@agent-native/core 0.122.4 → 0.123.0

package/corpus/core/docs/content/template-brain-agent.mdx

@@ -0,0 +1,103 @@
+---
+title: "Brain: Talking to the Agent & Cross-App Use"
+description: "Useful prompts for Brain, how it answers questions that span company memory and live app data, and how sibling apps ask Brain for cited answers over A2A."
+---
+
+# Brain: Talking to the Agent & Cross-App Use
+
+This page is for getting more out of Brain through chat, and for understanding what happens when a question needs both cited company memory and something only another app knows (a live metric, a mailbox, a workspace grant).
+
+## Useful prompts by task
+
+**Asking:**
+
+- "What did we decide about annual pricing, and where was that discussed?"
+- "Find the most recent onboarding-process change and cite the source."
+- "Summarize what this GitHub discussion means for the launch plan."
+
+**Reviewing:**
+
+- "Review the pending memory proposals and flag anything too vague to publish."
+- "Approve the Decision Digest proposal if the evidence holds up."
+
+**Source health:**
+
+- "Which sources are stale or failing sync?"
+- "Run a safe pilot on the #product-launches Slack channel and tell me what it would import."
+
+## Answering across company memory and live app data
+
+Brain owns cited company memory — reviewed knowledge, accessible raw captures, and source records. It does not reach into Analytics, Mail, Dispatch, or any other app's database directly. When a question needs both, the agent searches Brain first, then reads `federatedCoverage` on the result: a set of deterministic routing hints (not retrieved evidence) naming which specialist app to ask next and why. If the hints point at Analytics, Mail, or Dispatch, the agent calls that app's own agent for the live part of the answer and keeps the two sources labeled separately in its response — company-memory context from Brain, live data from the specialist app.
+
+<Diagram id="doc-block-brain4" title="A sibling app asks Brain for a cited answer" summary="Dispatch, Analytics, Mail, or any other workspace app can ask Brain a company-memory question over A2A and get back a cited answer plus routing hints for anything Brain doesn't own.">
+
+```html
+<div class="diagram-flow">
+  <div class="diagram-card">
+    <span class="diagram-pill">Dispatch / Analytics / Mail</span
+    ><small class="diagram-muted">asks a company-memory question</small>
+  </div>
+  <div class="diagram-arrow diagram-muted" aria-hidden="true">&rarr;</div>
+  <div class="diagram-box" data-rough>
+    A2A<br /><small class="diagram-muted">agent-to-agent call</small>
+  </div>
+  <div class="diagram-arrow diagram-muted" aria-hidden="true">&rarr;</div>
+  <div class="diagram-box" data-rough>
+    Brain retrieval<br /><small class="diagram-muted"
+      >audience-filtered search</small
+    >
+  </div>
+  <div class="diagram-arrow diagram-muted" aria-hidden="true">&rarr;</div>
+  <div class="diagram-panel center">
+    <span class="diagram-pill accent">Cited answer</span
+    ><small class="diagram-muted">+ routing hints for anything else</small>
+  </div>
+</div>
+```
+
+```css
+.diagram-flow {
+  display: flex;
+  align-items: center;
+  gap: 10px;
+  flex-wrap: wrap;
+}
+.diagram-flow .diagram-card {
+  display: flex;
+  flex-direction: column;
+  gap: 4px;
+  padding: 10px 12px;
+}
+.diagram-flow .diagram-box {
+  display: flex;
+  flex-direction: column;
+  gap: 4px;
+}
+.diagram-flow .diagram-arrow {
+  font-size: 20px;
+  line-height: 1;
+}
+.diagram-flow .center {
+  display: flex;
+  flex-direction: column;
+  align-items: center;
+  gap: 4px;
+}
+```
+
+</Diagram>
+
+Brain's public A2A surface is read-only and citation-backed by design — a sibling app can ask a company-memory question and get evidence back, but it can't write knowledge, approve a proposal, or change a source from outside Brain's own action surface. That authenticated write surface stays internal to Brain even though the read side is publicly discoverable.
+
+## Extensions: adding a custom widget to Brain
+
+Brain includes the standard Agent Native Extensions system: a sandboxed, agent-buildable mini-app that can render inside another surface. Ask the agent for a small dashboard, calculator, or widget and it's built as an extension rather than a source-code change. Extensions are managed from Brain's Settings page rather than a dedicated Brain route — see [Extensions](/docs/extensions) for what they can call and how they're sandboxed.
