Skip to content

Connect your AI

Briefings and the write gate

Before an AI writes to the brain, it reads a briefing: the blocks every task of that kind must see, in full, plus related blocks and what the graph is missing. The write gate checks that it did, and that it loaded the right expert.

This is context engineering done once, on the server, instead of in every prompt. Nobody has to remember to paste in the tone of voice or the design system: the task type decides what an agent reads, and the server refuses a write that skipped it.

What a briefing is

get_briefing takes a task type, an optional target (a block key, a name like "Table component" or a route like /pricing) and the task in a sentence. It returns:

  • The required blocks, in full. For a UI component, for example: the stack profile, the component's spec, the colour system, the tone of voice and the page pattern.
  • Related blocks as excerpts, up to a token budget (by default per task type, between 2,000 and 64,000 tokens).
  • Every block as key@version, so what was read can be cited and checked later.
  • What the graph is missing for this task.
  • The expert for the task, and the sub-skill to read, if any.
  • A briefing_id to pass with the writes that follow.

The same input gives the same briefing.

Task types

Task typeForExpert
ui-componentA component in the design systemDesign
ui-pageA page or screen, by routeDesign
contentCopy and contentBrand
strategyStrategy, roadmap, business caseStrategy
researchPersonas, insights, researchUsers and research
productFeatures, glossary, information architectureProduct
marketingCampaigns, channels, content piecesMarketing
performanceAnalytics, KPIs, feedbackPerformance
build-backendAPIs, data, architecture, decisionsBuild
org-setupSetting up an organisation's shared context–
generalAnything else; takes the expert of its target–

The write gate

A write to a core block (one of the thirty-four entities) from an AI session is checked for four things:

  1. A recent briefing from the same caller, for this project, named by briefing_id or found as its latest one. Recent means the last two hours.
  2. The right expert. The briefing's expert must be the written block's (or one the briefing also names). A component spec written under a strategy briefing does not pass.
  3. The expert loaded. The session must have read the expert's method with get_skill and the project.
  4. The sub-skill. The first sub-skill the briefing names is read, or skipped with a reason in sub_skill_skipped, which is shown with the change.

A content piece past draft must also carry its brief: who it is for, their need, the moment and the intent.

Rules, learnings and documents bypass the gate on purpose: save_rule and log_learning stay the easiest way into the brain.

Enforce, warn or off

Each project sets the gate under Settings › Brain › AI agents:

ModeWhat happens
Enforce (the default)The write is refused, with the exact call that clears it
WarnThe write lands; the result says what to read first, and the session log counts it
OffNo gate

get_adoption reports how sessions behave: how many read a briefing and loaded their expert before their first write.

Without MCP

  • Over HTTP, the same briefing is POST /api/v1/projects/{projectId}/v3/briefing with { "task_type": "…", "target": "…", "task": "…" }. A briefing fetched with an API key counts for MCP writes with that key.
  • For a sub-agent or a tool that cannot reach Epic Context, get_context_pack returns a paste-ready summary of about 4,000 tokens.

Next

Last updated: