Every analyst becomes an entire equity research team.
Your analysis becomes AI agents that cover every company you follow — every number traceable to its filing.
you › NVDA revenue, FY2024?
- Point-in-time, no look-ahead
- Every number auditable to its filing
- Human-on-the-loop — you approve what matters
One token. Three channels. The same point-in-time truth.
One subscription, three ways in — an AI agent, a browser workspace, or your own code. Same data, same lineage, same persisted state underneath: save a thesis in Claude, see it in Cursor.
The agent you already use, wired to data bound to its filing.
Agent-agnostic by design: Claude, Copilot, ChatGPT, Perplexity, Gemini, Grok, or Cursor — wired to 95 typed tools and 28 expert workflows. Works the moment you connect, pay per call to start, every result cited.
Connect your AI agentCalling Valuein MCP…
Your agents run while you sleep. You approve what matters.
A browser research desk with your own LLM key — sealed for 24 hours, never trained on. Agent teams re-run your workflows on every new filing; every high-impact action waits for your approval. Human-on-the-loop, not human-out-of-the-loop.
Try the WorkspaceRunning flagship equity_research_brief SOP…
The backtest that can't cheat.
pip install, one token, 111M+ standardized facts through DuckDB — point-in-time, survivorship-free, zero look-ahead. The raw truth in your own code, not a black box.
Read the SDK docsfrom valuein_sdk import ValueinClient # Point-in-time SEC fundamentals — sample tier, no API keywith ValueinClient() as client: df = client.run_template( "fundamentals_by_ticker", ticker="META", ) print(df.head())Your judgment, running on every company you cover.
Not another data feed. The engine that turns how you analyze a company into a repeatable process — and runs it across your whole universe.
- 01
Start with your judgment
Use our 28 expert workflows — or build your own, step by step, in the exact order your process demands.
- 02
Run your whole universe
One workflow, batched across your sector, index, or circle of competence. Same inputs, same output — every time.
- 03
Build a shared library
Every run persists a company profile, valuation, and risk read the whole firm can draw on.
- 04
Keep it current — automatically
When a new 10-K, 10-Q, or 8-K moves the numbers, your agents re-run and update the profile.
- 05
Safe for the institution
Your agent can't invent a figure. High-impact actions wait for a human. AI your compliance team can approve.
Build a library the whole firm draws on.
Every run produces a company profile, a valuation, and a risk read that persists and publishes to a shared catalog — one living source of truth, kept current by automations.
Your analysis
The way you read a company — margins, moat, leverage, the risk that actually matters.
A custom workflow
Order the exact steps from real tools and SOPs. Your edge becomes a repeatable procedure, not a one-off deck.
Across your universe
Batch the same workflow over every name you cover — deterministically, every number pinned to its filing.
temperature 0 · point-in-timeThe research library
Profiles, valuations and risk reads that persist — and refresh on their own as new filings land.
auto-updated on new filingsCredit desk
Prices a loan off the same risk read — interest that reflects the filings, not a guess.
M&A team
Scopes a target from a valuation everyone can trace back to the source.
Traders
Check a company's risk before sizing — the read is already there, already current.
Compliance
Signs off — because every number traces to the filing, one click away.
A research library so rigorous your credit desk can price a loan from it, your M&A team can scope a deal with it, and your compliance team can sign off on it — because every number traces to the filing.
One source of truth — not twelve conflicting decks.
See how teams use itAsk like you'd ask a junior analyst — get the work back from a senior researcher.
One login, every surface, the same underlying record. The figures come back audit-ready — so you move faster on work you can put your name on.
Spend your hours on judgment, not data entry.
Standardized fundamentals, ratios, and comps in seconds — cited, point-in-time, ready for the IC memo. Spreading a filing becomes a sentence, not an afternoon.
Cover more names without cutting corners.
Screen 19,000+ active and delisted companies, see what changed since last quarter, trace every claim back to the 10-K behind it.
Backtests that can't see the future.
Append-only history, as_of_date reconstruction, zero look-ahead — a survivorship-free universe back to 1993, streamed through DuckDB. Same result every time.
Wire SEC data your agent can't fabricate.
95 typed, tier-gated tools and 28 agentic workflows over SEC-filed data. Connect in minutes, skip the RAG pipeline — every answer comes back with a source attached.
Independent analyst or solo investor? The same platform, the same data, the same per-seat pricing are yours too — start free on the S&P 500 with no card, and scale to the full universe only when the work does.
One capability chain. Every desk's outcome.
The same platform — codified workflows, batch runs, a shared library, automations — lands differently on every desk. Pick yours.
Financial analysts
Spread any 10-K in seconds, cited to the filing.
Portfolio managers
Run the whole book — an analytical partner, not an autopilot.
Quants
Backtest 30 years without survivorship bias.
Researchers
Reproducible, restatement-aware data for published work.
Developers & AI builders
Wire SEC data your agent can't fabricate.
Data engineers
One clean feed — no scraper farm, no XBRL wrangling.
Independent investors
Institutional-grade research on a personal budget.
Research & finance leaders
AI you can put in front of a risk committee.
Two datasets: financial fundamentals and smart-money.
