PHORbetaRequest an invite

Evidence before conviction.

Research for startup investors: trace a trend to the companies in it, see what the sources actually establish, and make the call yourself.

Request an inviteSee an evidence record

PHOR uses AI to read everything. It never lets a summary pass for a source.

How to read these plates

Source
The document as retrieved, with its page and hash.
Machine reading
What a model read into it. Kept on its own sheet, pointing at the passage.
Human decision
You make the decision.

A plausible answer is not evidence.

AI can give you an answer in seconds. Can you retrace why you believe it?

  • Search result≠Evidence
  • Model answer≠Source
  • Company claim≠Independent validation
  • Mention≠Affiliation
  • Repository≠Company
Same project, two sources

One project, two numbers: the OpenMAIC v1.0.0 release says 20 built-in skills. The current README says 24.

20built-in skillsv1.0.0 release notes2026-08-27
24built-in skillsCurrent README2026-09-26

Both are right. The release note is frozen at v1.0.0; the README describes the repository today.

Summary, source dropped24 built-in skills

A summary that just says “24” has lost the version. PHOR keeps each claim tied to its source and date.

Follow the signal. Keep the evidence.

Seven stages, each one on record and open to inspection.

  1. 1

    Signal

    A weak lead, such as a rising repository. Not evidence yet.

  2. 2

    Question

    Written down: what would have to be true?

  3. 3

    Source

    Retrieved and hashed, with its URL, page and role.

  4. 4

    Claim

    One narrow statement, tied to the exact passage.

  5. 5

    Evidence

    A claim the source supports, with a stable ID.

  6. 6

    Thesis

    Propositions you can test, each with a status.

  7. 7

    Monitor

    Searches aimed at gaps and catalysts.

8

Decision

Made by a person, outside the pipeline.

GitHub is the discovery feed today. Other signal sources are intended, not built.

Evidence, not chat.

An accepted record keeps its source and says where its reach ends.

Example case: Instava

E009Cadvex annual report

“Investments — Instava Inc USA”

Source
Annual Report 2018–19
Page
Physical page 98
Role
Historical financial report
URL
https://www.cadvex.example/investors/annual-report-2018-19.pdf illustrative
Document date
2019-08-30 illustrative
Retrieved
2026-09-26
SHA-256
00697bc7e5793d06f41dd6c4848a6a62f89fa647ae7a634a03ae35c7dbcc4972

Establishes

historical reported investment entry

Does not establish

current ownership or current investment access

The entry is real history. It says nothing about who owns what today.

The URL and document date on this card are illustrative.

Evidence packet P01Analysis runs against a frozen evidence packet with its own hash. New evidence never rewrites an old conclusion.952344713d54bf276b0f3012c5edd1586b7cfa937993047eb29073f9f5c24a67

Machine readingPHOR is moving toward typed automated review for obvious matches. Overstatement, ambiguity and layout risk go to a person.

Research that accumulates.

A chat scrolls away. A research case keeps what was searched, inspected, accepted, rejected and left unknown.

Chat transcript

  1. Prompt
  2. Answer
  3. Forgotten

The reasoning lives in prose you can't cite.

Research state

  • E001Indian legal entity: incorporation and registration details
    • SUPPORTST01Instava is an identifiable company with an Indian legal entitySUPPORTED
    • G01Find customer-owned evidence
    • C01Independent customer documents production AI-agent deploymentWATCHING
  • E002Company-authored AI-agent positioning
    • QUALIFIEST02Customers deploy Instava AI-agent functionalityUNTESTED

Evidence, theses, gaps and catalysts, each with an ID you can follow.

E001 supports T01. G01 names what T02 still lacks. C01 watches for it.

A thesis you can test.

A thesis is a set of propositions. A person sets each status; it is never inferred from model output.

T02PropositionUNTESTED

Customers deploy Instava AI-agent functionality

Support
No independent deployment evidence yet
Gap
G01 Find customer-owned evidence
Evidence
  • QUALIFIESE002Company-authored AI-agent positioning
  • QUALIFIESE003Company-published customer and testimonial material
  • QUALIFIESE009Cadvex annual report, Instava Inc USA entry
  • SUPPORTSnone yet

Model output

INVESTWATCHPASS

Evidence packet P01

Human decision

PHOR can draft INVEST, WATCH or PASS. That is model output, stored with its evidence packet. Your decision is a separate record.

Monitor what matters.

PHOR searches against propositions, gaps and catalysts, not the company's name.

A catalyst is not a prediction. It is something worth watching.

C01CatalystWATCHING

Watching for

Independent customer documents production AI-agent deployment

Direction
STRENGTHENS
Proposition
T02 Customers deploy Instava AI-agent functionality

Each result is sorted: new source, known source, duplicate lead or irrelevant.

  • NEW_SOURCE
  • KNOWN_SOURCE
  • DUPLICATE_LEAD
  • IRRELEVANT

Monitoring finds possible new evidence. It never rewrites a thesis or marks a catalyst observed.

How PHOR thinks.

  • Lead → inspectA search hit points at a source. Open the source.
  • Claim → verifyCheck that the source says this, and no more.
  • Evidence → citeAnalysis cites evidence IDs, not untraceable prose.
  • Thesis → testA proposition is only as strong as its evidence.
  • Catalyst → watchName what would change the case, then watch.
  • Decision → humanA model may recommend. A person decides.

Bring a question.

PHOR is a small beta for people who do primary research, alone or in a small team. Leave your email and what you research. We'll write back.

Or email phor@fff.ad