How this page writes itself.

Orchestration is code. Only one model has a tool: the researcher can read pages, and code decides which ones. The one that reads the web cannot write anything; the one that writes never reads the web; only code publishes.

Figures from the run of 13 October 2026

1. code
   Collect

   Reads feeds from a hand-kept allowlist. Drops what was already seen.

   39new items
2. Haiku 5.5
   Triage

   Scores the items. Keeps the best six, or none.

   6topics studied
3. Sonnet 5.5 × N
   Research

   One agent per topic, with a single tool: fetch_page. Allowlist, at most 3 pages and 6 turns, every call traced.

   19facts proposed
4. code
   Gate 1

   Each quote must appear word for word in a page the agent actually read. Otherwise the fact is gone.

   19quotes found
5. Sonnet 5.5
   Fact check

   Fresh context. Judges each fact against its quote, in both languages. A refused fact never reaches the writer.

   17facts validated2 refused
6. Sonnet 5.5
   Writing

   Writes in French and English from validated facts only. Never sees the web.
7. Sonnet 5.5
   Statement check

   Judges each written sentence against the facts it cites.

   8statements published
8. code
   Gates 2

   Verifier threshold, volume, budget. One failure and nothing is published.
9. code
   Publish

   Writes the files. The trace is published either way.

What this does not guarantee

The gates prove a sentence is sourced, not that the source is right. An allowlisted page that is wrong will be quoted faithfully. And an exact quote can be refused because the page changed in the meantime: the pipeline prefers a day without an edition to a doubtful one.

Verifier eval

10/10 trap cases judged correctly, last run 13 October 2026.

Last 1 runs

What the pipeline refused to publish

• Haiku 5.5 uses a new tokenizer: the same long prompt uses around 1.25x as many tokens as with Haiku 4.5, according to the author's Claude Token Counter tool.relies on a fact its quote does not support (The quote only says the same prompt uses about 1.25x more tokens and does not state that Haiku 5.5 uses a new tokenizer.)
• Max 5x users will get $100 in API credits per month, Max 20x users $200, and Team subscribers up to $500, pooled across their users.relies on a fact its quote does not support (The quote says "credits" without specifying they are API credits, so the claim adds a detail not in the quote.)