RAG Finance

Keep the sources close to the answer.

A finance and tax research assistant connecting Indonesian regulations to article-level evidence, official sources, and clear uncertainty.

Explore the build

AI solutions Web apps

Regulatory research illustration pairing a sample answer with article-level citations and a source library. — Original interface illustration · Synthetic demo data.View larger

At a glance

Stage: Prototype
Industry: Finance and tax research
Context: Internal product
Capabilities: 6
Technologies: 9
Year: 2026

0.96 hit@5

Historical retrieval result on an early benchmark of 25 labelled questions and 693 regulatory chunks; not a full-corpus or answer-accuracy score

The challenge

Finance and tax teams work with rules spread across official portals, lengthy documents and amendments.

Finding a plausible answer is easier than checking which provision supports it and whether later wording changes the conclusion.

A useful research assistant needs to show its evidence, preserve the context around an article and admit when the indexed sources do not answer the question.

What we built

RAG Finance combines a searchable regulatory library with a research chat workspace.

Questions in Indonesian or English

Conversation context and query planning turn everyday wording into targeted searches across finance or tax sources

Questions in Indonesian or English

Conversation context and query planning turn everyday wording into targeted searches across finance or tax sources

Answers with references

Article and page evidence, document metadata and official-source links let the user inspect the material behind a grounded answer

Amendment-aware research

Retrieval considers document status and brings in later amended wording found in the index. It distinguishes the old provision from the indexed change

A reusable document library

Resources and hybrid search work independently of the chat, with filters for source, domain, document type and status

Controlled ingestion

Source adapters cover Bank Indonesia, OJK, SIKePO, DJP and the Ministry of Finance, alongside administrator uploads. File validation, incremental processing and reusable embeddings avoid repeating unchanged work

Tools for review

Administrators can inspect ingestion progress and retrieval traces, compare search results and configure model providers

How it works

Combined search, validated citations
The system combines vector search, full-text search and direct regulation lookups. A sufficiency check decides whether the selected material supports an answer, and the server validates citation markers against that evidence.
Clearly labelled answer modes
The interface distinguishes grounded, hybrid, general and no-answer modes. When optional general-knowledge fallback is enabled, the answer is visibly labelled; it does not acquire official-source status simply because it appears in the same conversation.

Current stage

Prototype

Research
Prototype
Pilot
Production

This is a working internal prototype, with no production user deployment claimed. An early documented benchmark used 25 labelled questions and 693 regulatory chunks: retrieval reached hit@5 of 0.96 and MRR of 0.84 using a local embedding model.

Read the full status

That small historical test measures retrieval, not legal correctness, full-corpus coverage or the quality of every generated answer. Only documents actually indexed can support research, and later wording found in the index is not a guarantee that every relevant amendment has been collected. The user remains responsible for checking authoritative sources and interpretation.

Where this fits

The same architecture can help teams research internal policies, standards or contracts with references they can inspect. Explore our AI solutions and web applications, or discuss your knowledge workflow.