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 risk managers

Industry Risk Watch for Credit Portfolio Agent

Connect industry events to borrowers early and flag those at real risk.

Industry Risk Watch for Credit Portfolio Agent: what goes in, what the agent does and what you get

What it does

A supplier collapse or a new tariff hits a whole industry, but the credit team often hears about it only when a borrower misses a payment. This agent watches news and data feeds for each industry in the portfolio. It maps each event to the borrowers in that industry, scores the exposure by loan size, rating and how directly the borrower is affected, and drafts a watch list. For the top names, it checks the latest borrower financials for early signs, such as falling margins or weak cash. If the data shows no effect, it lowers the watch level. The head of credit approves any rating change.

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 Daily scan begins 2 USES A TOOL Collect news and data for each industry in theportfolio 3 DOES Select events that could affect credit quality 4 USES A TOOL Map each event to borrowers and loan balances 5 DOES Score exposure by size, rating and degree ofdependence 6 USES A TOOL Read the latest financials for the top exposures 7 CHECKS THE RESULT Do the financials show an effect from the event? If not: lower the exposure score and note why, thenrescore. Back to step 4. 8 DOES Draft the watch list with suggested actions 9 YOU APPROVE Head of credit approves any rating change 10 RESULT Weekly watch list and exposure summary
Read the steps as a list
  1. Daily scan begins
  2. Collect news and data for each industry in the portfolio
  3. Select events that could affect credit quality
  4. Map each event to borrowers and loan balances
  5. Score exposure by size, rating and degree of dependence
  6. Read the latest financials for the top exposures
  7. Do the financials show an effect from the event?If not: lower the exposure score and note why, then rescore. Back to step 4.
  8. Draft the watch list with suggested actions
  9. Head of credit approves any rating changeThe agent waits here for your OK.
  10. Weekly watch list and exposure summary

How it decides

It scores exposure by how much of a borrower's revenue or cost depends on the event, weighted by loan size and rating.

  • Add a borrower to the watch list when exposure score is above 7 out of 10
  • Use only news from named reliable sources
  • Raise priority when the loan is rated below investment grade
  • Remove an event after 90 days without effects

Make it yours

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

  • Industries and sources to watch
  • Exposure score cutoff (default 7)
  • Rating group for higher priority
  • Watch list schedule

What keeps you in control

It always asks you first

  • Head of credit approves rating changes
  • Head of credit approves contact with borrowers

Hard limits

  • Never changes a rating
  • Cites the source for every event it uses

It stops when

  • Done: watch list delivered and rating proposals queued
  • Stop: portfolio industry codes are missing for many loans

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 tariff rise on imported steel hit headlines on Monday. The agent mapped 17 borrowers in manufacturing and construction totaling $64 million. Exposure scoring put 5 above the line. Reading financials, 2 showed margins down 4 points, while 3 had long fixed-price contracts and no effect, so it lowered their scores. The head of credit approved a rating review for the 2.

More agents for risk managers