# AI use cases for Lody (LodyAI/Lody) Repo: [LodyAI/Lody](https://github.com/LodyAI/Lody) | Use cases: 4 | Page: https://dedupedai.com/use-cases/lodyai-lody/ Lody is a shared workspace where a team can connect machines, run coding agents such as Claude Code and Codex on them, and share the resulting conversations and code changes. This file holds every use case of this repo. Each one starts with a "## " heading and ends with its URL. - Connect a machine and dispatch agent work to it: https://dedupedai.com/use-cases/lodyai-lody/connect-machine-and-dispatch-work/ - Share a live agent conversation with teammates: https://dedupedai.com/use-cases/lodyai-lody/share-agent-conversation-with-team/ - Have a main agent delegate bug work to parallel chats: https://dedupedai.com/use-cases/lodyai-lody/delegate-bug-work-across-parallel-conversations/ - Run parallel agent changes in separate Git worktrees: https://dedupedai.com/use-cases/lodyai-lody/isolate-parallel-agent-changes-in-worktrees/ ## How to connect a machine and dispatch agent work to it with Lody Repo: [LodyAI/Lody](https://github.com/LodyAI/Lody) | Difficulty: Intermediate | Time: 30 min | Basis: From the README Attach a laptop, server, or cloud VM to your workspace and start agent sessions on it from the CLI. **Who it is for:** A developer with a workstation or cloud VM who wants agents to run on that machine while they work from another device. **The problem:** Coding agents are tied to the machine where they are configured, so work cannot easily be started or followed from elsewhere. **The outcome:** The machine appears in the workspace, and a new agent session runs on it with status visible from the CLI. ### Steps 1. Run `npx lody daemon start` on the workstation, server, or cloud VM. 2. Complete the sign-in link that the command opens so the machine joins your workspace. 3. Run `npx lody session create --workspace my-team --agent-config codex --repo owner/repo "Fix the failing test"` and replace the workspace, agent config, repo, and prompt with your own. (inferred, check the README) 4. Run `npx lody session list --workspace my-team` to confirm the session appears with its status. ### Prompt to paste into your agent ```text In the LodyAI/Lody repo, use the CLI to create a session in the workspace on the connected machine using the agent config with the prompt . Output the new session ID and its status from the session list command. Verify that the session appears in the output of `npx lody session list --workspace `. ``` ### Caveat The README says machines stay private until their owner shares them with the workspace, so teammates may not see a machine until it is shared. Risk, credentials: Connecting a machine lets agents use the logins and subscriptions configured on it, so connect only machines you control or are authorized to use. Disclaimer: Third-party repos we don't own or vouch for. AI-generated use cases can be wrong: review everything and run at your own risk. Full text: https://dedupedai.com/disclaimer/ URL: https://dedupedai.com/use-cases/lodyai-lody/connect-machine-and-dispatch-work/ ## How to share a live agent conversation with teammates with Lody Repo: [LodyAI/Lody](https://github.com/LodyAI/Lody) | Difficulty: Beginner | Time: 15 min | Basis: From the README Open the same agent conversation with teammates to review the transcript, files, and changes. **Who it is for:** A team lead or reviewer who needs to see what an agent did and add instructions without screenshots or pasted logs. **The problem:** Passing agent output around by screenshots or pasted logs loses context about runtime status, files, and code changes. **The outcome:** Teammates open the same conversation and see the full transcript, runtime status, files, and code changes, then add instructions in the same thread. ### Steps 1. Open the agent conversation in the Lody desktop app or web app. 2. Share the conversation with your workspace teammates. 3. Ask teammates to open the same conversation and review the transcript, runtime status, files, and code changes. 4. Add follow-up instructions in the conversation so the agent continues with the team's feedback. 