Associated companyKnowledge system
Answer engine over 6.9M tax passages
A production answer engine we built and run for tax and accounting questions, searching about 6.9 million indexed passages.
- Qdrant
- Embeddings
- Reranking
- Hybrid search
Reference architectureCustom software
Operations platform with an AI layer
- 01 — The problem
- The business runs on a spreadsheet that three people edit and one person understands. It has outgrown the tool, but replacing it risks stopping the work.
- 02 — What we built
- A purpose-built application modelled on the real process, migrated in stages so the spreadsheet keeps working until each part is proven. Reporting and anomaly detection are built in rather than bolted on later.
- 03 — What changed
- One source of truth with roles, history and reporting — and a system the business owns and can extend.
Technology
Built with
- Next.js
- TypeScript
- Postgres
- Background jobs
- Role-based access
Related
Nearby work.
- Reference architectureAI agent
Inbound qualification system
Sales opens a ranked, enriched list instead of an inbox, and every enquiry is answered — including the ones that used to fall through.
- LLM agent
- CRM API
- Enrichment
- Queue
- Reference architectureDocument automation
Document-to-ledger pipeline
The routine majority posts without a human. Finance spends its time on genuine exceptions instead of on data entry.
- Vision + OCR
- Extraction
- Rules engine
- Accounting API
Have a problem shaped like this one?
Tell us what the process looks like today, and we'll show you what the built version does differently.