Executive summary
Hebbia stops at the findings. ArcaLabs delivers the file, checked, with every number sourced.
- Reading is not producing. Hebbia returns findings from a document set. Turning them into a model that ties out, in your template, is still analyst time. ArcaLabs starts from your own templates and definitions and hands back the finished file.
- Checks that stop the file. ArcaLabs finds hardcoded numbers where a formula should be and converts them, recalculates the workbook, and checks it for errors. Decks are rendered and compared against your template. A failed check stops delivery.
- Sourcing that leaves the platform with the file. Hebbia traces findings back to the documents inside its own workspace. In ArcaLabs the note sits on the cell and is written into the workbook, so it is still there after you email it.
One tells you what is in the documents. The other gives you the deliverable, and stands behind every number in it.
Building the deliverable
Both platforms will hand you a spreadsheet. The difference is where it comes from and what happens to it before you see it.
Hebbia
Matrix reads across documents and companies and returns findings in a grid, each one traceable to where it was found. Max produces spreadsheets, slides and reports from that research. The starting point is the document pile, and the output is a first draft that still has to be checked and reformatted by hand.
ArcaLabs
Files are built from your own templates and your firm’s definitions, then saved as versioned deal files. Three checks run on their own. Hardcoded numbers are found and turned back into formulas. The workbook is recalculated and checked for errors. The deck is rendered and compared against your template, and anything short of a pass stops delivery.
Sourcing and audit trails
Both platforms cite sources. The questions are what you get when you click one, and whether it is still there after you send the file.
In ArcaLabs every number carries its own source. What a reviewer does:
- Click a figure in the model.
- The filing opens in the app, scrolled to that number.
- Work through the tagged figures, marking each one reviewed.
- Sign off. The record of the review is kept.
- If a company reported the number, the tag links to the filing, not to a data vendor’s copy of it. Diluted shares, total debt, cash, the LTM actuals under an EV bridge.
- Numbers that only exist on a data vendor, like a share price or a consensus estimate, name the vendor and the date instead, and are never dressed up as coming from a filing.
Hebbia traces a finding back to the document it came from, inside Hebbia. ArcaLabs writes the note into the workbook, so the trail is still there when your MD forwards the model to a client.
Market data and licensing
ArcaLabs is FactSet’s Official AI Partner. The license is included in the seat price, and we can work off another provider (e.g. Cap IQ) if your firm prefers.
Hebbia connects to third-party data providers alongside your private documents and public filings. You bring the subscriptions, so that cost stays on your budget and belongs in your year-two comparison.
Holding the license also lets ArcaLabs check the data before it reaches your model. Every ticker is confirmed against its home market first, because a blind US default returns the wrong company on foreign names. Ask for TEP and you get Tallgrass Energy rather than Teleperformance, and the comp set looks fine until someone senior reads it.
The deal record
A live transaction is not only analysis. It is a record of who sent what, which version went to which counterparty, and what was agreed on a call.
Hebbia’s workspace is built for people and agents working over the same set of documents. It is a research surface, not a place a counterparty writes to, so the correspondence and the compliance record stay wherever they already live.
In ArcaLabs the deal log works with the email you already use. Connect Gmail or Outlook and correspondence is matched to the right deal automatically, so the record builds itself without anyone forwarding anything. Each deal also gets its own address that counterparties can write to directly, and the agent drafts the reply there for you to approve. Every email, meeting and agent action lands in one deal log you can export.
Where they differ
| Area | ArcaLabs | Hebbia |
|---|---|---|
| Starting point | Your templates, your firm’s definitions, and live market data | The document pile you point it at |
| Checks before delivery | Live formulas, workbooks recalculated and checked, decks compared against your templates | Not published |
| Sourcing | On every number. Click it and the filing opens at that figure | Findings traced back to the source document in Hebbia |
| After you export | The notes are inside the workbook, so they survive the email | Traceability lives in the workspace |
| Reported vs estimated | A filing beats a data vendor’s copy. Vendor-only numbers name the vendor and date | Not addressed |
| Market data license | Data agnostic. All licenses (e.g. FactSet, CapIQ) included in the seat price | Connects to third-party providers. You bring the subscriptions |
| Deal record | An email address per deal, drafted replies, one deal log you can export | A shared research workspace. No deal record |
Conclusion
Reading a data room quickly is useful. It is also the first hour of the job, not the last.
Files fail review in four places. A number was pasted in rather than calculated. The template drifted. An estimate was footnoted as if a company had reported it. Or someone asked where a figure came from and the answer took four minutes to find. None of those are reading problems.
ArcaLabs checks all four before the file reaches you, and keeps the sourcing inside the file so it holds up after you send it. Give both platforms three files from a deal you have already closed, ask for the same workbook and the same deck, then export them both and click a number.
Run the same test on your own deal.
Bring three files from a closed deal. Ask for the workbook and the deck, export them, and click a number.
Frequently asked questions
What is the difference between ArcaLabs and Hebbia?
Hebbia is built to read a very large pile of documents and returns findings you can trace. ArcaLabs is built to produce the file you send, starting from your own templates and definitions, and to check it before you do. Turning Hebbia’s findings into a model that ties out, in your template, is still analyst time.
Where does the sourcing live after you export?
Hebbia traces findings back to the documents inside its own workspace. In ArcaLabs the note sits on the cell and is written into the workbook, so it is still there after you email the file.
Does Hebbia include a market data license?
Hebbia connects to financial data providers alongside your private documents and public filings, but you bring the subscriptions. ArcaLabs is FactSet’s Official AI Partner and the license is included in the seat price, with other providers such as Cap IQ available if your firm prefers.
Sources
What Hebbia does is described here from that company’s public material, read from hebbia.com on August 5, 2026, and put in our own words. Vendor material changes often, so check anything that will decide your choice with them directly. ArcaLabs statements are verified against the platform before publication; single-tenant VPC deployment is available on request rather than standard.
Hebbia: hebbia.com · ArcaLabs: arcalabs.ai