Briefs & tests
Creative briefs, the next tests worth running, and Tests: a committed question, its linked artifacts, observations and conclusion.
meta_suggest_next
READ — What to produce next.
meta_list_briefs
READ — Briefs on the Briefs board (/app/briefs) — board briefs and the ones written from Next tests — newest first.
meta_get_brief
READ — One brief in full — by its id, or by its test id (`brief:<id>`, `note:<slug>`, a Next test id): every field, the learnings it cites (statement and status), and what was made from it.
meta_save_brief
WRITE — Put ONE brief on the Briefs board as a Draft: title, concept (the idea and why it should work), copy (hook, headline, primaryText, cta, leadFormId, script lines {from, to, onScreen, vo}), visual approach, reference ({kind: asset | swipe | ad, id} — an own winner or a swipe with a recipe gives the brief a format to work from, when there is one), deliverables ({count, format, ratios, maxSeconds}), success ({goalEvent, target, windowDays, minExpectedGoals} — the account goal by default), scope ({dimension, valueId}) and learningIds.
meta_save_briefs
WRITE — Save strategist briefs so the operator sees them under Briefs (/app/briefs).
meta_update_brief
WRITE — Change a brief: any of its fields (only those passed change; the evidence rule is checked again), its status, and what is linked to it.
meta_list_tests
READ — The creative tests this account has run, is running or has planned — answers "what tests have we run, and what did they show?".
meta_get_test
READ — One Test in full, by its id: its frozen intent (hypothesis, reference, keep / change, funnel, goal, the rule that judges it), the evidence snapshot it was decided on, what it produced (assets, ads, launches) and every Observation of its outcome, newest first.
meta_create_test
WRITE — Commit to a Next test: it becomes a Test whose intent is FROZEN — hypothesis, reference, keep / change, funnel, goal, and the rule that will judge it (comparator, the expected volume it needs before judging, how long it waits for late conversions, how long it runs) — with the evidence it was decided on.
meta_link_test_artifacts
WRITE — Tie what a Test produced to it, when it was not launched with its `testId`: assets (uploads), Meta ad ids, launches.
meta_observe_test
WRITE — Read a Test's outcome now and record it as a new Observation (append-only; nothing else changes).
meta_conclude_test
WRITE — Record a Test's Conclusion — supported, rejected, inconclusive or invalid — with a note on what it means for the next creative.
meta_abandon_test
WRITE — Stop a Test without a conclusion — the budget went elsewhere, or the question stopped mattering.