Let an orchestrator agent merge dozens of PRs
Pointed Firstmate with Grok 4.5 at a private AI legal-case app and largely left it running.
Source
@lbtech on X · 2026-07-10
Written in our own words. Credit to the original author. Link checked 2026-10-14.
What they did
Pointed Firstmate with Grok 4.5 at a private AI legal-case app and largely left it running.
Result (as claimed)
About 50 PRs merged to main in roughly 14 hours.
Tools they used
Cost: Pricing depends on the tools you pick; check each official pricing page.
Set it up
Pick a contained repo or task
Start on a branch or side project where mistakes are cheap.
Install and configure
Set up Grok 4.5, Firstmate. Read what it can run on your machine and limit permissions where possible.
Run it on a real task
Give it a well-scoped issue and let it work. Review the diff like any pull request.
Add guardrails
Keep tests and CI in the loop, and never let an agent push to main or touch production secrets unattended.
Copy the full setup prompt
Paste into your agent and it will walk you through the setup, asking before anything that sends, posts or spends.
You are helping me set up this AI use case end to end in Claude Code. Goal: Let an orchestrator agent merge dozens of PRs What the original author did: Pointed Firstmate with Grok 4.5 at a private AI legal-case app and largely left it running. Reported result (as claimed by the author): About 50 PRs merged to main in roughly 14 hours. Source: https://x.com/lbtech/status/2075514166304006529 Tools they used: Grok 4.5, Firstmate Category: Dev & ops Please: 1. Ask me 3 short questions about my situation (accounts I have, budget, what I want the output to look like). 2. Propose a step-by-step plan using these tools or cheaper alternatives, with the time and cost of each step. Use official pricing pages; say "check pricing" if unsure. 3. Then do the setup with me one step at a time, waiting for my OK before anything that sends messages, posts publicly, spends money or deletes data. 4. Finish with a checklist to run it again next time.
You are helping me set up this AI use case end to end in Codex. Goal: Let an orchestrator agent merge dozens of PRs What the original author did: Pointed Firstmate with Grok 4.5 at a private AI legal-case app and largely left it running. Reported result (as claimed by the author): About 50 PRs merged to main in roughly 14 hours. Source: https://x.com/lbtech/status/2075514166304006529 Tools they used: Grok 4.5, Firstmate Category: Dev & ops Please: 1. Ask me 3 short questions about my situation (accounts I have, budget, what I want the output to look like). 2. Propose a step-by-step plan using these tools or cheaper alternatives, with the time and cost of each step. Use official pricing pages; say "check pricing" if unsure. 3. Then do the setup with me one step at a time, waiting for my OK before anything that sends messages, posts publicly, spends money or deletes data. 4. Finish with a checklist to run it again next time.
You are helping me set up this AI use case end to end in Grok Bot. Goal: Let an orchestrator agent merge dozens of PRs What the original author did: Pointed Firstmate with Grok 4.5 at a private AI legal-case app and largely left it running. Reported result (as claimed by the author): About 50 PRs merged to main in roughly 14 hours. Source: https://x.com/lbtech/status/2075514166304006529 Tools they used: Grok 4.5, Firstmate Category: Dev & ops Please: 1. Ask me 3 short questions about my situation (accounts I have, budget, what I want the output to look like). 2. Propose a step-by-step plan using these tools or cheaper alternatives, with the time and cost of each step. Use official pricing pages; say "check pricing" if unsure. 3. Then do the setup with me one step at a time, waiting for my OK before anything that sends messages, posts publicly, spends money or deletes data. 4. Finish with a checklist to run it again next time.
Related use cases
Wake up to pull requests your agents finished overnight
Uses Firstmate so one agent in Claude Code orchestrates other coding agents overnight.
Let an agent debug your app on a spare phone
Enable USB or Wi-Fi debugging on an old Android phone, connect it, and ask Hermes agent or Claude Code to test and debug your mobile app.
Give your coding agent a personality with a skill
Vibe-coded a Claude Code skill called squidward that makes its replies sarcastic.
Manage agent sessions from your phone and watch
Built claude-master: all sessions in one view on phone and watch, reply by tap or voice, replies read aloud, live quota; even the demo video is code.