× STEPS
Case study | AI agents for credit, Afreximbank

SCRIBE, AI agents that draft credit documents

For Afreximbank, STEPS designed SCRIBE: a supervised multi-agent system that draws on the bank’s systems of record and drafts term sheets, PAMs and credit memoranda in the drafting officer’s style.

Time-boxed proof of concept
Supervised multi-agents
Systematic human review
01 - The context

Credit, a business of documents

Every financing granted by the bank goes through a series of standardised documents, drafted by credit officers from data scattered across several systems. Long, repetitive and yet critical work.

!

Scattered dataDeals, obligors and facilities are stored in different systems that must be checked one by one.

!

Manual draftingEach term sheet, PAM or memo often starts from an old document, copied and then adapted by hand.

!

A style to respectEach officer has their own way of writing, and committees expect consistent quality.

!

A risk of errorA miscopied figure can distort a credit decision.

02 - The stakes in figures

Hours of drafting before every committee

A credit file draws on scattered data and a demanding drafting style. SCRIBE prepares the first draft so the officer can focus on the analysis.

3

Systems of record to cross-check: deals, obligors, facilities.

3

Document types drafted: term sheet, PAM and credit memo.

100%

Of drafts reviewed and approved by a credit officer before use.

03 - The deliverables

Three documents, a first draft in minutes

DOCUMENT 01

Term sheet

The key terms of the facility, structured and ready to negotiate.

DOCUMENT 02

PAM

The project approval memo, with context, risks and recommendation.

DOCUMENT 03

Credit memo

The full analysis of the file, written in the officer's style.

04 - The agents

Four agents, one officer in control

The agents work in a chain, each with a precise role. The credit officer reviews, corrects and approves every draft: AI prepares, humans decide.

RetrieveAn agent retrieves deal, obligor and facility data from the bank's systems.

DraftAn agent drafts the document from this data and the bank's templates.

Match styleAn agent adapts the text to the drafting officer's style, based on their past documents.

VerifyAn agent checks every fact against its source before delivering the draft.

05 - The benefits

What SCRIBE changes for the bank

The gain is not only measured in time: SCRIBE also improves the quality, consistency and traceability of credit files.

Main benefitMore time for analysis

Credit officers no longer start from a blank page: they review a complete first draft and spend their time on credit judgement, where their expertise matters.

Lead timeFaster credit files

The first draft is ready in minutes, shortening the path to committee.

QualityFewer data entry errors

Data comes straight from the systems of record, with no copy and paste.

ConsistencyA consistent style

Documents follow the bank's templates and each officer's style.

TraceabilityEvery fact sourced

An auditor can trace the origin of every piece of data cited in a document.

KnowledgeKnowledge captured

The EKC layer organises the bank's credit knowledge and makes it reusable.

DecisionHumans stay in charge

Nothing is sent without a credit officer's approval.

06 - Our work

A proof of concept in four steps

PHASE 01Scoping

Choice of target documents, data sources and success criteria with the credit teams.

PHASE 02Knowledge

Building the EKC layer: connection to the systems of record and indexing of past documents.

PHASE 03Agents

Development of the four agents, document templates and style learning.

PHASE 04Evaluation

Tests on real files, review by officers and measurement of the gain before scaling up.

07 - Governance

AI designed for a bank

Traceability

The EKC knowledge layer links every fact in the draft to its source in the bank's systems.

Model risk

The system is designed to be controlled: scope, logging and human review at every step.

Proof of concept

A time-boxed project to measure the real gain before any scale-up.

08 - Architecture

Under the hood

An orchestrated multi-agent architecture, built on retrieval-augmented generation (RAG) over the bank's knowledge.

AI agentsLLMRAGOrchestrationPythonLogging
  • SourcesSystems of record for deals, obligors and facilities
  • KnowledgeEKC layer: indexed documents, facts linked to their source
  • AgentsRetrieve, Draft, Match style, Verify, orchestrated in a chain
  • ControlHuman review, step logging, model risk management
  • OutputsTerm sheets, PAMs and credit memos in the bank's format
FAQ

Frequently asked questions

Does SCRIBE replace the credit officer?

No. It prepares a first draft; the officer reviews, corrects and approves every document.

How are AI errors avoided?

A dedicated agent checks every fact against its source, and the EKC layer keeps track of where every piece of data comes from.

Can it be adapted to other documents?

Yes. The multi-agent architecture extends to other standardised documents: risk reports, committee notes, annual reports.

Do your teams spend hours drafting standardised documents? Let's talk about your AI agents.

Book a scoping session ↗