AI agents in banking · The build map · Brief 13

AI-generated code & coding agents: a design brief for banks.

Last updated Sep 17, 2026 · standard answers for this use case · adjust them in the map

AI-generated code is the agentic use case most banks already run and the one with the thinnest rulebook. No regulator has written a rule for software produced by a model, but the expectations are not empty: New York DFS told regulated entities in May 2026 to put human review on AI-generated code before deployment, validate inputs and restrict script execution; NIST profiled the secure software development life cycle for AI models and AI-integrated systems in SP 800-218A; the April 2026 model risk guidance decides whether something the agent produced counts as a model; and third-party guidance covers the coding platform and the foundation model behind it. The design problem is therefore enforcement, not policy. A bank's architecture rules — approved libraries and services, data-classification boundaries, logging, authentication patterns, no direct writes to the core — already exist for people. The system that survives an examination applies them to the agent mechanically: the rules are encoded as checks the agent cannot bypass, every change carries the prompt, the model, the diff and the reviewer, and a person with authority approves anything that reaches production. The agent accelerates the work inside the guardrails; it never moves them.

WorkflowPrompt chainingTier 2: act with approvalautonomy level 2

AI-generated code & coding agents: The model prepares and may act within limits; a person approves anything that reaches a customer or cannot be undone. Several model calls orchestrated by your code, in a sequence or a graph you designed. Material but recoverable. The model may prepare and, within limits, act, with a person approving anything that leaves the bank or touches a customer.

PatternWorkflow. Your code lays out the steps, the cost of error is real, and you need to observe every step.Prompt chainingEach step's output is the next step's input, with a programmatic check between them.KnowledgeRetrieval over the governed document set, with a citation on every answer and a refusal when nothing relevant is found. Tool calls to the system of record for anything live. Never retrieval for a balance, a case status or a limit. Documents to reason with, systems to check against: the workflow decides which question goes where before the model answers.Delivery routeThrough a cloud platform: two third parties in the chain and a concentration question; often the faster route through security review.

Which steps belong to a person, the model and a system?

A PERSONTHE MODELA SYSTEM1
Encode the architecture rules as executable checks
2
Scope what the agent can reach
3
Generate the change
4
Run the gates
5
Review and approve
6
Classify what was built
7
Deploy under change management
8
Monitor and learn
#StepOwnerNote
1Encode the architecture rules as executable checksA systemLinters, policy-as-code, dependency allow-lists, secret and data-boundary scanners, run in CI on every change regardless of author; the rules a reviewer used to hold in their head.
2Scope what the agent can reachA systemRepository, branch and tool permissions per task; no production credentials, no core-system endpoints, an allow-listed dependency registry; the constraint NIST's agent-security work describes.
3Generate the changeThe modelFrom a ticket and the codebase, in a branch; the prompt, model version and retrieved context are recorded with the diff.
4Run the gatesA systemBuild, tests, static analysis, the architecture checks and a licence and provenance scan; a failed gate returns the work to the model or the engineer, never to production.
5Review and approveA personAn engineer with authority over that system reads the diff and the gate results and approves; the record names them — the DFS expectation stated in May 2026.
6Classify what was builtA personIf the change implements or alters a complex quantitative method, it enters the model inventory and validation under the 2026 guidance; otherwise it is software under change management.
7Deploy under change managementA systemThe existing release process, with the AI-assisted origin flagged so incident review and audit can trace it.
8Monitor and learnA systemDefect, vulnerability and rollback rates for AI-assisted changes tracked against the baseline; rules tightened where the agent keeps failing a gate.

Which control layers carry the weight?

Governance and accountabilityCOREIdentity and entitlementsCOREAction gatewayCOREData and knowledgeCOREModels and vendorsCORERuntime and orchestrationSTANDARDObservability, evaluation and auditSTANDARDHuman oversight and escalationSTANDARD

Each layer is described, with its controls and documents, on the control plane page.

Which rules and guidance does this design answer to?

