Complete AI Training
Sign inGet my AI kit

Your job's AI kit

Get your AI kit

Tell us who you are and what you do. We show you your kit right away and email you the link: skills, prompts, AI agents, MCP servers and courses for your job.

500+ jobs ready, and we make a kit for any other job. No payment needed to look.

Share

AI agent for credit analysts

Credit Policy Change Impact Agent

A clear list of loans and deals affected by each policy change

Credit Policy Change Impact Agent: what goes in, what the agent does and what you get

What it does

When credit policy changes, nobody knows how many existing loans and pipeline deals it touches until someone checks them one by one. This agent finds the effect. It compares the old and new policy and lists each changed rule, such as a lower maximum loan to value or a new industry limit. It turns each rule into a test and runs it over the portfolio and the pipeline. It lists loans that no longer meet a rule and pipeline deals that need changes. It checks its own tests by sampling a few loans by hand and fixes any misread rule before rerunning. The analyst and credit officer decide how to handle existing loans. Edge case: a rule applies only to new loans, so the agent keeps existing loans out of the exceptions list.

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.

Start and resultWhat it doesA check on its own workWaits for your OKGoes back and retries
Yes, continueApprovedNo 1 STARTS WHEN New policy published 2 USES A TOOL Compare old and new policy 3 DOES Turn changed rules into tests 4 USES A TOOL Run tests on portfolio and pipeline 5 CHECKS THE RESULT Do sample loans confirm the tests are right? If not: fix the rule test and rerun. Back to step 3. 6 YOU APPROVE Credit officer decides on handling 7 RESULT Impact report
Read the steps as a list
  1. New policy published
  2. Compare old and new policy
  3. Turn changed rules into tests
  4. Run tests on portfolio and pipeline
  5. Do sample loans confirm the tests are right?If not: fix the rule test and rerun. Back to step 3.
  6. Credit officer decides on handlingThe agent waits here for your OK.
  7. Impact report

How it decides

It converts each changed rule into a data test and applies it to loans in scope.

  • Rule applies to new loans only: test pipeline only
  • Existing loan fails new rule: list for next review
  • Pipeline deal fails: notify the loan officer

Make it yours

Every agent is a starting point. You choose these settings for your own situation.

  • Portfolio segments in scope
  • Sample size for checks
  • Who gets pipeline notices
  • Report layout

What keeps you in control

It always asks you first

  • Handling plan for affected loans
  • Notices to loan officers

Hard limits

  • Never changes loan terms
  • Never interprets policy beyond its text

It stops when

  • Done: impact report delivered
  • Stop: policy wording ambiguous, ask policy owner

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.

10 minto set it up in your AI
5 AIsChatGPT, Claude, Copilot, Gemini, Grok
  • 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
Get access to this agent

An example run

What happensA new policy cut maximum loan to value for hotels from 70% to 65%. The agent found 8 existing hotel loans and 2 pipeline deals above 65%. A sample check failed: it had used original appraisals instead of current values. It reran with current values and the count dropped to 6 loans. The credit officer approved reviewing them at their next renewal.

More agents for credit analysts