Standardized fundamentals plus insider and institutional ownership — point-in-time, survivorship-free, every figure traceable to the exact filing it came from.
Financial fundamentals
111M+ facts · 19,000+ companies · 1993–present
Income statement, balance sheet, cash flow, ratios and valuation — raw XBRL normalized into canonical concepts. Active and delisted names alike, from 10-K/10-Q/8-K filings and their amendments.
Smart-money signals
78M+ rows · 6 tables · Forms 3/4/5/144 + 13F/13D/13G
Insider transactions and institutional ownership — who is buying, selling, and holding — under the same point-in-time discipline, across the full universe.
Point-in-time
Every fact carries its EDGAR acceptance timestamp. Query any past date and see only what was public then.
No look-ahead, survivorship-free
Append-only — restatements add rows, never overwrite. Delisted, merged and bankrupt names stay in, so backtests can't cheat.
Provenance on every number
A deterministic fact_id pins each value to one SEC filing; verify_fact_lineage round-trips it back to EDGAR in a click.
Accuracy guardrails
A reported 0 stays distinct from missing; derived figures ship their formula and inputs; in the Workspace, untraceable numbers are blocked — enforced by a build-gating test.
The model never mints a number.
Typed tools return SEC-filed values; the model only arranges the words. Same inputs, same output — and every figure is one click from its filing.
A tool returns the number.
META · op_income · FY2024
$69,380,000,000
There is no free-text digit to invent — the model selects a fact, it doesn't author one.
Same inputs, same output.
temperature 0 · point-in-time snapshots · deterministic tools. Research your firm can reproduce years later.
One click to the filing.
No re-running, no trust-me. An auditor clicks through and checks the figure against the original 10-K.
We didn't ask the model to stop hallucinating. We removed its ability to be the source of a digit.
Read the full methodologyMost “historical” data is a lie told in hindsight.
It silently overwrites with restatements and quietly drops the companies that failed. Both errors inflate every backtest. Here is what ours does instead — visibly.
| Metric | as reported | restated |
|---|---|---|
| Revenue | 10,388 | 10,388 |
| Operating income | 2,114 | 1,902 |
| Net income | 1,640 | 1,431 |
| Diluted EPS | 3.05 | 2.66 |
verify_fact_lineage() → both versions retained · each keyed to its filing
- ENRNbankrupt · 2001
- LEHbankrupt · 2008
- WAMUseized · 2008
- BBBYbankrupt · 2023
- SIVBfailed · 2023
- FTXcollapsed · 2022
get_pit_universe(date) → the index as it stood, not as it survived
The adoption gap
Adoption is solved. Trust is the bottleneck.
91% of institutions are raising their AI budget this year — and the blockers that keep agents stuck in pilots are all the same blocker: an answer your firm can't stand behind. Valuein removes the cause, not the symptom.
Agents invent numbers
86% of CFOs say they have personally seen AI hallucinate a finance figure. A wrong number can't go near a client or an IC.
Resolved
Agents call typed tools that return SEC-filed values. There is no free-text number to invent — the model selects a fact, it doesn't author one.
Nobody can defend the answer
AI is the #1 compliance concern for RIAs (57%), and unauditable output fails the exam. “Trust the model” doesn't pass a DDQ.
Resolved
Every value carries a fact_id and a lineage envelope — EDGAR acceptance timestamp, source filing, one click to the original. Deterministic runs reproduce the same answer years later.
Autonomy nobody signed off on
95% of hedge funds already use generative AI — yet only 5% of asset managers let it act autonomously. The gap is governance, not appetite.
Resolved
Human-on-the-loop is the product, not a disclaimer: agents run the work, and every high-impact action waits in a staged approval ledger with an immutable audit log.
Your data and model leak into the vendor
Confidentiality keeps pilots from production. Deal interest, book positions, and prompts are all signal you can't hand a black box.
Resolved
Bring your own LLM. The key is sealed in a 24-hour cookie and never stored. Your data and your model never train ours; Enterprise adds zero-retention.
Hand your risk committee a guarantee, not a hope.
Every figure bound to its filing. The unbound ones blocked from exported reports — enforced by a build that fails without it. And 60% of LPs now favor managers with real AI governance: this pack is a fundraising asset, not a checkbox.
Start on the house. Scale when the work does.
Begin on the S&P 500 with no card, then open the full universe and smart-money signals as the work grows. Paid plans are priced per seat — per person, never per firm.
Free — S&P 500
$0no card
Begin on the S&P 500, 1993–present.
- Full S&P 500 history
- MCP, SDK & Workspace
- One token across channels
Pro
$49/mo per seat
The full universe for analysts & developers.
- 19,000+ companies, incl. delisted
- 15-year point-in-time window
- 95 tools + 28 workflows + SDK
Institutional
$499/mo per seat
Full history, smart-money, redistribution.
- 1993–present, all amendments
- Insider + 13F smart-money data
- Webhooks, SLA & redistribution
Add one connector. Get a research floor.
Start with the free tier — real filings in under 15 seconds, no card. Full 1993–present history on the S&P 500; connect an agent in 30 seconds or open the Workspace in your browser.