If the agent writes the code who s actually testing it?

Do you still go through edge cases and user scenarios manually, or are you also delegating please break my app to another agent now?

We launched CoWork, a mobile app testing solution, on PH a while back and got a lot of useful feedback. Some of the most interesting comments came from developers who wanted to test their mobile apps before the merge, not after.

So we built QApilot MCP, that lets Claude, Cursor or Codex drive a real Android device. It launches Saturday.

Most Lovable apps I've seen ship with integrations that were never actually run end to end.

What's usually happening?

The Stripe webhook is wired, the retry logic is there, but nobody ran a confirm capture webhook fire sequence before going live. Testing is either skipped or scripted in isolation against mocked responses that don't reflect real API behavior.

Genuinely curious what the community does here.

We've been talking to hundreds of teams building with Cursor, Claude Code, and other agentic tools and the honest answer from most of them is: "We just run it and hope."

Some do a quick manual click-through. Some write a few spot checks. Some just ship and wait for users to find the bugs.

We built TestSprite to solve exactly this autonomous testing that runs from your PRD and codebase but I'm curious what your actual workflow looks like before you merge.

The gap most auto-fix tools have

They tell you the bug is fixed. They don't show you. Our rule has always been: make the bug happen on real code, apply the fix, show it stops happening. The gap was we could only do that for bugs we'd scripted in advance. Anything unusual and the honest answer was "found it, fixed it, can't prove this one."

What we built

We taught FetchSandbox to write the reproduction itself, no pre-scripted test required.

AI code review for free.
@Kilo Code Reviewer is currently free. No credit card. Unlimited reviews on GitHub or GitLab. Bitbucket support coming soon.

Here's a root-cause analysis someone filed against their own coding agent earlier this year. An end-to-end test timed out at 300 seconds, then at 420. The agent raised the limit to 480 and added a skip-on-timeout. Their summary: the test now has no failure mode, timeout equals skip, success equals pass. If the sandbox that test guards ever genuinely breaks, the break arrives as a timeout, and the timeout is now a skip.

Nothing in the issue suggests anyone asked for that. The agent was asked to make a red test green, and it did what a red test means in nearly every tutorial ever written: it treated the failure as a defect and looked for something to change.

The mechanism underneath is simple. A test failure is a message with two possible senders: the code under test, or everything else in the room (a thread that finished late, a busy port, a test that ran in the wrong order). Both senders write the same line of output. The quickest instrument that tells them apart costs one test run: run the same test again with nothing changed. If the verdict flips, the edit is no longer the prime suspect. Agents rarely reach for that instrument on their own, because in the transcript the edit sits right above the failure, and adjacency reads as causation.

The old flaky-test research adds a twist. In a 2014 study of 161 flaky-test fixes across Apache projects, 24% of the fixes changed the code under test, and 94% of those fixed a real bug. A flaky test is a bug report with a wider error bar. Skipping it throws the report away.

Meow world, welcome back to The Breakpoint, a weekly thread on all things dev tools on Product Hunt.

The latest

Recent dev-first products launched on the site.

I recently came across what the majority calls "vibe coding" and I am addicted. As I am a marketing guy, I couldn't resist in creating not one, not two, but 8 apps, which are basically systems to solve my own problems and frustrations.

However, I couldn't help but notice that all these tools are far from perfect. Lovable, Replit (which I use extensively now) say they did something, but in reality, they made only the surface.

I'm creating a fitness app that uses AI on @Lovable, and I'm also testing it myself.

I use the app daily to check its functions, how it works, and the exercises. If I find something strange or think of something new, I record voice memos with issues, changes, or improvements. I act as both the product manager and a user. Later, I listen to these notes and make the changes.

There s a lot of discussion on X and other places about the future of software development. As with many things in life, the reality is both complex and in the middle of the extreme viewpoints. What we re seeing at Tonkotsu:

• Agents are fast and powerful, but make mistakes. They can t operate unsupervised. We think they re like unreliable compilers.

• That means developers are as critical as ever, but their role shifts to being managers of coding agents.

• This transformation means developers need to be focused on planning and verification, while delegating coding. The role has become barbell-shaped, and the industry needs new tools and workflows to accommodate this.

More here https://blog.tonkotsu.ai/p/manag...

After rebuilding the same project three times because AI forgot my architecture, I got fed up and built @CodeRide (Beta) with my team.

The problem: AI code assistants lose track of your project between sessions. Every time I start coding with Cursor, Claude, or any AI assistant, I waste time re-explaining my codebase structure, architectural decisions, and coding patterns.

What we built: The project management tool for coding agents using MCP. Upload your project documentation or PRD, and CodeRide breaks it into optimized, fully contextual tasks ready for your AI agent.

If generating code is a commodity, then what is built, and how is the most critical question to answer.

This is the goal of Shotgun - to help you turn technical research and spec generation into context for software engineers, AI code-gen tools like Codex, Cursor, Claude Code, with complete codebase understanding, and agents doing the heavy lifting.

Shotgun produces clean, reusable artifacts and exports to the agents.md ecosystem to help you get the most out of code-gen tools and Agents.

New release highlights: