<p>Hey Product Hunt. We're Seth, Neil, and Nick, and we've spent a decade in security and dev tools across Google/Gmail, Valimail, Twilio, and Algolia.</p><p></p><p>We built <a href="https://backplanes.com/?ref=producthunt" target="_blank" rel="nofollow noopener noreferrer">Spotlight by Backplanes</a> to help you keep up with your agents. It reads your Claude Code and Codex sessions and shows you what your agents actually did: session reports that make you a better engineer, every day.</p><p></p><p>This started with a scare. Neil asked Claude to fix one file. It read 47, including his ~/.ssh keys, and wrote an API key into a tracked .env. We build security software, and our own agents did this. We missed it, and caught it by accident while investigating something else.</p><p></p><p>So we looked deeper, stitching our Claude and Codex sessions together across machines. Two things floored us: how much we'd missed, and how many good moves we were making in one place but not another. Surfaced and shared, those patterns made us better, every day.</p><p></p><p>That's what <a href="https://backplanes.com/?ref=producthunt" target="_blank" rel="nofollow noopener noreferrer">Spotlight</a> does for you. After every session, you get a report: what to fix now, what to ship better next time, what's worth sharing. One harness or seven, solo or across your team.</p><p></p><p>We're building toward a world where you can see and manage everything your agents do. Visibility is where it starts, and we think everyone deserves to know what their agents are doing, so we're making this piece free. We'll be offering paid features and automations in the near future; seeing what your agents did won't cost you. Private and secure by design, with details at <a href="https://backplanes.com/trust/?ref=producthunt" target="_blank" rel="nofollow noopener noreferrer">backplanes.com/trust</a>.</p><p></p><p>Install is one line, and your first report lands in ~2 minutes: Get started on <a href="https://backplanes.com/?ref=producthunt" target="_blank" rel="nofollow noopener noreferrer">backplanes.com</a>.</p><p></p><p>Click here to <a href="https://join.slack.com/t/backplanescommunity/shared_invite/zt-40a7vr634-prUGl_B7~YG~7tmmkWFdsA" target="_blank" rel="nofollow noopener noreferrer">join our Slack and say hello</a>.</p><p></p><p>We hope you love <a href="https://backplanes.com/?ref=producthunt" target="_blank" rel="nofollow noopener noreferrer"><strong>Spotlight</strong></a>, and we can't wait to hear what it illuminates for you.</p>
<p>As of this year, I’ve become a “non-engineer engineer”, letting Claude and all his robot friends abuse my terminal. For example, the other day I just discovered how to <em>actually</em> use a `.env` file. Yes, I am embarrassed.</p><p></p><p>How was I forced to discover this? <a href="https://www.producthunt.com/@antifreeze" target="_blank" rel="nofollow noopener noreferrer">@antifreeze</a> (who I've known for what? 20 years??) gave me a demo of Backplanes and in a reports on one of my coding sessions I saw red:</p><img src="https://ph-files.imgix.net/84ffb93e-d3e2-4d41-a58f-335cf8bedfbe.png?auto=compress,format&codec=mozjpeg&cs=strip" style="max-width: 100%"><p>And this wasn't the only red I saw...!</p><p></p><p><strong>Backplanes showed me the ugly underbelly of my agent sessions: leaked credentials, missing tests, sloppy patterns I’d normalized because the app I was building "worked".</strong></p><p></p><p><em>By shipping like a maniac</em>, I leaked my secrets all over the place — and Backplanes provided me actionable steps to get my shit locked down.</p><p></p><p>This isn't just “agent analytics.” It’s a backstop for the bullshit your coding agents quietly create while you’re moving at AGI speed. Like being shown what bacteria lives on your toothbrush when you stop to under a microscope. 🦠🤮</p><p></p><p>So if you haven't been practicing excellent agentic hygiene, give Backplanes a try.</p><p></p><p><strong>Because behind every successful coding session is a backplane.</strong></p>
You emphasize “no OAuth into Anthropic/OpenAI” and still show org-level rollups (security/engineering/spend) with spend reconciliation close to invoices. How are you attributing sessions and spend across engineers/repos/tools without provider-side integrations, and what were the key tradeoffs you made to ship that early versus, say, real-time monitoring or policy gating?
<p>The session report angle makes sense. What I'm curious about is how much signal you're actually extracting versus just replaying what happened. Claude Code sessions can get noisy fast, lots of back-and-forth, abandoned branches, retried prompts, and the raw transcript isn't that useful without some layer of interpretation on top. Does Spotlight surface things like where the agent got stuck, or which tool calls failed silently, or is the report mostly a structured summary of the final output? Also curious what the security topic covers here, whether you're flagging things like secrets exposed in prompts or risky code patterns the agent introduced, since that would be a genuinely different use case than the reporting side.</p>
