This product was not featured by Product Hunt yet. It will not be visible on their landing page and won't be ranked (cannot win product of the day regardless of upvotes).
AI Council
An AI product team in your repo, from idea to merged PR
An open-source template that turns a git repo into your product's AI council. Four lenses (product, UX, tech, business) debate each real decision, check your live data through MCP connectors, and write it down as a PR/FAQ, ADR or council decision. Approve the plan, and the council chat branches into Claude Code or Codex sessions in your code repos, each ending in a merged PR, and the roadmap moves. A studio makes your launch films as code.
I build products alone or with a very small team, so I play every role: PM, designer, architect, marketer. The code got easy. Making good calls, fast, and remembering why, did not.
So in January I started an "AI council" for my English-learning app, Subturtle. It's a git repo where four AI lenses (Product, UX, Tech, Business) each think about a question on their own, then one agent writes a single verdict and saves it as a doc. Since then I've run four products this way, and today I'm opening the template.
What it does: • Decides. Only real decisions get the full council. Small things get one lens, or none. • Writes it down. PR/FAQs, ADRs and council decisions, in plain markdown in git. Six months later you still know why. • Checks the numbers. With MCP connectors (Mixpanel, Stripe, ClickUp…), it queries your data before it argues. • Hands off to code. Once you approve the tasks, the council chat starts Claude Code or Codex sessions in your product repos. Each one opens a PR, and the roadmap moves. Last week Subturtle's council turned 6 live-test gaps into a fix that was merged to production 33 minutes later. • Makes the launch film. The studio builds films, demos and motion graphics as code. The video on this page was made that way.
It works with Claude Code, Codex, Gemini CLI and Cursor. No server, no account. Fork or clone the repo, open it in your agent and say "set up the council": https://github.com/navidshad/ai-...
I'd love to hear what lens you'd add for your product. Mine for Subturtle is a language-learning scientist.
No comment highlights available yet. Please check back later!
About AI Council on Product Hunt
“An AI product team in your repo, from idea to merged PR”
AI Council was submitted on Product Hunt and earned 3 upvotes and 1 comments, placing #105 on the daily leaderboard. An open-source template that turns a git repo into your product's AI council. Four lenses (product, UX, tech, business) debate each real decision, check your live data through MCP connectors, and write it down as a PR/FAQ, ADR or council decision. Approve the plan, and the council chat branches into Claude Code or Codex sessions in your code repos, each ending in a merged PR, and the roadmap moves. A studio makes your launch films as code.
AI Council was featured in Open Source (69k followers), Developer Tools (521.5k followers), Artificial Intelligence (481.6k followers) and GitHub (41.4k followers) on Product Hunt. Together, these topics include over 269.3k products, making this a competitive space to launch in.
Who hunted AI Council?
AI Council was hunted by Navid Shad. A “hunter” on Product Hunt is the community member who submits a product to the platform — uploading the images, the link, and tagging the makers behind it. Hunters typically write the first comment explaining why a product is worth attention, and their followers are notified the moment they post. Around 79% of featured launches on Product Hunt are self-hunted by their makers, but a well-known hunter still acts as a signal of quality to the rest of the community. See the full all-time top hunters leaderboard to discover who is shaping the Product Hunt ecosystem.
Want to see how AI Council stacked up against nearby launches in real time? Check out the live launch dashboard for upvote speed charts, proximity comparisons, and more analytics.
Navid Shad
Hey Product Hunt 👋 I'm Navid.
I build products alone or with a very small team, so I play every role: PM, designer, architect, marketer. The code got easy. Making good calls, fast, and remembering why, did not.
So in January I started an "AI council" for my English-learning app, Subturtle. It's a git repo where four AI lenses (Product, UX, Tech, Business) each think about a question on their own, then one agent writes a single verdict and saves it as a doc. Since then I've run four products this way, and today I'm opening the template.
What it does:
• Decides. Only real decisions get the full council. Small things get one lens, or none.
• Writes it down. PR/FAQs, ADRs and council decisions, in plain markdown in git. Six months later you still know why.
• Checks the numbers. With MCP connectors (Mixpanel, Stripe, ClickUp…), it queries your data before it argues.
• Hands off to code. Once you approve the tasks, the council chat starts Claude Code or Codex sessions in your product repos. Each one opens a PR, and the roadmap moves. Last week Subturtle's council turned 6 live-test gaps into a fix that was merged to production 33 minutes later.
• Makes the launch film. The studio builds films, demos and motion graphics as code. The video on this page was made that way.
It works with Claude Code, Codex, Gemini CLI and Cursor. No server, no account. Fork or clone the repo, open it in your agent and say "set up the council": https://github.com/navidshad/ai-...
I'd love to hear what lens you'd add for your product. Mine for Subturtle is a language-learning scientist.