive or resolve checks, send held requests, edit the memo.

4
Run againanalyst

When the customer answers or the case changes, the agents run again on the new facts.

5
Decideanalyst or second lead

The supervisor agent says when nothing blocks; the decision is a person’s.

What it means for each audience

For the CCO & MLRO

The boundary between automation and judgement is written into the product, not into a procedure manual. Every agent action has a level, an owner and a history.

When a supervisor asks “who decided?”, the answer is always a named person.

For the KYC operations lead

Analysts start each case with the reading, checking, screening and drafting done, and a short list of decisions waiting.

Agreement rates tell you which agents to trust more, and which rules need work.

For the board

AI shortens onboarding without moving accountability. That is the version of AI in compliance that survives an examination.

Autonomy can rise later, on evidence, within limits the bank sets.

What to be careful about

  • Agreement can be lazy. If analysts accept everything, the agreement rate rises without meaning anything. Sample accepted decisions as you would sample dispositions.
  • Agents inherit the data’s gaps. An agent can’t find an owner the registry doesn’t record. The prepared decision says what it looked at; read that.
  • Raising the ceiling is a governance decision. Treat it like a policy change, with an owner, evidence and a date to look again.

Let agents do everything that is preparation. Make sure they can’t do anything that is a decision.

Narrow roles, prepared decisions, autonomy earned on evidence under a ceiling, and every figure checked against the case.

Keep reading