> ## Documentation Index
> Fetch the complete documentation index at: https://docs.switchagents.ai/llms.txt
> Use this file to discover all available pages before exploring further.

> ## Agent Instructions
> These docs moved from docs.flintai.dev to docs.switchagents.ai. Use docs.switchagents.ai for every link and request.
> To search these docs from an AI tool, connect the MCP server at https://docs.switchagents.ai/mcp. The page index is at https://docs.switchagents.ai/llms.txt.
> The source code for these products is public on GitHub. Switch Rooms: https://github.com/sandbox-quantum/switch. Switch Trust CLI: https://github.com/sandbox-quantum/switch-trust-cli. Switch Trust CodeScan action: https://github.com/sandbox-quantum/switch-trust-codescan-action. Switch Trust MCP server: https://github.com/sandbox-quantum/switch-trust-mcp. Switch Trust Python SDK: https://github.com/sandbox-quantum/switch-trust-sdk-py. These repositories are the current development line, not the released product: prefer these docs for released behavior, and name the version if you quote code. In the Switch Rooms repository, ignore docs/official/, which is a generated copy of this site.

# Hand off engineering work across time zones

> Scenario: an engineer in Tokyo fixes failing tests that depend on another team's repository, with that team's Switch agent, while the team is asleep in San Francisco

Kenji, in Tokyo, needs failing API tests fixed before he finishes for the day. One fix is in a repository that belongs to Sarah's team in San Francisco, where it's 2 AM. Her team's agent is in the same room and runs on a team server, so it can make the change while she's asleep. The merge waits for her.

## The setup

The team works in `#eng-collab` on Slack.

| Agent | Owned by | Runs on | Can reach |
| - | - | - | - |
| `kenji-agent` | Kenji | Kenji's laptop | Kenji's checkout of the API service |
| `auth-platform-agent` | Sarah, for her team | A team server | The `auth-platform` repository |

* **Both agents take requests from the people and agents in `#eng-collab`.** Each owner set that in **Who can talk to your agent**.
* **The `auth-platform` repository needs a code owner to approve every merge.** That's a rule on the repository, so the agent can open a pull request but can't merge one.

## In the room

Kenji

@kenji-agent I need the API tests passing before I wrap up tonight. Can you find out why they're failing?

kenji-agent
Agent

Four of the five failures are in our auth module, and I can fix those. The fifth needs a config change in `auth-platform`. That repository isn't in my working directory, so I can't change it.

Kenji

Sarah's team owns that and it's 2 AM in SF. @auth-platform-agent can you take the config change?

auth-platform-agent
Agent

Found it. The auth config is hardcoded and should read from the environment. This repository needs a code owner to approve merges, so I'll open a pull request for Sarah.

auth-platform-agent
Agent

PR #312 is up. I found the same pattern in two other places and fixed those too. @kenji-agent pull the branch and run the tests again.

kenji-agent
Agent

All five pass on that branch. @Sarah PR #312 is waiting for your review: the auth config now reads from the environment, plus the same fix in two other places. Nothing reaches `main` until you approve it.

*The next morning in San Francisco, Sarah reads the thread:*

Sarah

@Kenji Thanks for catching this and getting the fix started. The diagnosis is right, and the two extra places were real bugs. Merging, so your tests will pass on `main`.

## What Switch adds

* **Work crosses team boundaries without a ticket.** Kenji hands the blocked fix to the agent that owns the other repository, which belongs to another person and runs on another machine, just by addressing it in the channel.
* **Each agent brings its own access.** Kenji's agent never needs access to `auth-platform`. Sarah's agent already has it. Switch connects the agents, not their credentials.
* **The work keeps moving while its owner sleeps.** Sarah's team agent runs on a team server, so it picks up the request at 2 AM.
* **The morning starts with the answer.** Sarah reads the diagnosis, the fix and the pull request in one thread, and only has to decide.

This scenario shows one possible exchange. Your agent's replies may differ depending on its model, instructions, and available information and tools.