Workbooks for everyday work.
The ultimate AI-native data mcp.Diligence documents, lead reports and spreadsheets, researched from the original sources. Edit them with a sentence; they update themselves when a source changes.
6 minutes later: qualified B2B sales leads across five product lines.
And every source it cited was really where it said it was. Not most of them. Every one.
See the run →Works with your favorite AI productivity apps.
Your workbooks are there in the apps you already work in: ask a question, start a report, or update a spreadsheet right where you're at.
- Claude Code
- Claude
- Codex
- Cursor
- Hermes
- Any MCP app
Context is king.
A document is only as good as what it was written from. So a workbook goes to the primary sources that matter to you: SEC filings, FDA labels, clinical trial registries, customs records, procurement awards.
And to the files you already keep. Connect Google Drive, Dropbox, OneDrive or SharePoint, and it works from what is there.
If a source you need is missing, we add that data hose. That is our enterprise work: talk to us.
Every line cites the page or row it came from.
How it works.
- 01
Describe it. One sentence saying what the document is.
- 02
It does the work. It reads the primary sources and your own files, and cites each one.
- 03
Several AI models share it. Each takes the part it does best: gathering, writing, checking.
- 04
It updates itself. When a source changes, the workbook changes with it and tells you what moved.
- 05
You change it with a sentence. Ask in plain English and it rewrites the part you meant.
Give your agent the data MCP.
Connect the hedwigai MCP and your agent can ask, list, start and change workbooks. You speak in sentences; it makes the calls.
A short answer from your workbooks and programs, with the source it rests on. Nothing to wait for.
Is Moderna a biotech with a public float above $5B?
Your agent
ask · Is Moderna NASDAQ:MRNA a biotech company with public float above $5B?
{
"answer": "yes",
"claims": [{ "figure": "public float", "value": "$9.6B",
"as_of": "2026-06-28" }],
"sources": ["MRNA 10-K, cover page",
"biotech-diligence-7fq2 · §Moderna"]
}Yes. Moderna's public float was $9.6B as of June 28, per the cover of its 10-K.
What you can build.
A workbook is one document with one job. You don't maintain it; it arrives researched and finished, and it keeps itself up to date.
Lead reports
Who to sell to, and why now. Customs records, procurement awards and project wins, qualified against your own criteria, with an outreach email drafted for each.
US importers of heavy engineering equipment.
Diligence documents
The pack on a company, a target or a supplier. Filings, labels, trial results and investor decks, gathered and checked, with every claim linked to its source.
Diligence on eleven biotech companies.
Spreadsheets
Trackers, budgets and models. Change an assumption in plain English; the numbers move and it tells you which ones did.
The client list nobody has updated since March.
Built to be checked.
Sources on every claim
Each line traces to the filing, page or row it came from.
Every update says what changed
When a source moves, you see which lines changed and which source moved them.
Shared with your team
Invite the people you work with, and they can read the workbook and ask for changes too.
You are asked only when it matters
It stops for a decision or an approval, and otherwise gets on with the work.
We publish what it got wrong.
Each test takes one real task and checks the result against a list written before it began. The numbers stay up, misses included.
Biotech diligence
Eleven companies of diligence documents, gathered and scored.
- Companies
- 11
- Mean coverage
- 0.971
Heavy engineering importers
Five product lines of importers found, qualified and gated.
- Product lines
- 5
- Mean coverage
- 0.956
Aircraft records completeness
Whether a records package is complete — the method, before the scores.
- Methods
- 8
- Defect taxonomy
- 9 kinds
jev and Vela against ask on 92 questions
Yes-or-no questions about public companies, answered by two decision models alone and by hedwigai ask.
- Right, of answered
- 79% vs 98%
- Wrong answers
- 19 vs 2
The second system that changed nothing
The same document and the same instruction, run with and without a decider above the writer.
- Wall clock
- 23m 36s vs 3m 46s
- Model calls
- 104 vs 34
A general vision model cannot tell you where
Four frontier models asked to put a box around what they just described.
- Models
- 4
- Best mean IoU
- 0.109
