agent-native

How to configure, compose, or eject Agent-Native features into app-owned code. Use when overriding shared components or integrations, customizing a template, adding UI to chat or headless apps, or inspecting package source.

How to configure, compose, or eject Agent-Native features into app-owned code. Use when overriding shared components or integrations, customizing a template, adding UI to chat or headless apps, or inspecting package source.

Save a run-code fetch/join/aggregate script as a stored, refreshable data source any app's own charts/tables can render, instead of a hardcoded provider action or a per-view re-fetch. Use when an ad-hoc run-code or provider-api-request analysis should become a live, cached data source other users or panels can reuse.

How to delegate all AI work to the agent chat. Use when delegating AI work from UI or scripts to the agent, when a user asks for agent behavior or LLM-powered features, when tempted to add inline LLM calls, or when sending messages to the agent from application code.

How to delegate all AI work to the agent chat. Use when delegating AI work from UI or scripts to the agent, when a user asks for agent behavior or LLM-powered features, when tempted to add inline LLM calls, or when sending messages to the agent from application code.

Which tier — main thread vs. a cheaper subagent — owns a piece of work, decided at the moment you're about to start it. Use before writing an implementation yourself, driving a browser, babysitting a PR, running a test/fix loop, or doing a mechanical multi-file sweep on the main thread.

Required for any bug fix or behaviour change in the Design editor (the canvas, layers, inspector and export in templates/design/app), and for clips of Design editor bugs: copy the real design, reproduce the bug on it in a browser, fix obvious bugs directly, measure Figma only when the right behaviour is unclear, and verify side by side. Not for Design's server, actions or AI generation. Runs in a Fusion branch or on your own machine.

Use Design for UI/UX exploration, side-by-side design directions, interactive prototype previews, user selection, iteration, and design-to-code handoff through the hosted Design MCP app.

Inline, popup, and floating-button embeds — snippet generation and theming.

How event types work — fields, scheduling types, tabs in the editor, and the full set of configurable options.

How extensions render as widgets inside other apps via named UI slots — the framework's optional extension system. Use when an extension-enabled app needs to wire an ExtensionSlot or make an existing one-off custom block installable into a slot.

Creating, editing, and managing extensions — sandboxed Alpine.js mini-apps that run inside iframes. Use only when the host app explicitly enables extensions and the user asks for a one-off custom block or mini-app. Distinct from LLM "tools" (function calls) — see note below.

Connect external agents and MCP hosts (Claude, Claude Desktop, Claude Code, ChatGPT custom MCP apps, Codex, Cursor, Claude Cowork, VS Code GitHub Copilot, Goose, Postman, MCPJam) to an agent-native app over MCP, and round-trip artifacts back into the UI with MCP Apps and deep links. Use when adding an action's `link` builder or `mcpApp`, wiring the `/_agent-native/open` route, exposing an "ingest" action to MCP/A2A, or scaffolding apps from an external agent.

Declare, evaluate, manage, and remove framework feature flags. Use when shipping a capability gradually, targeting users or organizations, or replacing a compile-time rollout switch with a production-safe runtime flag.

How to find every sibling instance of a reported bug before fixing it. Use whenever a bug report names one file but the defect is a call pattern, hook, duplicated literal, or copy-pasted helper that plausibly exists in other files, apps, or templates.

Sets the visual direction for UI work, avoiding generic AI aesthetics. Use for any user-facing UI change: new surfaces, screenshot-driven feedback, copy/density cleanup, settings, control placement, or a "make this look good" pass. Do not load it only for purely mechanical wiring or formatting.

Generate transient or saved inline chat UI with Alpine/Tailwind controls, outputs, app state, and extensions. Use for knobs, pickers, calculators, dashboards, widgets, or reusable mini-apps.

Add or use full agent harness runtimes like Claude Code, Codex, Pi, Cursor, Mastra, or ACP agents inside Agent-Native.

Calendar + video provider integrations — Google Calendar, Office 365, Zoom, built-in video, Google Meet — and how to write new ones.

Cross-platform pattern for handling messaging integration webhooks (Slack, Telegram, WhatsApp, email, etc.) on serverless hosts. Use when adding a new integration adapter, debugging dropped messages, or wiring long-running agent work into a webhook handler.