<p>Hi Product Hunt - Matt here, co-founder of Prefactor with Simon. </p><p></p><p>We've been heads-down on this one for a while, so finally getting to show you is a real thrill.</p><p></p><p>Let me start with the question this whole thing is built around: <strong>do you actually know what your agents are doing in production right now?</strong></p><p></p><p>For most teams we talk to, the honest answer is "…not really." Your evals pass, everything's <em>green</em>, you ship - and then every real run vanishes into a <strong>black box</strong>. Quality quietly drifts. Risk creeps in. Costs climb. And eventually someone asks which of your agents are still doing their job, and the room goes quiet.</p><p></p><p>That silence is the entire reason Prefactor exists. Gartner reckons <strong><em>40%+ of agentic AI projects get scrapped by 2027</em></strong> - and honestly, this gap is a big part of why.</p><p></p><p>So we built the thing we kept wishing we had: Prefactor scores every run in production the moment it happens - quality, drift, risk - then wires those scores straight into action. A failing agent gets caught live, not charted three days later.</p><p></p><p><strong>How it actually works</strong></p><ol><li><p><strong><em>prefactor init </em></strong>- one command connects your workspace and discovers your agents across your runtimes. First traced run in under 5 minutes.</p></li><li><p><strong><em>Drop in the SDK </em></strong>(TypeScript or Python) - native for LangChain, Claude, Vercel AI, OpenClaw and LiveKit. Every call becomes a span, streaming in live with cost and data risk attached.</p></li><li><p><strong><em>Run the evals </em></strong>you define on every run - LLM-as-judge, technical checks, qualitative metrics. Custom spans pull context from GitHub, Linear, Jira or your database, so every eval is grounded in what actually happened, not a guess.</p></li><li><p><strong>Act.</strong> Hold, approve or block the second a run crosses a line - automatically at runtime, or routed to a human. Every decision logged and enforced through the SDK or API.</p></li></ol><p>The payoff: you get to ship agents like real software — versioned, staged, promoted through dev → staging → prod only when evals pass, with instant rollback when they don't.</p><p></p><p><strong>Why it's different</strong></p><p>Most tools observe and score, then hand you the problem. Prefactor closes the loop - observe, evaluate, act, all inside the same run. A risky agent gets caught, not just charted.</p><p>My favourite bit of feedback so far: a customer with 40 agents in production and, in their words, "no honest way to say which ones were still doing their job." We gave them that answer - and the brake pedal for when one wasn't.</p><p></p><p><strong>Who it's for</strong></p><p>Engineering teams shipping agents to real customers, on any stack. Agent frameworks work natively; everything else plugs in through OpenTelemetry or the core SDK.</p><p></p><p><strong>A little something for the PH community</strong></p><p>Sign up today and you get <strong>1,000,000 free agent steps</strong>. Every span counts, so that's a serious amount of live production evaluation on us. Valid until Friday 11:59pm PT, once you've set up your first agent.</p><p></p><p><strong>Our ask</strong></p><p>If you're running agents in production, tell us how you keep tabs on them today - even if the honest answer is "we're mostly hoping." We'll be in the comments all day and we'd genuinely love to hear what's working, what's breaking, and what you'd want a tool like this to do next.</p><p></p><p><strong><em>Get started free at </em></strong><a href="http://prefactor.tech" target="_blank" rel="nofollow noopener noreferrer"><strong><em>prefactor.tech</em></strong></a><strong><em>.</em></strong> First 25,000 spans a month free, no card needed. </p><p></p><p><a href="https://www.producthunt.com/@simon_russell1" target="_blank" rel="nofollow noopener noreferrer">@simon_russell1</a> <a href="https://ww
