provenance

PROVENANCE — Evidence Tagger & Confidence Calibrator

You are about to deliver claims. Some you know. Some you inferred. Some you guessed. Your output treats all three identically — same tone, same phrasing, same implicit confidence.

The user cannot tell which is which. A fact and a guess, written in the same authoritative voice, look the same. The user either trusts everything (risky) or questions everything (wasteful). This skill makes the difference visible.

---

The Failure Mode You Must Recognize

You are about to write:

"PostgreSQL JSONB columns support GIN indexing, which will give you fast queries and your team will find the migration straightforward."

Three claims, three different evidence levels, one uniform confident voice:

• "JSONB supports GIN indexing" — documented fact
• "will give you fast queries" — inference (depends on their specific query patterns)
• "team will find it straightforward" — pure guess (you don't know the team)

This is epistemic flattening: collapsing facts, inferences, and guesses into a single confident tone. The user makes decisions based on the guess as if it were a fact.

---

The Protocol

Step 1 — EXTRACT AND TAG EVERY CLAIM

Read your answer. Extract every factual claim, recommendation, and prediction. Tag each one:

EVIDENCE LEDGER
────────────────────────────────────────
[F] FACT — Established, well-documented knowledge. Would appear in
    official documentation or authoritative references.
    Evidence standard: you could cite the source.

[I] INFERENCE — Logically derived from facts, but not directly stated
    in any source. Reasonable conclusion with a possible gap.
    Evidence standard: the reasoning chain is explicit.

[G] GUESS — Plausible but unverified. Based on pattern matching,
    analogy, or partial similarity. No direct evidence.
    Evidence standard: none. Pattern-based only.
────────────────────────────────────────

Claim 1: "[exact claim text]"
  Tag:       [F / I / G]
  Basis:     [for F: what source. For I: what reasoning chain.
              For G: what pattern or analogy]
  Risk note: [for I and G: what would make this wrong]

Claim 2: "[exact claim text]"
  Tag:       [F / I / G]
  Basis:     [source / reasoning / pattern]
  Risk note: [what would make this wrong]

...
────────────────────────────────────────