Skip to main content
idapt
HomeCodeAI ModelsPricing
Sign inStart free
  • Home
  • Pricing
  • AI Models
  • Image models
  • Voice models
  • Video models
  • Rankings
  • New models
  • Model status
  • Multi-Model Chat
  • Voice Mode
  • Voice HUD
  • Web Search
  • Image Generation
  • Video Generation
  • Audio Generation
  • Transcription
  • Drive
  • Credentials
  • Sharing
  • Workspaces
  • Tasks
  • Memory
  • Agents
  • Subagents
  • Automations
  • Skills
  • idapt Code
  • Code Execution
  • Computers
  • Computer Use
  • Computer Assist · Soon
  • Containers · Soon
  • Cloud Computers
  • Local AI
  • AI Gateway
  • API & SDK
  • CLI
  • MCP
  • Tunnels
  • All features →
  • LLM cost calculator
  • Token counter
  • Context window checker
  • Can I run it
  • Model picker quiz
  • Savings finder
  • Video cost estimator
  • Text to speech cost
  • Transcription cost
  • API endpoint tester
  • All free tools →
  • Blog
  • Use cases
  • Comparisons
  • Best of
  • Skills
  • Learn
  • Changelog
  • Help center
  • FAQ
  • Privacy
  • Compare all models
  • Support
  • idapt Code
  • Developers
  • Quickstarts
  • API reference
  • API pricing
  • CLI
  • MCP
  • Downloads
  • Desktop
  • Badges and embeds
© idapt[email protected]TermsPrivacy PolicyLegal noticeReport content
X (Twitter)
Help Center
🪝

Hooks

Found this helpful? Share it:

Hooks are short reminders idapt adds to every chat turn to keep an agent on track. Each agent ships with a set of platform hooks. Think of them as default habits that come built in 🪝

What hooks do

On each turn, hooks add short pieces of guidance to what the agent sees, like today's date, the agent's own identity, or the list of computers attached to the chat. They run quietly: you do not see them in the transcript, but they shape how the agent responds.

What the platform hooks do

Every agent ships with the same built-in hooks. The ones you are most likely to notice:

  • Agent persona: keeps the agent's name and instructions fresh on every turn.

  • Today's date: gives the agent a stable sense of time, so it does not guess.

  • Computers: surfaces the computers reachable from the chat, so the agent knows what it can use.

  • Tool schemas: explains which tools are off or unavailable on this run.

  • Workspace members: names who is in the workspace, so the agent can assign work correctly.

Related articles

🤖

Agents

Create AI personas with custom instructions, their own memory, and their own default model.

Up next

Agent notifications

Let agents ping you when a long task finishes or needs a decision.

Was this helpful?