5. Run `npx lody session list --workspace my-team` to confirm the conversation is listed in the workspace. ### Prompt to paste into your agent ```text In the LodyAI/Lody repo, find the shared conversation in the workspace and summarize its transcript, runtime status, and code changes for a teammate. Output a short summary with the current status and the files changed. Verify the summary against the output of `npx lody session list --workspace `. ``` ### Caveat The README describes sharing conversations within a workspace, and the desktop and web sharing steps may vary by surface, so check the Lody documentation for the exact sharing controls. Disclaimer: Third-party repos we don't own or vouch for. AI-generated use cases can be wrong: review everything and run at your own risk. Full text: https://dedupedai.com/disclaimer/ URL: https://dedupedai.com/use-cases/lodyai-lody/share-agent-conversation-with-team/ ## How to have a main agent delegate bug work to parallel chats with Lody Repo: [LodyAI/Lody](https://github.com/LodyAI/Lody) | Difficulty: Advanced | Time: 45 min | Basis: From the README Use one coordinating conversation to split a bug into investigation, fix, and test conversations. **Who it is for:** An engineer handling a bug that needs analysis, a code fix, and tests that can run in parallel. **The problem:** Running several agent tasks by hand means tracking each one separately and collecting results manually. **The outcome:** The coordinating conversation creates child conversations, reads their status and history, sends follow-up instructions, and brings results back. ### Steps 1. Open a conversation with a main Agent and describe the bug to analyze. 2. Ask the main Agent to create separate conversations for investigation, implementation, and testing. 3. Let the main Agent read each child conversation's status and history and send follow-up instructions where needed. 4. Use an `@` mention to reference a child conversation when you need to connect work across sessions. 5. Run `npx lody session list --workspace my-team` to check the status of the child conversations from the CLI. ### Prompt to paste into your agent ```text In the LodyAI/Lody repo, act as the coordinating conversation for the bug in the workspace . Create or reuse child conversations for investigation, implementation, and testing, then report each child conversation's status. Verify the statuses against the output of `npx lody session list --workspace `. ``` ### Caveat The README says child conversations stay independent while keeping a link to their creator, so results still need review before they are merged into your code. Disclaimer: Third-party repos we don't own or vouch for. AI-generated use cases can be wrong: review everything and run at your own risk. Full text: https://dedupedai.com/disclaimer/ URL: https://dedupedai.com/use-cases/lodyai-lody/delegate-bug-work-across-parallel-conversations/ ## How to run parallel agent changes in separate Git worktrees with Lody Repo: [LodyAI/Lody](https://github.com/LodyAI/Lody) | Difficulty: Intermediate | Time: 30 min | Basis: From the README Give each session its own Git worktree and review diffs and pull request status beside the chat. **Who it is for:** A developer or reviewer who wants several agents changing the same repo at once without their edits mixing. **The problem:** Parallel agent edits in one checkout can mix changes, making diffs hard to review and attribute. **The outcome:** Each session works in its own worktree, and per-turn or full-session diffs can be inspected beside the conversation. ### Steps 1. Start two or more sessions against the same repository so each gets its own Git worktree. 2. Open each session in its own tab with its files, diffs, and terminal. 3. Inspect per-turn or full-session diffs beside each conversation and add line-level comments where needed. 4. Follow the pull request status and CI for the branch the session produced. 5. Fork a session into another worktree when you want to explore a different approach. ### Prompt to paste into your agent ```text In the LodyAI/Lody repo, start two sessions in the workspace against the repository , each with its own Git worktree and a different task and . Output the worktree and diff summary for each session. Verify that the two sessions show separate diffs in their own tabs. ``` ### Caveat The README says the worktree and GitHub review features are part of the product, but it does not say which repository hosts are supported beyond GitHub, so confirm your setup before relying on it. Disclaimer: Third-party repos we don't own or vouch for. AI-generated use cases can be wrong: review everything and run at your own risk. Full text: https://dedupedai.com/disclaimer/ URL: https://dedupedai.com/use-cases/lodyai-lody/isolate-parallel-agent-changes-in-worktrees/