AI agent for compliance officers
Third-Party Due Diligence Agent
Every third party screened and rated before onboarding
What it does
Third parties such as agents and distributors are a common source of bribery and sanctions risk, and checking them properly takes time. When a new third party is proposed, or an existing one is due for review, this agent runs due diligence. It collects the questionnaire, ownership details and certificates, screens the company and owners against sanctions and adverse media, and scores risk by country, service and government contact. It checks answers against outside sources. If information is missing, such as owners over 25%, or a screening hit is unresolved, it drafts follow-up questions and rescreens with new details. It writes a report with a risk rating and conditions. The compliance officer approves all high-risk parties. Edge case: an owner shares a name with a sanctioned person, so the agent checks date of birth and country.
How it works
Follow the arrows from top to bottom. The orange dashed arrow is the loop: when a check fails, the agent goes back and tries again.
Read the steps as a list
- Third party proposed
- Collect questionnaire and ownership details
- Screen sanctions and adverse media
- Score risk
- Are answers complete and screening hits resolved?If not: draft follow-up questions and rescreen. Back to step 3.
- Write report with conditions
- Compliance officer approves high riskThe agent waits here for your OK.
- Third party record updated
How it decides
It scores risk on country, service type and government contact, and requires clear screening results.
- Sanctions name match: verify identifiers
- Government-facing agent in high-risk country: high risk
- Missing ownership over 25%: incomplete
Make it yours
Every agent is a starting point. You choose these settings for your own situation.
- Risk factors
- Review frequency
- Screening sources
- Report template
What keeps you in control
It always asks you first
- High risk onboarding
- Rejecting a third party
Hard limits
- Never approves high risk parties
- Never contacts the party without approval
It stops when
- Done: report filed
- Stop: true sanctions match
Set it up
We guide you through the set-up, step by step
Members get the full set-up guide for this agent. No technical skills needed: you copy, paste and upload.
- One set of instructions to paste into your AI, with the clicks for ChatGPT, Claude, Microsoft 365 Copilot, Gemini and Grok
- The agent then walks you through connecting your own data, one source at a time
- A downloadable copy with the flow chart, the rules and the full guide