+
+## What's next
+
+- [**Brain overview**](/docs/template-brain) — what Brain is and when to pick it
+- [**Connecting & Reviewing Sources**](/docs/template-brain-sources) — provider setup and the Slack rollout
+- [**Asking, Citations & Knowledge**](/docs/template-brain-knowledge) — the Ask/Search/Knowledge/Review surfaces
+- [**Developer Guide**](/docs/template-brain-developers) — the full action reference, including the public A2A actions
+- [**A2A Protocol**](/docs/a2a-protocol) — cross-app delegation mechanics
+- [**Extensions**](/docs/extensions) — the sandboxed widget system

package/corpus/core/docs/content/template-brain-developers.mdx

@@ -0,0 +1,379 @@
+---
+title: "Brain: Developer Guide"
+description: "Data model, action reference, and extension points for forking or self-hosting the Brain institutional-memory template."
+---
+
+# Brain: Developer Guide
+
+This page is for anyone forking the Brain template, running it as a service, or wiring another app to call it. It covers the data model, the full action inventory, how source credentials resolve, and where to make changes.
+
+## Quick start
+
+```bash
+npx @agent-native/core@latest create my-brain --standalone --template brain
+```
+
+See [Getting Started](/docs/getting-started) for `cd`/install/dev steps. Open the app and choose **Start demo** to see cited memory with a seeded product-decision corpus before connecting a real workspace.
+
+## Data model
+
+All data lives in SQL via Drizzle. Brain's schema is `templates/brain/server/db/schema.ts` — **23 tables**, not the nine you'd guess from the core ingest-to-answer flow. The extra tables back three subsystems that don't show up in casual use: per-conversation audience scoping (who is allowed to see a given capture or knowledge entry), a hybrid full-text-plus-semantic search index, and lightweight source grouping ("projects").
+
+Retrieval itself has no vector-database dependency to run or pay for. Full-text search runs on every deployment target (SQLite, Postgres, Neon, D1, Turso). When the deployment is Postgres, Brain also builds a pgvector-backed semantic index automatically and blends its ranking with full-text results — no separate service, no extra configuration flag, and no vectors leave the same `brain_search_embeddings` table everything else lives in.
+
+<DataModel
+  id="doc-block-qwo0b1"
+  title="Brain data model — core ingest-to-answer flow"
+  summary={
+    "Connectors produce raw captures; distillation turns captures into reviewable knowledge; proposals gate sensitive entries. Sync runs and the ingest queue track background work."
+  }
+  entities={[
+    {
+      id: "sources",
+      name: "brain_sources",
+      note: "Connector config",
+      fields: [
+        {
+          name: "id",
+          type: "id",
+          pk: true,
+        },
+        {
+          name: "provider",
+          type: "text",
+          note: "manual / generic / clips / slack / granola / github",
+        },
+        {
+          name: "ingest_token_hash",
+          type: "text",
+        },
+        {
+          name: "status",
+          type: "text",
+        },
+        {
+          name: "last_synced_at",
+          type: "timestamp",
+          nullable: true,
+        },
+      ],
+    },
+    {
+      id: "source_shares",
+      name: "brain_source_shares",
+      note: "viewer / editor / admin",
+      fields: [
+        {
+          name: "source_id",
+          type: "id",
+          fk: "brain_sources.id",
+        },
+      ],
+    },
+    {
+      id: "captures",
+      name: "brain_raw_captures",
+      note: "Ingested raw payloads",
+      fields: [
+        {
+          name: "id",
+          type: "id",
+          pk: true,
+        },
+        {
+          name: "source_id",
+          type: "id",
+          fk: "brain_sources.id",
+        },
+        {
+          name: "external_id",
+          type: "text",
+          note: "dedupe key",
+        },
+        {
+          name: "content_hash",
+          type: "text",
+        },
+        {
+          name: "kind",
+          type: "text",
+        },
+      ],
+    },
+    {
+      id: "knowledge",
+      name: "brain_knowledge",
+      note: "Distilled atomic entries",
+      fields: [
+        {
+          name: "id",
+          type: "id",
+          pk: true,
+        },
+        {
+          name: "kind",
+          type: "text",
+          note: "decision / rationale / how-it-works / fact / open-question / process / risk / policy",
+        },
+        {
+          name: "topic",
+          type: "text",
+        },
+        {
+          name: "entities",
+          type: "json",
+        },
+        {
+          name: "confidence",
+          type: "real",
+        },
+        {
+          name: "publish_tier",
+          type: "text",
+        },
+      ],
+    },
+    {
+      id: "knowledge_shares",
+      name: "brain_knowledge_shares",
+      fields: [
+        {
+          name: "knowledge_id",
+          type: "id",
+          fk: "brain_knowledge.id",
+        },
+      ],
+    },
+    {
+      id: "proposals",
+      name: "brain_proposals",
+      note: "Pending review items",
+      fields: [
+        {
+          name: "id",
+          type: "id",
+          pk: true,
+        },
+        {
+          name: "op",
+          type: "text",
+          note: "create / update / archive",
+        },
+      ],
+    },
+    {
+      id: "proposal_shares",
+      name: "brain_proposal_shares",
+      fields: [
+        {
+          name: "proposal_id",
+          type: "id",
+          fk: "brain_proposals.id",
+        },
+      ],
+    },
+    {
+      id: "sync_runs",
+      name: "brain_sync_runs",
+      note: "Sync audit log",
