Parses onboarding docs, runs the rules engine, screens sanctions/PEP, flags gaps. Same source as the kyc-screener Cowork plugin — this directory is the Managed Agent cookbook for POST /v1/agents.

Deploy

export ANTHROPIC_API_KEY=sk-ant-...
export SCREENING_MCP_URL=...
../../scripts/deploy-managed-agent.sh kyc-screener

Steering events

See steering-examples.json.

Security & handoffs

Onboarding documents are untrusted. Three-tier isolation:

Tier	Touches untrusted docs?	Tools	Connectors
`doc-reader`	Yes	`Read`, `Grep` only	None
`rules-engine` / Orchestrator	No	`Read`, `Grep`, `Glob`, `Agent`	screening (read-only)
`escalator` (Write-holder)	No	`Read`, `Write`, `Edit`	None

doc-reader returns length-capped, schema-validated JSON. escalator produces ./out/escalation-<packet>.xlsx.

Not guaranteed: this agent recommends a risk rating; the compliance officer decides.