Filing-knowledge-base (FKB)
pgvector-backed semantic search across the company's filing trail. Every claim in the brief cites the specific 10-K/10-Q section it came from.
All use cases
Strategy briefsLive in portalsign-in
Management Consultant AI
Ask a decision question, get an analyst-grade strategy brief in ~5 minutes — multi-step reasoning over the context you provide, every claim cited.
Management Consultant AI is an analyst-grade strategy briefing service. Ask a decision question — 'Should we shift to usage-based pricing?', 'Is this M&A thesis intact?', 'What's the archetype of this competitor?' — and a multi-step reasoning pipeline runs for ~5 minutes, producing a cited markdown brief with a bottom-line recommendation, conviction level, and quality score. You paste the context (financials, strategy docs, meeting notes, filings); the agent auto-RAG's it and pulls only relevant passages into each sub-question. Live in portal; each run costs a few cents in compute (shown per consultation).
What makes it different: Live multi-step reasoning pipeline. Cost transparent per run (~$0.10-0.25). Reports rendered as cited markdown, not vibes.
What it does
Capabilities
Archetype classification
Observable-financial-grounded classifier puts the company in a strategy archetype (compounder, consolidator, turnaround, etc.) — not vibes-based.
Catalyst assessor
Identifies specific upcoming events (earnings, regulatory milestones, segment divestitures) most likely to move the stock and quantifies the expected magnitude.
Diff-over-time
Track how management's messaging changes quarter-over-quarter. When the language shifts (caution → confidence, or vice versa), surface it explicitly.
How it works
Input → output
Input
(Coming soon — pilot tickers selected per engagement)
- 1Ingest full filing history into FKB (vectorized 10-K / 10-Q / 8-K / DEF 14A)
- 2Run archetype classifier against observable financials (capital allocation, segment mix, M&A cadence)
- 3Walk the catalyst-assessor framework: 12 specific question nodes per company
- 4LLM synthesizes the strategy brief — every claim hyperlinked to its FKB citation
- 5Quarterly diff: surface language changes vs. prior period (commentary, not as drivers)
Output
Multi-page strategy brief: archetype + thesis + catalysts + risks + management-tone diff. Every paragraph cited.
Output preview
portal · live
(your ticker)
Strategy brief in active build
Coming soon
We're shipping the consultant-grade strategy brief format for select pilot tickers. Each brief will combine the archetype classifier, FKB citations, catalyst assessor, and quarterly-tone diff into one structured document.
Brief structure (preview)
- Archetype classification (5 sentences + supporting financials)
- Bull / bear / base case thesis with FKB citations
- Catalyst assessor: next 12-month moves with expected magnitude
- Quarterly tone diff: management language drift
Why this isn't a wrapper
Why this isn't a 10-K summarizer
Generic summarization is table stakes. The hard part is being right.
- Archetype classification is grounded in observable financials (capital allocation history, segment mix changes, M&A pace), not in what management calls itself.
- Every claim in the brief is a hyperlink to the source paragraph. A committee can verify any assertion in 1 click.
- Quarterly diffs surface the silent narrative shift — when guidance language changes from 'durable' to 'navigating' (or vice versa).
- The catalyst assessor specifically identifies high-impact upcoming events and quantifies expected magnitude rather than listing every event in the next 12 months.
Ready to see it?
Sign in to the portal and pull a dossier on any ticker in the universe.