+      fields: [
+        {
+          name: "source_id",
+          type: "id",
+          fk: "brain_sources.id",
+        },
+        {
+          name: "status",
+          type: "text",
+        },
+        {
+          name: "stats",
+          type: "json",
+        },
+      ],
+    },
+    {
+      id: "ingest_queue",
+      name: "brain_ingest_queue",
+      note: "Background distillation queue",
+      fields: [
+        {
+          name: "operation",
+          type: "text",
+        },
+        {
+          name: "status",
+          type: "text",
+        },
+        {
+          name: "priority",
+          type: "int",
+        },
+        {
+          name: "run_after",
+          type: "timestamp",
+          nullable: true,
+        },
+      ],
+    },
+  ]}
+  relations={[
+    {
+      from: "sources",
+      to: "captures",
+      kind: "1-n",
+      label: "ingested into",
+    },
+    {
+      from: "knowledge",
+      to: "captures",
+      kind: "n-n",
+      label: "evidence",
+    },
+    {
+      from: "knowledge",
+      to: "proposals",
+      kind: "1-n",
+      label: "gated by",
+    },
+    {
+      from: "sources",
+      to: "sync_runs",
+      kind: "1-n",
+      label: "audited by",
+    },
+  ]}
+/>
+
+The remaining 14 tables back the three subsystems above the diagram doesn't show:
+
+| Table                                | Subsystem      | What it holds                                                                                                                                                                                     |
+| ------------------------------------ | -------------- | ------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- |
+| `brain_audiences`                    | Access scoping | One row per distinct audience (org-wide, a private Slack channel's membership, a meeting's attendee list, or a restricted set), with an ACL hash and membership freshness state                   |
+| `brain_audience_members`             | Access scoping | Principal (user/org) membership in an audience, synced from the upstream provider                                                                                                                 |
+| `brain_audience_dependencies`        | Access scoping | An audience that inherits from another audience                                                                                                                                                   |
+| `brain_audience_source_dependencies` | Access scoping | Which sources an audience's membership depends on refreshing                                                                                                                                      |
+| `brain_capture_audiences`            | Access scoping | Which audience(s) can see a given raw capture                                                                                                                                                     |
+| `brain_sensitivity_events`           | Privacy        | The deterministic pre-storage privacy screen's decisions — suppressed, quarantined, released, discarded, or expired — with policy version and confidence band, never the sensitive content itself |
+| `brain_search_artifacts`             | Search index   | One denormalized, redaction-safe search document per capture (title, question, summary, resolution, systems, code refs)                                                                           |
+| `brain_search_bursts`                | Search index   | Chunked passages of a search artifact for finer-grained full-text and semantic matching                                                                                                           |
+| `brain_search_embeddings`            | Search index   | Vector rows for artifacts/bursts/knowledge, keyed by embedding set — populated only on Postgres deployments                                                                                       |
+| `brain_term_stats`                   | Search index   | Per-term document frequency, used for text-search ranking                                                                                                                                         |
+| `brain_search_corpus_stats`          | Search index   | Corpus-wide document count for ranking normalization                                                                                                                                              |
+| `brain_projects`                     | Projects       | A named grouping of related sources (ownable)                                                                                                                                                     |
+| `brain_project_shares`               | Projects       | Per-project share grants                                                                                                                                                                          |
+| `brain_project_sources`              | Projects       | Which sources belong to which project                                                                                                                                                             |
+
+Every allowed capture and derived row carries an audience id and ACL hash. Retrieval filters by audience before ranking, and an answer that spans multiple sources may only cite the intersection of their evidence audiences — a private Slack thread's content can't leak into an answer a non-member reads. Application state mirrors the current route, filters, and selected IDs so the agent always knows the current navigation and selection.
