Recipes
Ready-made multi-agent teams. Each recipe spins up a whole team of AI agents — with models, repos, toolpacks, skills, and first prompts already wired up. Open one to use it on chat.dev.
BugFinder
Creates a team of agents that act like users and finds bugs. Emails you every few hours with what its found.
Growth Squad
A marketing team that ships campaigns: a strategist researches the audience, a copywriter drafts the assets, and a publisher commits them to your marketing-site repo and sends the announcement email.
Full-Stack Feature Team
Ships features end-to-end against a shared GitHub repo: an architect writes the API contract and delegates, backend and frontend build in parallel on branches, and a reviewer gates every PR before merge.
Deep Research Pod
Fan-out researchers plus a synthesizer produce a cited report on any question, using real web search and scraping APIs. Findings are committed to a Markdown report in your repo.
Content Studio
Turns a brief into a published blog post on your Git-backed site: a writer drafts, an editor sharpens for clarity and voice, and a publisher commits the Markdown and opens the PR.
On-call SRE
An incident team: a monitor watches Sentry/PagerDuty for alerts and opens an incident, a diagnoser investigates the repo and recent changes for root cause, and a fixer ships the mitigation PR.
Sales Outreach
Builds and runs a personalized outbound sequence: a prospector pulls and researches accounts via Apollo, a writer drafts tailored emails, and a CRM agent sends them via Resend and logs activity to HubSpot.
PR Review Crew
Two agents that triage your open pull requests on a GitHub repo: one reviews correctness, security, and house style; the other checks out each branch and runs the full test suite.
Bug Bash Squad
Turns a bug report into a merged fix: a reproducer writes a failing test from Sentry/issue details, a fixer makes it pass, and a verifier confirms no regressions before the PR goes up.
Data Analytics Pod
Answers a data question end-to-end against your database: an extractor pulls and validates the data, an analyst explores and models it, and a reporter commits a written, charted findings doc to the repo.
LinkedIn Product Updates
Auto-post video walkthroughs to linkedin every time your product changes.
Mir
weekly-product-grok
Uses grok and allowance to buy you a product every week to review and become an influencer. Also posts about it on linkedin and youtube, analyzes the results, and calls you about it.
Github Issue Agents
This recipe builds/maintains a project by creating agents that own github issues and orchestrates fixing them. Assumes a main/staging project structure and many feature branches.
Java21_BugHunter
Java21_BugHunter
Histogen Evidence Review Lab
A reusable, research-only workflow inspired by the Histogen project that won 1st place at Nucleate New York BioHack 2026. It turns de-identified pathology research inputs into a source-traceable hypothesis brief, then audits citations, uncertainty, privacy, and human-review requirements. It does not diagnose or recommend treatment. Credits the publicly named Histogen team: Taylor Y., Aonkon Dey, Emma Finnegan, and Panteha Behboodi. Original winning post: https://www.linkedin.com/posts/panteha-behboodi-753b9969_my-first-biohackathon-was-a-success-excited-activity-7471368274254000128-qlHq
Shared Pet Chore Steward
A reusable roommate coordination agent inspired by Munji, the Eazo Global Hackathon 2026 winner. It creates a fair chore rotation, records explicit check-ins and swaps, tracks streaks, and turns verified completion into a lightweight shared-pet progress loop—without claiming a chore is done unless a roommate confirms it.
Landing Page Conversion Fix Brief
Audit a landing page from its URL or pasted copy, identify evidence-backed conversion problems, and return a prioritized fix brief with concrete rewrite suggestions and lightweight experiments.