easyspecs.ai

<p><strong>Hey Product Hunt</strong> 👋</p><p>I'm Xesca, CTO turned founder. Before EasySpecs, I spent 15+ years being the person accountable for code I didn't personally write, across fintech, insurtech, and media.</p><p>That's the job now for every engineering leader: your agents ship code faster than anyone can read it, and you're still the one who answers for what breaks.</p><p></p><h2>The problem</h2><p>I kept hitting the same wall everywhere I looked:</p><ul><li><p>Teams adopt AI coding agents, and PRs pile up faster than anyone can review them</p></li><li><p>Specs get written against a mental model of the codebase, not the actual codebase</p></li><li><p>Agents generate code against those specs</p></li><li><p>Things break silently, and nobody can trace why, because nobody documented what was actually there to begin with</p></li></ul><p><strong>Code review is dead. Spec review is where quality lives now.</strong> But spec review only works if the spec is grounded in reality, not guesswork.</p><h2>What EasySpecs does</h2><p>Two things, one workflow:</p><p><strong>1. We document your codebase automatically</strong></p><p>Even the undocumented, nobody-wants-to-touch-it kind. Our first real test was a pharmaceutical company's legacy Delphi system. If it works there, it works on whatever you're building.</p><p><strong>2. We turn that understanding into specs your team and your agents can actually trust</strong></p><p>Every spec comes paired with validators, so you know it matches the app before anyone codes against it.</p><p>Here's the part I'm most proud of: as you write a spec, the specs crafter suggests <strong>oracles and rubrics</strong> for it, concrete, checkable ways to verify the change actually did what the spec said.</p><ul><li><p><strong>Oracles</strong> — the "does this pass or fail" checks a machine can run</p></li><li><p><strong>Rubrics</strong> — the judgment calls that need a human or an AI reviewer to score against clear criteria</p></li></ul><p>You're not staring at a blank page trying to guess how to verify your own spec. The tool proposes it alongside the spec itself.</p><h2>Built for more than developers</h2><p>You don't need to be a developer to use it. Right now the only way to sanity-check a spec against reality is to go read the source yourself.</p><p>We built EasySpecs so product managers and team leads get that confidence without opening a single file.</p><h2>Try it</h2><ul><li><p><strong>Free to start</strong> — connect a repo, bring your own AI key, see what it finds</p></li><li><p><strong>Workbench</strong> — €5/repo/month while launch pricing lasts (normally €10)</p></li><li><p><strong>Factory</strong> — €150/month if you want us to run the AI side too, with credits to use on any repo</p></li></ul><p>I'd genuinely love your feedback, especially if you throw a messy, undocumented codebase at it. That's the case we built for.</p>

<p>FINALLY!!!! 🍾🎉🎊</p>

<p> Didn't know that these sort of tools existed. Excited to see this in action going forward</p>

<p>Congratulations <a href="https://www.producthunt.com/@xesca_i_am" data-node-type="mention" data-mention-type="user" data-mention-id="xesca_i_am" target="_blank" rel="nofollow noopener noreferrer">@xesca_i_am</a> <a href="https://www.producthunt.com/@carlos_guirao" data-node-type="mention" data-mention-type="user" data-mention-id="carlos_guirao" target="_blank" rel="nofollow noopener noreferrer">@carlos_guirao</a> &amp; team <a href="https://www.producthunt.com/products/easyspecs-ai" data-node-type="mention" data-mention-type="product" data-mention-id="easyspecs-ai" target="_blank" rel="noopener">@easyspecs.ai</a> 🚀. Question, Having written the specifications, what would be the way to keep them consistent with the changing source code? Manually running them, or keeping them constantly up-to-date?</p>