+
+## Full action inventory
+
+Brain ships 55 actions in `templates/brain/actions/`, grouped by area:
+
+- **Source management** — `create-source`, `update-source`, `delete-source`, `get-source`, `list-sources`, `sync-source`, `sync-due-sources`, `run-slack-pilot`, `test-slack-connection`, `rotate-source-ingest-token`
+- **Capture ingestion** — `import-capture`, `import-transcript`, `list-captures`, `get-capture`, `mark-capture-distilled`, `resanitize-captures`, `remediate-legacy-capture-audiences`
+- **Distillation** — `enqueue-distillation`, `enqueue-captures-distillation`, `claim-distillation`, `retry-distillation`, `list-distillation-queue`
+- **Knowledge & review** — `write-knowledge`, `get-knowledge`, `list-knowledge`, `set-knowledge-canonical`, `preview-canonical-resource`, `list-proposals`, `review-proposal`, `approve-proposal`, `reject-proposal`, `update-proposal`
+- **Search & retrieval** — `ask-brain`, `search-knowledge`, `search-everything`
+- **Projects** — `list-projects`, `manage-project` (create/update/delete/set-default a named grouping of sources)
+- **Health & connections** — `get-brain-health`, `list-connection-providers`, `get-pilot-report`
+- **Settings** — `get-brain-settings`, `update-brain-settings`, `set-settings`, `get-settings`
+- **Evaluation & demo** — `seed-demo-data`, `run-demo-eval`, `run-retrieval-eval`
+- **Context & navigation** — `view-screen`, `navigate`
+- **Provider APIs** — `provider-api-catalog`, `provider-api-docs`, `provider-api-request`, `list-staged-datasets`, `query-staged-dataset`, `delete-staged-dataset`
+
+A few worth calling out specifically:
+
+- **`get-brain-health`** backs the [Ops page](/docs/template-brain-sources#ops) and answers "why isn't X in Brain yet" cheaper than inspecting sources by hand: the same per-source health value shown there, plus distillation queue counts, pending proposals, and ordered next setup steps.
+- **`get-pilot-report`** summarizes one source's sync health, capture counts, queue state, published knowledge, and pending proposals without returning raw capture bodies — call it after a Slack safe-pilot sample sync.
+- **`rotate-source-ingest-token`** is reachable from the Sources UI ("Rotate ingest token" on a source card) but is not agent-callable (`agentTool: false`) — it's a deliberately human-only control since the new token is shown once and can't be recovered.
+- **Staged-dataset actions** (`list-staged-datasets`, `query-staged-dataset`, `delete-staged-dataset`) let the agent stage a large provider pull with `provider-api-request`'s `stageAs`, then filter/aggregate it without re-fetching — the same pattern used across Agent Native's provider-API surface.
+
+## Connecting sources
+
+Brain resolves every provider-backed source's credential in this order, and never skips ahead to ask for a duplicate token if an earlier tier already has one:
+
+1. A granted workspace connection (`workspace_connections` / `workspace_connection_grants`) for `appId=brain` — a credential Dispatch or another app already connected and granted to Brain.
+2. Backward-compatible Brain-local SQL credentials.
+3. Registered vault secrets scoped to the same user/org/workspace.
+
+Brain source credentials **do not** fall back to raw deploy-level environment variables — `.env`/`.env.local` alone will not satisfy a source's credential check. `list-connection-providers` reports per-provider readiness (`connected`, `granted`, `needs_grant`, `not_connected`) plus credential health; check it before adding a new token.
+
+**Clips and generic webhooks.** Brain exposes a signed webhook for Clips and generic transcript/capture imports. Create a source with a `sourceKey` to receive a bearer token, then send a `RawCapturePayload` with `Authorization: Bearer <ingestToken>`.