DocumentAuthorityWhy it applies hereStatus
DFS Frontier AI Models Industry Letter (May 2026)NY DFSHuman review of AI-generated code before deployment, input validation and restricted script execution — the one US expectation stated by name.In force
NIST SP 800-218A (SSDF profile for generative AI)NISTThe secure-development life cycle extended to AI models and AI-integrated systems; the standard to cite for the review gate.In force
SR 26-2Federal ReserveDecides whether what the agent produced is a model: complex quantitative methods are validated, deterministic code is not — but the boundary must be documented.In force
SR 23-4Federal ReserveThe coding platform, the foundation model and any hosted tools are third-party relationships with due diligence, contract and monitoring duties.In force
NIST AI 600-1 (Generative AI Profile)NISTConfabulation, information security and value-chain risks for the generative system writing the code.In force
CAISI RFI on AI agent security (2026)NISTConstraining and monitoring what a coding agent can reach; indirect prompt injection through repositories and dependencies.Proposed
23 NYCRR Part 500NY DFSFor New York-regulated banks, the change-management, access-control and certification obligations the code gate sits inside.In force
SB 26-189Colorado AI ActColorado: notice, explanation and human review for consequential automated decisions from Jan 1, 2027.Final
BCBS Third-Party Risk Principles (Dec 2025)Basel CommitteeNth-party supply chains and concentration on cloud providers.In force
BCBS ICT Risk Management Report (June 2026)Basel CommitteeHow supervisors look at ICT and cloud dependencies.Final
OCC Bulletin 2026-13OCCFor a national bank, the OCC's copy of the 2026 model-risk guidance.In force
NIST AI RMF 1.0NISTThe voluntary Govern, Map, Measure, Manage frame for everything model-risk guidance leaves out.In force

How will you know it works, before and after launch?

CODE CHECKS50%JUDGE MODEL30%HUMAN REVIEW20%
  • A golden dataset of at least 150 real cases with expected outputs, including adversarial inputs: wrong documents, unusual formats, prompts that try to change the task.
  • Code-based checks on every output: schema conformance, required fields, reconciliations against the system of record. Threshold: 99% or better before launch, every run in production.
  • Citation checks: every factual claim resolves to a passage in the governed set; unsupported claims below 2% of answers.
  • Trace evals per step, not only end to end: which step fails, how often, at what cost, so a prompt or model change can be judged step by step.
  • The same suite reruns on every prompt change, model version change and retrieval change; a regression blocks the release. That is what ongoing monitoring and outcomes analysis mean in model-risk terms.

Where must a person be in the loop?

  • Per-action approval by a competent reviewer for anything customer-facing or irreversible; sampled review for the rest.
  • Validation proportionate to materiality, with monitoring for drift on inputs and outputs.
  • An escalation route to a person that the customer can reach in one step.
  • Monthly review of the evals and the exception log by the accountable owner.
  • Trusting review to a second model: DFS asked for human oversight of AI-generated code, and an examiner will ask who the human was.
  • Letting the agent hold credentials or reach the core directly; the blast radius of a wrong action is the whole reason for the permission scope.
  • Treating every generated artefact as 'just code': a scoring formula or a monitoring threshold the agent wrote is a model under the 2026 definition and needs validation.
  • Forgetting the platform is a vendor: the coding assistant, the model and any hosted tools sit under third-party guidance, including what the provider does with the bank's code and data.
  • Skipping provenance: without prompt, model version and context in the record, the change cannot be explained at an incident review or reproduced for an audit.

What will a validator or an examiner ask?

  1. Where is this system in your inventory, what tier did you assign, and who signed it off?
  2. What counts as a model here, and what does your validation cover for the parts that are not?
  3. Show me the data lineage behind the retrieval set and the training or tuning data.
  4. What can the system do without a person, and where is that written down?
  5. How do you know it is still working: which evals run, how often, and what happened the last time one failed?
  6. What did you do about the vendor: due diligence, contract, exit plan, concentration?
  7. Walk me through one wrong output from production and what the customer, if any, saw.
  8. Who can switch it off, and has that been tested?

What it does: writes, reviews and ships code with AI assistance under the bank's architecture rules; the model prepares and may act within limits; a person approves anything that reaches a customer or cannot be undone.

Pattern: workflow (prompt chaining); tier 2: act with approval.

Rules it answers to: 4 documents across US, each linked in the brief.

How we know it works: a golden dataset, automated checks on every release, and human review at the level the tier demands.

What could go wrong and who answers: the accountable owner, the kill switch, the escalation route.

Every rule this brief cites, the morning it changes.

agent deployments, regulator positions and the day's six stories · in your inbox by 7 am ET · free

plus every tracker, bank and agent page update, the morning after · leave any morning