Using Agent-to-Agent
Practical examples of how your AI tools can work with Chalie.
The talk_to_chalie tool
Every interaction goes through a single tool with four parameters:
| Parameter | Required | Description |
|---|---|---|
message |
Yes | What you want to say or ask Chalie |
agent_name |
Yes | Your tool’s identity (e.g. “Claude Code”, “CI Bot”) |
project_or_task_name |
Yes | The project or task context |
loop_in_human |
No | If true, Chalie tells the user about this exchange. Default: false |
When to loop in the human
Set loop_in_human: true when the exchange involves something the user should know about — decisions being made, actions taken on their behalf, or information that affects their day. Keep it false for background lookups and routine coordination.
Loop in: “Tell Dylan the deploy failed and his 3pm meeting conflicts with the rollback window.”
Don’t loop in: “What timezone is Dylan in?” or “What’s the project name for the billing service?”
Practical examples
Development workflow
Your coding assistant can pull context from Chalie to make better decisions:
- “Does Dylan have any meetings in the next 2 hours? I want to know if I should schedule a long build.”
- “What’s the current status of the billing service migration? Check Dylan’s documents and memory.”
- “Remind Dylan to review the PR I just opened — it’s for the auth refactor on the payments repo.”
CI/CD integration
A CI bot can keep Chalie informed about deployments:
- “The staging deploy for payments-api v2.3.1 just completed successfully. All 847 tests passed.”
- “Build #4521 failed on the main branch. The error is in the auth middleware — test_token_refresh is timing out.”
- “The nightly test run finished: 52 passed, 3 failed, 5 warnings. Score: 0.89.”
Cross-tool coordination
Multiple agents can coordinate through Chalie as a shared context layer:
- Research agent: “Store these findings about competitor pricing in Dylan’s documents — he asked for this yesterday.”
- Monitoring agent: “Dylan’s home office temperature has been above 28°C for an hour. Should I adjust the thermostat?”
- Calendar agent: “Dylan has back-to-back meetings from 2pm to 5pm. Don’t send him non-urgent notifications during that window.”
Personal assistant tasks
Agents can delegate personal tasks to Chalie:
- “Add milk, bread, and eggs to Dylan’s shopping list.”
- “What’s the weather forecast for this weekend? Dylan mentioned wanting to go hiking.”
- “Check if Dylan has any unread emails from his accountant.”
What Chalie can access
When your agent talks to Chalie, it has access to everything Chalie normally does:
- Memory — preferences, past decisions, personal context
- Calendar — schedule, events, conflicts
- Email — inbox, threads, sending
- Contacts — people, relationships, contact details
- Documents — uploaded files, notes, searchable content
- Lists — shopping, to-dos, any custom list
- Smart home — devices, automations, controls
- Weather — forecasts and conditions
- News — headlines and summaries
- Web search — current information from the web
- Scheduling — reminders, timers, recurring tasks
Tips
- Keep
agent_nameconsistent across calls so Chalie can track conversations per agent - Use
project_or_task_nameto scope the context — Chalie uses it to keep exchanges organised - Chalie remembers previous exchanges with your agent, so you can have multi-turn conversations
- If Chalie doesn’t have the answer, it’ll say so rather than guess