//Case studies
Advisory firm.
A consultant's assistant — a self-updating knowledge base with hybrid search and a research agent. A preliminary analysis in ~2 minutes instead of 12 hours.
- Industry
- Advisory
- Timeline
- 2024–present
- Outcome
- From ~12 hours to ~2 minutes
The problem
Preparing a substantive analysis took hours of manually searching and reviewing documents. The knowledge was scattered across a corpus of more than half a million documents — with new ones arriving daily.
What I built
A system that maintains its own knowledge base and serves it to consultants in seconds:
- Half a million documents processed — to start, every one of the more than half a million documents had to be analysed by AI: summarised, described with metadata and indexed. I spread an operation of that scale in parallel across several model providers' infrastructure; today the system runs on Anthropic models.
- A self-updating base — every night the system checks for new publications and automatically downloads, analyses and indexes anything it doesn't yet have — retrying failures by itself, with no one on call.
- Hybrid search — a user's query is searched semantically and full-text at the same time; results are merged, scored for relevance and ordered before they reach the consultant.
- Analysis drafts — the system analyses the retrieved documents and prepares a preliminary analysis in two steps: analysis, then synthesis.
- A research agent — an autonomous AI agent that decides for itself when to query the search engine and when to pull a document's full text — conducting research in stages, the way a person would.
- Internal portal backend — search, research and the agent are available to consultants through the firm's internal portal.
Stack: n8n, PostgreSQL, Elasticsearch, Next.js; Anthropic models.
The outcome
Preliminary analysis preparation cut from around 12 hours to around 2 minutes. The engagement is ongoing: the system is being extended with further document corpora — on the same proven architecture.