Overview
Docutron tackles a genuinely hard document problem: taking a pile of raw project files — drill logs, permits, assay results, surveys, photos — and producing a compliant, investor-grade technical report. The founding use case is the NI 43-101 mining standard, where accuracy is a regulatory requirement, not a nicety. The platform's core principle is anti-hallucination by construction: every AI-generated claim must cite a source document and page reference, and missing data produces an explicit gap statement rather than a guess.
The Multi-Agent Pipeline
Fifteen specialized Claude agents collaborate on each report: an orchestrator coordinates ingestion, classification, section extraction, QA, editorial review, economic analysis, permit and timeline agents, image handling, and a final report builder. A schema-discovery agent researches regulatory standards using web search, so the system can adapt to new report formats. Model selection is tiered — Haiku for high-volume classification, Sonnet for extraction and writing, Opus where depth matters.
Engineering Highlights
- Prompt caching on agent system prompts cuts AI costs by more than 80% across the pipeline
- Per-call AI usage tracking, cost estimation, and circuit breakers around every Claude integration
- Async FastAPI backend with SQLAlchemy 2.0, Celery/Redis task queues, and schema-per-tenant PostgreSQL multi-tenancy
- Security-first auth: JWT RS256, bcrypt, and TOTP two-factor authentication
- Stripe billing across three subscription tiers, with Whisper-powered voice transcription for interview ingestion
Outcome
A deeply architected demonstration of production multi-agent design — orchestration, cost control, resilience, and verifiable output — applied to a domain where hallucination is disqualifying.