Kepler for Finance

Your firm's research,
with every number proven

An AI research tool for investment teams that turns filings, transcripts and your own documents into answers, models and memos you can trust, with every number traced to its source.

Request Demo
Debt structure, last three 10-Qs
Plan
  1. 1Read the last three 10-Qs
    ReadingRead 3 SEC filings10-Q Q110-Q Q210-Q Q3
  2. 2Extract the debt schedule
  3. 3Reconcile footnotes
  4. 4Build the table

Total debt is $74B across three notes.

Ask in plain English

Questions across 26M+ SEC filings, international filings in 120+ countries, earnings transcripts, news, and market data. Kepler plans the work and shows each step.

Kepler verified response

Debt-to-equity was 3.77, on total equity of $19.6B.

10-QBalance sheet2026-08-01
Total liabilities74,000
Total shareholders' equity19,600
Source verified

Click any number. See the source.

Every figure links to the original filing, page, and line item. Peer comparisons, debt structures, revenue breakdowns: each data point carries its citation.

Workbook · Comps Download Comps.xlsx
C9ƒx=C4/C7Formula
BC4Enterprise value512,4007EBITDA36,0809EV / EBITDA14.2x
XBRL C4, C7 cited to the 10-K

Straight to Excel. Already verified.

Export to Excel and PowerPoint, or use Kepler as an add-in inside them, with every data point checked before it leaves Kepler.

Built for the workflows
that matter most

Hedge funds

Screens and earnings updates

Screen thousands of companies on metrics and disclosures, and update the model the hour results land.

  • Idea screens across filings and metrics
  • Post-earnings model updates
  • Thesis tracking and alerts
Semiconductor companies whose inventory days rose three quarters in a row
Private equity

Diligence and portfolio monitoring

Work through years of filings, footnotes and data-room documents to find what changed and what doesn't add up.

  • CIM and data-room diligence
  • Portfolio company monitoring
  • Investment committee memos
Restatements and off-balance-sheet commitments in the last five 10-Ks
Equity research

Earnings models and estimates

Pull segments, margins and share counts from 10-Qs and transcripts, and see exactly what changed when a company files.

  • Earnings previews and post-print notes
  • Segment and margin build-outs
  • Estimate revisions with sources attached
Update FY2026 estimates from Alphabet's latest 10-Q and earnings call
Investment banking

Comps, valuation and deal materials

Build comps and precedents where every multiple traces to a line item in a filing.

  • Trading comps and precedent transactions
  • Buyer lists and deal screens
  • Pitch book pages in your format
Trading comps for US cybersecurity, EV/EBITDA on each filer's own adjusted EBITDA

Why not existing AI tools?

Most AI for finance is a frontier model, used directly or inside a finance product. Either way, the model is the one writing the numbers.

Existing AI tools Kepler
NumbersExisting AI toolsWrites the numbers itself, and can hallucinate.KeplerCode pulls every number and cites its source.
CoverageExisting AI toolsSearches a few passages and answers from those.KeplerReads and indexes every document before you ask.
DefinitionsExisting AI toolsGuesses what you mean by adjusted EBITDA or Q3.KeplerUses your firm's definitions, every time.
ConflictsExisting AI toolsPicks one figure when sources disagree.KeplerShows each figure and where sources disagree.
ConsistencyExisting AI toolsAsk twice, get two answers.KeplerSame question, same answer, same sources.

What investment teams
tell us

“Our analysts used to spend more time verifying AI outputs than generating them. With Kepler, every number is already traced to source.”
Senior Managing DirectorTop-10 Global Asset Manager
“Kepler's numbers match the filings. My team stopped re-checking every figure before it goes to a client.”
Vice PresidentGlobal Investment Bank
“Every other AI tool I've tried misses what's buried in the footnotes. Kepler has read every filing, so nothing slips past it.”
Managing DirectorMulti-billion dollar fund

Your rules, built in,
and always improving

Kepler learns how your desk works, from the analyst up to the firm, and its skills get better with every correction.

Definitions

Your definitions, built in

Adjusted EBITDA, fiscal calendars and peer sets work the way your firm defines them.

Templates

Your formats, every time

Models, memos and pitch pages come back in your firm's templates.

Memory

Skills that keep improving

Every correction and review feeds back into the skill, so it gets sharper without anyone rewriting it.

Control

Rules you can customize

See, edit and delete everything Kepler has learned about how your desk works.

Public data on day one,
your data in the first week

Kepler comes preloaded with public market data. We connect your private sources, pre-index them and build your firm's ontology on top.

Day oneFirst week
Day one

Public data, already loaded

SEC filings, earnings transcripts, investor presentations, consensus estimates, market data and news.

First week

We connect your sources

Internal research, models, broker notes, expert calls, your CRM, SharePoint and drives.

First week

We pre-index every document

Each one is read in full once, with every fact kept next to the passage it came from.

First week

We build your ontology on top

Your companies, funds, definitions and relationships, linked to the public record.