---
title: "CRECO, agentic RAG for credit analysis"
description: "STEPS case study: an agentic RAG that queries credit memorandums and committee minutes, cites every source down to the page and stays installed at the bank."
canonical: https://steps.tn/en/agentic-rag-credit/
last-updated: 2026-11-16
---

# CRECO, agentic RAG for credit analysis

STEPS case study: an agentic RAG that queries credit memorandums and committee minutes, cites every source down to the page and stays installed at the bank.

URL: https://steps.tn/en/agentic-rag-credit/

Case study | Agentic AI

CRECO: an agentic RAG for credit analysts

Analysts query years of credit assessment memorandums and committee minutes in natural language. Every answer cites its sources, down to the page.

× STEPS Case study | Agentic AI 

## CRECO: an agentic RAG for credit analysts

 Analysts query years of credit assessment memorandums and committee minutes in natural language. Every answer cites its sources, down to the page.
 Afreximbank Cited answers AI installed at the bank 
 Book my scoping session ↗
 
 Which covenants did we require on the latest export pre-financing facilities?Planning the searchReading 214 credit memorandumsReading committee minutesChecking sourcesThe last three comparable facilities required a minimum coverage ratio1, domiciliation of export proceeds2 and quarterly reporting to the committee3.[1] CAM 2025-041, p. 12[2] Credit committee, March 2025[3] CAM 2024-188, p. 7How it works, fictitious data 01 - The problem"Have we already financed a comparable deal, and on what terms?"
A simple question for a credit analyst. But the answer is buried in hundreds of documents nobody can reread before every committee.
CAMCredit assessment memorandums of 40 to 80 pages, in PDF, filed by deal.
MinutesCommittee minutes, where the decisions and the conditions actually imposed are recorded.
?Institutional memory, which leaves with experienced analysts.
 02 - How it works

## An agentic RAG, not just a search engine

Instead of returning a list of documents, CRECO does the reading: it plans the search, assigns each source to an agent, then checks every citation before answering.
QuestionPlanningagentCAM agentCommittee agentPolicy agentCitationcheckCitedanswernatural languagememorandumsdecisions, conditionsinternal rulesStep 1

## Understand

The question is rephrased and broken down into precise searches.
Step 2

## Search

Specialised agents query each type of document in parallel.
Step 3

## Read

Relevant passages are extracted, with their page and date.
Step 4

## Verify

Every statement is checked against its source; otherwise it is removed.
Step 5

## Answer

A short answer, clickable citations and the documents to open.
 03 - The interface

## Designed for the analyst, not the IT team

The wireframes set one rule: the analyst must be able to check every answer in one click.
Search the credit files…CAM 2025-041, p. 12Credit committee, March 2025CAM 2024-188, p. 7+ 6 documents12341

## A single search bar

The analyst asks a question as they would ask a colleague, in French or English.

2

## The answer, highlighted

Sentences taken from the documents are highlighted, each with its source number.

3

## Sources alongside

Each citation opens the document at the right page. Nothing is stated without proof.

4

## Suggested next steps

Compare two deals, list the conditions imposed, prepare a note for the committee.

Wireframe of the CRECO interface 04 - Trust

## Built for a bank's most sensitive data

## Access rights respected

An analyst only sees in the answers the files they are allowed to consult.

## Data stays at the bank

Documents, indexes and models remain inside the bank's information system.

## Open source models

Locally hosted models, with no data sent to an external service.

## Traceability

Every question, every source consulted and every answer is logged.

## No answer without a source

If no document supports an answer, CRECO says so instead of making one up.

## Continuously evaluated

A set of reference questions measures answer quality at every change.
 FAQ

## Frequently asked questions

What is an agentic RAG?A system that finds the right passages in your documents, then has AI agents read and check them before answering. Unlike a standard chatbot, it cites its sources.
Can CRECO be wrong?It may not find an answer. But every statement is linked to a document: the analyst checks in one click, and CRECO says when no source answers.
Do the documents leave the bank?No. Indexing, models and answers all run inside the bank's information system.
Can it be adapted to other functions?Yes. The same approach applies to compliance, executive committees or loan agreements: only the documents and the agents change.
 Do your analysts spend more time searching than analysing? Let's talk about your documents and your recurring questions.
Book a scoping session ↗

---

Book a free scoping session: https://steps.tn/reserver-une-session-de-cadrage/

Site guide for agents: https://steps.tn/llms.txt