+
+<Endpoint id="doc-block-1udptrp" title="Signed ingest webhook" summary="Clips and generic transcript/capture imports post a RawCapturePayload with a per-source bearer token." method="POST" path="/api/_agent-native/brain/ingest" summary="Import a raw capture from Clips or a generic source" auth={"Bearer <ingestToken> issued per source via its sourceKey"} request={{
+  "contentType": "application/json",
+  "example": "RawCapturePayload — bounded transcript / capture body"
+}} responses={[
+  {
+    "status": "200",
+    "description": "Capture accepted and queued for distillation"
+  },
+  {
+    "status": "401",
+    "description": "Missing or invalid ingest bearer token"
+  }
+]}>
+
+</Endpoint>
+
+Slack, Granola, and GitHub sources can opt into background `autoSync` with a poll cadence once review quality is proven. See [Connecting & Reviewing Sources](/docs/template-brain-sources) for the per-provider setup flow and the Slack rollout sequence.
+
+## Layout
+
+<FileTree
+  id="doc-block-brain1"
+  title="Brain layout"
+  entries={[
+    {
+      path: "actions/",
+      note: "55 agent-callable operations — source lifecycle, ingestion, distillation, knowledge/review, search, projects, settings, eval",
+    },
+    {
+      path: "app/routes/",
+      note: "Ask (/), Search, Knowledge, Review, Sources, Ops, Settings, Team, Extensions",
+    },
+    {
+      path: "server/db/schema.ts",
+      note: "23 tables across sources, captures, knowledge, audience scoping, search index, and projects",
+    },
+    {
+      path: "server/lib/",
+      note: "brain.ts (shared helpers), brain-health.ts, search.ts, hybrid-search.ts, search-index.ts, ingest-queue.ts",
+    },
+    {
+      path: ".agents/skills/brain/",
+      note: "SKILL.md (public-safe workflow) plus RUNBOOK.md (internal architecture/ops detail, not in these docs)",
+    },
+    {
+      path: ".agents/skills/ingestion-and-connectors/",
+      note: "Source lifecycle, health states, and credential resolution",
+    },
+    {
+      path: ".agents/skills/ask-across-everything/",
+      note: "Cross-app delegation rules for federatedCoverage",
+    },
+  ]}
+/>
+
+## Customizing it
+
+Brain follows the agent-native four-area contract — change behavior by editing the matching area, and the agent can make these edits for you:
+
+- `templates/brain/app/routes/` — the UI surface: Ask, Search, Knowledge, Review, Sources, Ops, Settings, Team, and Extensions routes.
+- `templates/brain/actions/` — every agent-callable operation. Add a new file with `defineAction` to expose a new capability.
+- `templates/brain/.agents/skills/` — Brain-specific guidance for ingestion, distillation, and retrieval. Update or add a skill when you teach the agent a new workflow.
+- `templates/brain/AGENTS.md` — top-level agent guide. Update when you add major features.
+- `templates/brain/server/db/schema.ts` — data model. Additive migrations only.
+
+Ask the agent to make changes for you — it can edit its own source. See [Self-Modifying Code](/docs/key-concepts#agent-modifies-code).
+
+## What's next
+
+- [**Brain overview**](/docs/template-brain) — what Brain is and when to pick it
+- [**Connecting & Reviewing Sources**](/docs/template-brain-sources) — provider setup, the Slack rollout, and source health
+- [**Asking, Citations & Knowledge**](/docs/template-brain-knowledge) — the Ask/Search/Knowledge/Review surfaces
+- [**Talking to the Agent & Cross-App Use**](/docs/template-brain-agent) — prompts, `federatedCoverage`, and A2A
+- [**Actions**](/docs/actions) — the action system Brain is built on
+- [**A2A Protocol**](/docs/a2a-protocol) — cross-app delegation
+- [**Extensions**](/docs/extensions) — the sandboxed widget system available from Brain's Settings page

package/corpus/core/docs/content/template-brain-knowledge.mdx

@@ -0,0 +1,50 @@
+---
+title: "Brain: Asking, Citations & Knowledge"
+description: "How to ask Brain a cited question, browse distilled company knowledge, and review a pending proposal before it publishes."
+---
+
+# Brain: Asking, Citations & Knowledge
+
+This page is for anyone using Brain day to day: asking a question, browsing what Brain already knows, or reviewing something before it becomes official company knowledge.
+
+## Asking a cited question
+
+Ask is the front door. Type a plain-English question — "why did we retire the freemium tier?" — and Brain answers from approved company knowledge, with links back to the Slack thread, meeting, transcript, issue, or webhook capture that supports the answer. Open any citation to see a source timeline: when the underlying decision was captured, when supporting evidence was added, and when it was approved.
