Project · ABN AMRO x AISO2 min read

AURORA: source-grounded drafting and review for ABN AMRO

A proof of concept for ABN AMRO: a pipeline that turns a rough writing request into a draft with retrieved sources, quality checks and a trace of how it was made.

AURORA turns a rough writing request into a draft accompanied by retrieved sources, quality checks and a trace of how it was produced. We built it as a proof of concept for ABN AMRO with the AI Student Organization (AISO), for ABN AMRO Insights content in Technology, Media and Telecom, with English, Dutch and bilingual output.

I wrote about the project while it ran: why retrieval is the main design decision and the mid-cycle pipeline.

GitHub repositoryarkdong/ABNAMRO_AISO_AURORA

Why we built it

A short prompt rarely contains everything an editor needs: the audience, the relevant source material, the bank’s writing guidance, and the criteria for a usable draft. Supplying those details again and again leaves much of the work with the author and the reviewer.

Our central design decision was to make that preparation part of the system. AURORA interprets the request, selects editorial and domain profiles, retrieves articles and writing guidance, and refines the assignment before any drafting happens. Evaluation then gives the reviewer specific findings next to the text.

Seven AURORA stages grouped into interpreting the request, grounding the assignment, and drafting with evaluation
The seven-stage workflow. Context and editorial constraints are assembled before generation; clarification can send the run back through profile selection and retrieval. Open full size ↗

What it does

Step What happens
Interpret the request Classifies the task, sector, keywords and language, and selects drafter, reviewer or curator profiles.
Retrieve sources Searches English and Dutch articles and writing guides, and returns snippets with their source.
Refine the prompt Adds context and constraints, and asks clarification questions when the request is too open.
Generate the draft Writes the draft with citation references, in English, Dutch or both.
Evaluate Combines deterministic checks, six LLM quality judges and the human reviews still required.
Trace Keeps the stage results, selected sources and findings for every run, so an editor can inspect them.

The same services are exposed three ways: a REST API built with FastAPI, eight MCP tools, and a Streamlit interface with a guided mode and a pipeline inspector.

The integration design below shows how an approved corporate agent could call these services. Production access controls and durable audit storage remain requirements for a pilot.

AURORA integration architecture showing a corporate agent calling REST or MCP tools, the seven-stage pipeline, governed sources and draft outputs
Integration design: the external agent uses AURORA as a tool layer. The diagram describes the intended governed deployment, rather than claiming that every production safeguard is already in place. Open full size ↗

How evaluation works

The evaluation catalogue holds 135 KPI entries derived from ABN AMRO’s content KPI workbook. Only the part that applies to a draft runs during generation.

  • Deterministic checks catch invalid citation markers, missing image alt text and citations to sources that may not be used.
  • Six LLM judges assess factuality, adherence to bank standards, relevance, privacy and security, source groundedness and completeness.
  • Human review requirements, such as editorial and legal sign-off, are reported as pending. A passing evaluation is not publication approval.

Status

AURORA is a working proof of concept with 97 passing tests. It shows an inspectable drafting and evaluation workflow. It does not yet show measured time savings or quality gains: that needs a controlled pilot comparing editorial tasks with and without it, which the final report proposes.

Published
30 Jun 2026
Updated
13 Nov 2026
Topics
AI, RAG, AISO, ABN AMRO