pruuf.
Admin
Checking your access…
⚠
Caution: The research, writer and Go Deeper prompts affect every article readers see. The teachers prompt drives the panel that labels the PRUUF judge's training data behind the scenes; the judge itself scores readers' articles with its own fixed prompt. Keep all {{TOKEN}} placeholders intact — they are substituted at runtime. Removing a token causes that value to appear literally in the prompt sent to the model.

Not editable here (changed in code and deployed): the PRUUF judge’s own prompt (judge-prompt.js, fixed by its training), Why this score (score-basis-prompt.js), the reader-language translation, the Tavily research pair, and reading text-message screenshots.
Loading…
Overview — Teachers prompt

The full scoring rubric, used by the teacher panel that labels the PRUUF judge’s training data. It does not score what readers see: the judge scores every reader’s article with its own fixed prompt.

Runs
After the reader already has their result (labelWithTeachers, from the teacher queue), and for admin comparisons on the Compare page and A/B tests.
Reads
The article, the research verdicts and prior facts, plus the category weights from Remote Config through the weight tokens below.
Produces
Category scores in the live rubric (v3: Facts & Sources, Framing, Reasoning, each 1–4; v2: eight categories, each 0–4), the opinion share and a summary per teacher; the panel’s median, grounded, becomes one training row in training_log.
Shows up
Nowhere directly. It shapes the next judge that is trained on these labels.
Model
The teacher panel on the Models page (ensemble members and the lead teacher).

A change here changes future training data, not today’s scores. Mixing old and new labels in one training run blends two rubrics, so note the date of any material edit.

Tokens — substituted at runtime from Remote Config weights
This editor holds the template of the live rubric (config/scoring.rubric): …. v3 takes the v3 tokens and weights from Remote Config fvi_category_weights_v3; v2 the v2 tokens and fvi_category_weights.
v3 (three categories, 1–4, 50/30/20)
{{W_FS}} {{W_FR}} {{W_RE}} {{TOT}} {{FORMULA}}
v2 (eight categories, 0–4) — this editor
{{W_FA}} {{W_OMR}} {{W_MT}} {{W_SVT}} {{W_IC}} {{W_DFO}} {{W_LI}} {{W_AI}} {{TOT}} {{FORMULA}} {{MAX}}
Characters: —
Version history Every save is kept. Restore loads it into the editor — review, then Save.
Loading…
Loading…
Overview — Research prompt (Prompt 1)

Checks the article’s factual claims against the web before anything is scored. Everything after it, the score, the explanation and Go Deeper, leans on the verdicts it returns.

Runs
First, on every article that is not answered from the cache. Skipped when the facts knowledge base already holds 3 or more fresh, relevant verified claims (≤ 30 days).
Reads
Today’s date {{TODAY}} and the article’s first 5,000 characters {{EXCERPT}}.
Produces
One line per claim: claim → Confirmed | Contradicted | Unverifiable — reason, with the search results it relied on.
Used by
The PRUUF judge (as evidence), grounding L2 (a contradicted claim lowers Factual Accuracy), the facts knowledge base, Why this score, Go Deeper and the writer.
Model
Research model and provider on the Models page (default Claude Haiku), one web search, 45 s limit.

This prompt is used only when the research provider is Anthropic, where Claude searches and judges in one call. With Tavily selected, research runs on two built-in prompts instead (pick the claims, then judge them against the search results), and edits here have no effect.

Tokens — substituted at runtime per request
{{TODAY}} {{EXCERPT}}
Characters: —
Version history Every save is kept. Restore loads it into the editor — review, then Save.
Loading…
Loading…
Overview — Writer prompt (Prompt 3)

Writes the parts of the reader’s panel the PRUUF judge was never trained to produce, from the judge’s finished, grounded result. It never re-scores anything: what it writes must agree with the score.

Runs
After grounding, on every new analysis, alongside Why this score and Go Deeper.
Reads
The final scorecard and verdict, the judge’s summary, the research verdicts on the article’s claims, and the article text. No tokens are substituted.
Produces
takeaway: the panel’s headline finding, at most 12 words, usually “what it gets right. Its weakness.”
topic: health, finance, legal or none, which decides whether the “Pruuf isn’t medical / financial / legal advice” note shows. Default none; set only when a reader might act on the article and be harmed.
article_summary: a neutral 2–4 sentence account of what the article reports.
Shows up
THE TAKEAWAY block in the extension panel and on shared result pages, the topic note under it, and the takeaway line in text-message replies.
Model
Writer model and provider on the Models page (default Claude Haiku).
Stored
…, the field of the live rubric (writerPromptV3 on v3, writerPrompt on v2). Empty means the built-in copy in functions/writer-prompt-v3.js or writer-prompt.js is live; edits apply within about 5 minutes.

article_summary is no longer shown anywhere (“what the article says” was removed in extension 1.55.0), but this prompt still asks for it, so every analysis pays to write it.

Tokens — none. Writes the takeaway and topic from the judge's finished result
no substitutions
Characters: —
Version history Every save is kept. Restore loads it into the editor — review, then Save.
Loading…
Loading…
Overview — Go Deeper prompt (Prompt 4)

Writes the section worth opening: how to read an article like this one, grounded in what research found. It is a separate call so that scoring can stay clinical while this part is written to be read.

Runs
Last, on every new analysis, because it reads what the earlier phases produced.
Reads
The article, each extracted claim with its verdict, the research notes, the pages research retrieved, and the grounded scorecard. No tokens are substituted.
Produces
The article’s kind (one of ten, e.g. breaking news, shopping, research coverage), a gravity register that keeps wit off grave subjects, 2–3 short bullets, two “learn more” paragraphs, a commercial flag and note, and up to three sources with tiers T1–T4.
Shows up
GO DEEPER · <KIND> in the panel’s Analysis tab and on shared result pages, translated into the reader’s language.
Guards
Only URLs the research phase actually retrieved may be cited; any other URL is dropped before it reaches the reader. Dashes are normalised and the language is checked against the article’s.
Model
Go Deeper model and provider on the Models page (default Claude Haiku).
Tokens — none. This prompt is not weight-dependent
no substitutions
Characters: —
Version history Every save is kept. Restore loads it into the editor — review, then Save.
Loading…
Scores each article twice — once under each candidate analysis prompt — and reports the difference. Nothing is persisted: no cache write, no facts-KB write, no outlet stats, so a run cannot contaminate production data. Research runs once per article and both variants receive the identical context, and prior-facts KB context is omitted, so the only thing that differs between A and B is the prompt. Single model, no ensemble. Only the deterministic grounding layers apply (L1 score recompute, L2 research-contradiction penalty).
Single-model scoring carries roughly ±14 points of run-to-run noise — use several articles and 2–3 repeats before trusting a delta.
A
0 characters
B
0 characters
—
Article A scoreB scoreΔ score A framingB framingΔ framing Cost
Category (mean across articles)ABΔ