+
+<Callout tone="info">
+
+**Brain won't guess.** If nothing in approved knowledge (or, depending on settings, in raw source material) supports an answer, Brain says so instead of inventing one. A confident-sounding wrong answer is worse than an honest "I don't have evidence for that yet."
+
+</Callout>
+
+## Where Search fits next to Ask
+
+Ask is a conversation. Search is a filterable list — useful when you want to scan everything Brain has on a topic rather than get one synthesized answer. It's a separate page (not in the main sidebar; open it from the Cmd+K command menu or navigate directly) with filters for project, record type (knowledge, capture, or source), source, and status, so you can narrow down to exactly the record you're looking for before opening it.
+
+## Browsing distilled Knowledge
+
+The Knowledge page lists every distilled, approved entry: what kind it is (decision, rationale, how something works, a plain fact, an open question, a process, a risk, or a policy), its topic, a confidence score, the evidence it cites, and — when a newer entry replaces an older one — a link showing what it supersedes.
+
+<WireframeBlock id="doc-block-brain3">
+  <Screen
+    surface="desktop"
+    html={
+      "<div style='display:flex;flex-direction:column;gap:14px;padding:18px;min-height:520px;box-sizing:border-box'><div style='display:flex;align-items:center;gap:10px;padding-bottom:10px;border-bottom:1.4px solid var(--wf-line)'><h1 style='margin:0'>Knowledge</h1><span class='wf-pill'>Kind: All</span><span class='wf-pill'>Topic: All</span><span class='wf-pill'>Tier: All</span><div style='flex:1'></div><span class='wf-pill accent'>42 entries</span></div><div class='wf-card' style='display:flex;flex-direction:column;gap:6px'><div style='display:flex;align-items:center;gap:8px'><span class='wf-pill accent'>Decision</span><strong style='flex:1'>Retiring the freemium tier</strong><span class='wf-pill'>92% confidence</span></div><p class='wf-muted' style='margin:0'>Freemium signups converted at a fraction of trial signups; support cost per account exceeded contribution margin.</p><div style='display:flex;gap:8px;flex-wrap:wrap'><span class='wf-pill'>Pricing RFC</span><span class='wf-pill'>Launch retro</span><span class='wf-pill warn'>Supersedes: Freemium v1 policy</span></div></div><div class='wf-card' style='display:flex;flex-direction:column;gap:6px'><div style='display:flex;align-items:center;gap:8px'><span class='wf-pill'>Process</span><strong style='flex:1'>How Decision Digest works</strong><span class='wf-pill'>88% confidence</span></div><p class='wf-muted' style='margin:0'>Weekly digest compiles approved decisions from the prior seven days and posts a summary to product.</p></div><div class='wf-card' style='display:flex;flex-direction:column;gap:6px'><div style='display:flex;align-items:center;gap:8px'><span class='wf-pill'>Policy</span><strong style='flex:1'>Support tickets never quote pricing</strong><span class='wf-pill'>95% confidence</span></div></div></div>"
+    }
+  />
+</WireframeBlock>
+
+## Reviewing and approving a pending proposal
+
+Not everything Brain distills publishes immediately. High-confidence, non-sensitive entries can publish right away, but anything sensitive, low-confidence, or set to company-wide visibility queues as a proposal first. Review shows the proposed title and body, the rationale, and the exact evidence it's based on, so a reviewer can edit wording, inspect the source, and approve or reject before it becomes something the whole company can be told as fact.
+
+## Mirroring approved knowledge as ambient context
+
+An approved, canonical entry can also be mirrored into a shared workspace resource, so other apps (Dispatch, and anything else in the workspace) can use it as ambient context without asking Brain directly. Turning this on is a deliberate choice per entry — reserved for durable decisions, policies, or product facts that are genuinely safe to hand to every app in the workspace — and Brain always shows the exact text that will be written or removed before it happens.
+
+## What's next
+
+- [**Brain overview**](/docs/template-brain) — what Brain is and when to pick it
+- [**Connecting & Reviewing Sources**](/docs/template-brain-sources) — where this knowledge comes from and how sources are kept healthy
+- [**Talking to the Agent & Cross-App Use**](/docs/template-brain-agent) — example prompts for asking, reviewing, and checking source health
+- [**Developer Guide**](/docs/template-brain-developers) — the knowledge and proposal data model and full action reference