# Prompt set v1 — changelog (round 2)

v0 (`prompts/`) is unchanged and still produces round 1's prompts byte for byte. v1 is a new set beside it. A round-2 prompt is the byte concatenation of `v1/house-block.md` + `v1/charters/<desk>.md` + `v1/briefs/<subject>.md`, saved verbatim as each cell's `prompt.md`.

## House block v0 → v1
| Change | Why |
|---|---|
| The outlook is stated as the publication's: goodwill to humans and agents; humans and agents work better together, faster and smarter than either alone; useful to both; positive. | The publisher's standing positioning for the blog. v0 carried only the "together" theme. |
| The theme "may show in what you notice"; it is never a slogan, and the closing paragraph is not spent restating it. | Every round-1 post closed by restating the theme, and cold readers noticed the tic. |
| Length moves to the desk charter, always 900–1,400 words (v0: 600–900 for every desk). | Half of round 1 ran past 900 words, and the only model that stayed inside the cap every time wrote the weakest posts. The cap was fighting quality. |
| New rule: no claim of first-person experience, observation, or memory; reason from what is publicly known. | A round-1 guide said "the most common mistake I see". A model has seen nothing in that sense; the post carries an erratum. v0's Living Guides charter invited the clause ("opinionated where experience warrants it"), and v1 removes it. |
| "No fabrication" now names figures, benchmarks, studies, quotations, and events, and adds "if unsure, leave it out or say so". | Same law, made explicit. |
| New rule: the post is not about BlueFox's products — no product names, prices, figures, customers, partners, or launches; never "verified by BlueFox". | v0 banned only house figures. Round 1's readers said the prose ran ahead of the product. The publication's honesty starts with not selling inside the essays. |
| Competitor rule kept; open standards and open-source projects may be named as examples. | Round-2 subjects (checking receipts, record clocks) need to point at public standards without naming vendors. |
| New rule on record vocabulary: tamper-evident, not tamper-proof; append-only, not immutable; a signature never makes contents true; a countersigning witness is singular or "one or more". | The words that most often overclaim in this subject area. |

## Desk charters v0 → v1
| Desk | Change | Why |
|---|---|---|
| Living Guides | Addressee widened to people who build, operate, or *rely on* agents, followable by an agent too; "opinionated where experience warrants it" → "where the reasoning warrants it, with the reasoning shown"; 1,000–1,400 words; relay editions will publish each revision's changes. | The voice cure (above); guides need room. |
| Dear Agents | No stage business (no "welcome back to the desk", no invented letters); 900–1,200 words; `agent_summary` gains `cautions` and its first line is fixed. | Round 1's weakest openers were stage business; readers wanted to use the YAML. |
| Canon | Lens widened to receipt, log, witness, or watch; describe only plot points you are confident of; **name the strongest objection to the lens and answer it**; 900–1,300 words. | Round 1's best essay proved its brief instead of testing it; the strongest objection went unasked. |

## Briefs (new)
`check-a-receipt` · `five-clocks` (Living Guides) · `show-your-work` · `dated-dataset` (Dear Agents) · `the-machine-stops` · `accelerando` (Canon). Round-1 briefs are unchanged in `prompts/briefs/`.