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).
Product upvotes vs the next 3
Waiting for data. Loading
Product comments vs the next 3
Waiting for data. Loading
Product upvote speed vs the next 3
Waiting for data. Loading
Product upvotes and comments
Waiting for data. Loading
Product vs the next 3
Loading
Stacks
Steal one coding-agent trick from 94 top engineers
Stacks shows how 94 well-known engineers, including Peter Steinberger, Armin Ronacher and Simon Willison, work with coding agents. Each card covers their agents, models and skills, and how they review the code their agents write. Every detail links to its source, and each card ends with one practical trick you can try yourself. You can also create your own card with a single prompt. Nothing is shared unless you choose to publish it.
We're building a code review tool, and I wanted to understand how people who work with coding agents every day really work, not just how they review, but how they use agents at all.
So we made this small, free tool. It shows how 94 well-known engineers use coding agents, and each card ends with their most useful trick, ready for you to steal. Every claim links to its source, so you can check it yourself.
Most of us here use AI agents every day now, but it's hard to know what you're missing. So you can also make your own card: paste one prompt into Claude Code, Codex or whatever you use, and your agent compares your setup with the 94 and suggests what to try next. It takes a couple of minutes, and nothing is sent to us unless you publish it.
What surprised me most: only 8 of the 94 still read every line their agents write.
It's surely incomplete, so if something is wrong or missing, there's an edit link on every card and I'll fix it.
What's one trick that changed how you work with agents? :)
About Stacks on Product Hunt
“Steal one coding-agent trick from 94 top engineers”
Stacks was submitted on Product Hunt and earned 5 upvotes and 1 comments, placing #66 on the daily leaderboard. Stacks shows how 94 well-known engineers, including Peter Steinberger, Armin Ronacher and Simon Willison, work with coding agents. Each card covers their agents, models and skills, and how they review the code their agents write. Every detail links to its source, and each card ends with one practical trick you can try yourself. You can also create your own card with a single prompt. Nothing is shared unless you choose to publish it.
On the analytics side, Stacks competes within Productivity, Developer Tools, Artificial Intelligence and GitHub — topics that collectively have 1.7M followers on Product Hunt. The dashboard above tracks how Stacks performed against the three products that launched closest to it on the same day.
Who hunted Stacks?
Stacks was hunted by Peter Hraška. 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.
For a complete overview of Stacks including community comment highlights and product details, visit the product overview.
Peter Hraška
Hi 👋, I'm Peter.
We're building a code review tool, and I wanted to understand how people who work with coding agents every day really work, not just how they review, but how they use agents at all.
So we made this small, free tool. It shows how 94 well-known engineers use coding agents, and each card ends with their most useful trick, ready for you to steal. Every claim links to its source, so you can check it yourself.
Most of us here use AI agents every day now, but it's hard to know what you're missing. So you can also make your own card: paste one prompt into Claude Code, Codex or whatever you use, and your agent compares your setup with the 94 and suggests what to try next. It takes a couple of minutes, and nothing is sent to us unless you publish it.
What surprised me most: only 8 of the 94 still read every line their agents write.
It's surely incomplete, so if something is wrong or missing, there's an edit link on every card and I'll fix it.
What's one trick that changed how you work with agents? :)