Executive summary
F2 is a credit underwriting tool. ArcaLabs is the workspace a deal team runs the whole mandate on.
- Scope. F2 is built for private markets investors and says it is purpose built for credit workflows. ArcaLabs covers sell-side M&A and ECM alongside private equity, private credit, hedge funds and corporate development, and produces the pitchbook and the memo as well as the model.
- Where the audit trail ends. F2’s audit mode shows the formula behind a number and traces it back to its source cell. ArcaLabs does that and then goes one step further: click a reported figure and the company’s own filing opens at that number, and the note stays in the workbook after you email it.
- Who pays for the data. ArcaLabs is FactSet’s Official AI Partner, and FactSet licenses are included per seat. F2 names no data partnership, so the market data behind a comp set is a subscription you bring.
For an underwriting file, the formula is the answer. For a deal, the filing is.
What each one is built to produce
Both produce Excel with live formulas. They aim at different ends of the job.
F2
Five parts, all pointed at private markets: a library of your past IC memos and models, deal screening, diligence against your firm’s history, underwriting in Excel with live formulas, and portfolio monitoring for covenants and exposures. The output is the underwriting file and the monitoring around it.
ArcaLabs
The model, the deck and the memo, built from your own templates and your firm’s definitions and saved as versioned deal files. Then 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
F2 lets you click a number and see the formula behind it, traced back to its source cell. That answers how a figure was calculated. It does not answer whether the inputs are right.
ArcaLabs answers both. Derived cells stay live formulas, and every input carries a note naming where it came from. 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.
The notes are written into the workbook, so a reviewer who opens the file in Excel outside the platform can still see where each number came from.
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. Public comps, EV bridges and market-based assumptions pull live.
F2 works from your firm’s own history, your data rooms and market information, without naming a data partnership. The market data behind a public comp set is therefore a subscription you hold, which 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
F2 keeps your firm’s history: past memos, models and decisions, searchable when the next deal looks familiar. That is a record of what you concluded.
It is not a record of the live transaction. 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.
For an advisor running a process, that record is half the job. For a credit fund it is the answer when a covenant is disputed and someone asks who agreed what, and when. A library of past memos does not contain it.
Where they differ
| Area | ArcaLabs | F2 |
|---|---|---|
| Lane | Sell-side M&A and ECM, private equity, private credit, hedge funds, corporate development | Private markets investors, built for credit workflows |
| Decks and memos | Built from your template, rendered and compared against it before delivery | Not a stated part of the product |
| Checks before delivery | Live formulas, workbooks recalculated and checked, decks compared against your templates | Not published |
| Audit trail | The formula, plus the source of every input. Click a reported figure and the filing opens at that number | The formula behind a number, traced to its source cell |
| 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 | No data partnership named. You bring the subscriptions |
| Deal record | An email address per deal, drafted replies, one deal log you can export | A library of past deals. No live deal correspondence |
Conclusion
A tool built for one lane does that lane well and stops at its edge. Private credit underwriting is a narrower job than running a mandate end to end.
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.
ArcaLabs checks all four before the file reaches you, links reported numbers to the filing rather than to a vendor’s copy, and produces the deck and the memo in your house style alongside the model. Give both platforms three files from a deal you have already closed and ask for the same workbook and the same deck.
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 F2?
F2 is a credit underwriting tool built for private markets investors. ArcaLabs is the workspace a deal team runs the whole mandate on: it covers sell-side M&A and ECM alongside private equity, private credit, hedge funds and corporate development, and produces the pitchbook and the memo as well as the model.
How do the audit trails differ?
F2’s audit mode shows the formula behind a number and traces it back to its source cell. ArcaLabs does that and then goes one step further: click a reported figure and the company’s own filing opens at that number, and the note stays in the workbook after you email it.
Does F2 include a market data license?
F2 names no data partnership, so the market data behind a comp set is a subscription you bring. ArcaLabs is FactSet’s Official AI Partner, and FactSet licenses are included per seat.
Sources
What F2 does is described here from that company’s public material, read from f2.ai 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.
F2: f2.ai · ArcaLabs: arcalabs.ai