Prove your edge with receipts

Save your view as a claim tied to filings, let it be scored against what happens, and keep a record you can show.

Every thesis and claim scored over time — a verifiable track record for an allocator, a boss, or anyone evaluating you.

The pain

"Trust me, I called it" doesn't raise capital or win mandates. Without a time-stamped, scored record, your best calls are indistinguishable from luck — and your process is invisible to anyone evaluating you.

“I called it, but I cannot prove when.”
Without a timestamped record, a good call is only an anecdote.
“My thesis has no sources.”
Notes without citations do not survive a challenge.
“I never score my own calls.”
No feedback loop means no improvement.

The solution

1
Write claims, not vibes
save_claim records an atomic, evidence-backed statement cited to a filing; link_claim_to_thesis composes claims into a thesis with conviction and horizon.
2
Let the data grade you
score_claim and score_thesis_outcome auto-grade your calls against what actually happened — fundamentals plus a price leg scored off adjusted close. Your agent keeps score; your accuracy is measured, not asserted.
3
Make it public on your terms
list_public_theses_by_user powers a public @handle profile with your scored track record — an SEO/AEO-indexed page that turns your research into reputation.

Copy this

Real code and a ready prompt. Each block says what it needs before it runs.

APython SDK

No token needed: runs on the free sample

prove-your-edge-with-receipts.pypython

from valuein_sdk import ValueinClient with ValueinClient() as client:  # no key: the free sample    fin = client.financials("AAPL", freq="FY", periods=4)    # Trace one cell to the SEC filing it came from.    trail = fin.explain("TotalRevenue", "2024-09-28")    print(trail[["concept", "value", "form_type", "accession_id", "sec_url"]])

Runs on the free sample with no token. Claims and theses are saved through the MCP tools.

pip install valuein-sdk

BPrompt for Claude or ChatGPT

Works without a token on the free sample; your token unlocks your plan

prompt.txttext

Use save_claim to record this view with the filings it rests on, link_claim_to_thesis to attach it to my thesis, and score_claim when the outcome is known. Verify each cited figure with verify_fact_lineage first.

Tools it uses: save_claim, link_claim_to_thesis, score_claim, verify_fact_lineage

CConnect your AI client

No token? Delete the headers block and it runs on the free sample

mcp configjson

{  "mcpServers": {    "valuein": {      "url": "https://mcp.valuein.biz/mcp",      "headers": {        "Authorization": "Bearer YOUR_VALUEIN_TOKEN"      }    }  }}

What you get

Your edge becomes provable — a compounding, auditable record you can take to an allocator, a boss, or anyone evaluating you.

A dated claim with its evidence attached.
A score that follows the outcome, not your memory of it.
A record you can show a client or an IC.

Put a tireless analyst on every name you coverSee how Spread and comp any company in minutesSee how Find the mispricing with a reverse-DCFSee how

Frequently asked

Is my research public by default?

No — theses, claims, and reports are private by default. You choose what to publish to your @handle profile and what to keep private or share by link.

How are claims scored?

Each claim is an evidence-backed, testable statement cited to a filing. As new data arrives it's auto-graded against the outcome — fundamentals plus a price leg computed from adjusted close — building a measured accuracy record over time.

Try it on your own ticker.

The free sample needs no token and no card. One token works across your AI agent, your code and the Workspace.

Start free — no card See pricing