Launching today
Spotlight by Backplanes
Session reports for Claude Code & Codex to improve your code
313 followers
Session reports for Claude Code & Codex to improve your code
313 followers
Keep up with your agents. Spotlight reads your Claude Code and Codex sessions and shows you what your agents actually did, and how to get recursively better every session: what to fix now, what to ship better next time, what's worth sharing. One harness or seven, solo or across your team. Free.
Well done! Was post-session reporting a deliberate call over an inline guardrail that interrupts the agent mid-write (i.e. less intrusive, keeps you in flow)?
@artstavenka1 Thanks, Art! Definitely deliberate, but one (good!) clarification: it's not limited to being post-session. Spotlight reports actually build while you work, just minutes behind your agent, so you're not waiting for a session to end to find out what happened.
What we deliberately avoided is the inline path. A guardrail that interrupts mid-write has to sit between you and the model, with the latency and potential breakage that path implies, and we very much want to help keep you in flow. :)
The scary part of vibe coding fast isn't the bug you catch, it's the secret you committed three sessions ago and never noticed. I spent years in risk and security before I ever touched Claude Code, so "what my agent actually did" is exactly the report I always wished I had. Does Spotlight call out the security stuff specifically, leaked keys, missing checks, or is it more about code quality and patterns?
@luca_capone, "the secret you committed three sessions ago" is almost word-for-word how Spotlight actually started for us: I asked Claude to fix one file, and an API key ended up in a tracked .env that we only caught by accident. So yes, security is very much called out specifically, and it leads the report rather than riding along. Findings arrive severity-ordered in their own stream: secrets landing in files git tracks, prod-touching commands that skipped a dry run, an agent quietly reaching a service you've never used, each with the evidence behind it and a concrete fix.
Code quality and patterns that can help make you more effective with your harness are in there too, so the report always gives you value, even when there are no security-related findings. And since those transcripts are already sitting on your machine, the first report can start with the sessions you've already run. Your "three sessions ago" is still catchable. :)
The "what your agents actually did" angle is great, that read-47-files scare is too real. When you're running several harnesses at once, does Spotlight give you one combined report or one per session?
Thanks@ianhxu. "Too real" is exactly how it felt on the inside too. :) The answer is both, at different layers. Each session gets its own report, with its own findings and evidence, so you know exactly which session did what, and exactly what to do about it.
Running several harnesses at once just means several reports, and your Claude Code and Codex reports live side by side in Spotlight. But your highest-leverage opportunities are often in the trends and patterns across sessions, and so Spotlight gives you a report of what's important across all of them. And finally, connect your whole team and the view widens even further: patterns and trends across every engineer in an org.
One individual or a team, one harness or seven, Spotlight gives you both the detail and the big picture.
This is a useful direction. For coding agents, the hard part is usually not generating more code, it is making the session reviewable afterward.
The report I’d want is pretty boring: changed files, risky assumptions, tests/checks run, failed attempts, and a short “what a human should look at first” section.
@kevinzrzgg, you seem to have written our report spec almost exactly. :)
Changed files: all files read and written are in there. Tests and checks: flagged with their outcomes when the session shows them. Failed attempts: called out, including the distinction between deliberate re-verification and flailing retries. "What a human should look at first": that's the top of the report, a one-line verdict with the main outcome, then findings ordered by severity and guidance on what to do for each.
The one we can only claim half credit on is risky assumptions: concrete risky choices surface as findings, and a blind-spots section names what the report couldn't verify, but a dedicated assumptions section is a great idea.
And we're with you on boring: the standing rule inside the report is no invented findings and no padded advice, an empty section beats a manufactured one.
DiffSense
300$ for 50min coding. what kind of models are you running? 😅 How does it get recursivly better for each session i dont get it? reminds off entire.io
@conduit_design Ha, right?! The wild part: that's the agents' own tab, we just hand you the receipt. It's crazy how quickly token usage accelerates when you're running multiple subagents on an intensive job, and Fable pricing is going to make this even more fun for all of us soon. 😅
On "recursively better," the idea is that it's a loop with you in it. The model never changes; your setup does. Each report turns what happened into concrete and actionable advice: a fix to apply, a CLAUDE.md line to include, a Skill to draft. Your agent loads that richer setup next session and starts more informed than the last one.
The Neil story is the real pitch here, not productivity, but security. Most devs assume they're reviewing what the agent does, but at scale (multiple sessions, multiple team members), drift is invisible. The framing as "session reports" makes it feel like a dev tool, but this is really an audit trail. Smart. Curious whether you'll add diff-level visibility (which files were read, not just that 47 were).
Best Meme of The Decade
Congrats @antifreeze - this is one of those products that feels obvious once you see it.
I’m using Claude Code/Codex every day right now, and the trade off is you don’t really know what got touched, what got skipped, or what weird security debt just got created. In our space making sure everything is tightened up and polished is a necessity more than ever.
Spotlight makes it clear what actually happened. Every team using agents seriously is going to need this. Bullish.
@armand thank you! "Obvious once you see it" is the best kind of compliment. Excited to hear what Spotlight illuminates for you-- and what you wish it showed. That's the stuff we want to build next!
Tabstack
@antifreeze curious what's on your product roadmap btw? anything you could share here?
@fmerian Ha, fair question. Happy to share the general compass, even if I have to hang on to the detailed map for now. ;-)
The direction is in the name: Spotlight is the visibility and advisory layer, illuminating what's happening. The plan for Backplanes is not just being able to see, but to manage/shape everything your agents do, whether you're an individual user or an enormous organization.
Where we're pushing next with Spotlight, directionally:
Deeper: richer insights on individual sessions as well as richer cross-session and team-level patterns.
Broader: more harnesses and agent surfaces beyond Claude Code and Codex.
Automated: from reports to actions. Today a Spotlight finding hands you advice on how to resolve an issue; over time, more of that loop gets automated.
What I'd love from this thread: tell me which harness you'd want next, or what a report should catch that it doesn't today.
We're building this for builders and creators like you, and nothing steers the roadmap like hearing it straight from you.
Tabstack
@armand exactly! @Spotlight by Backplanes brings clarity to your sessions. it improves your code and makes you a better engineer.
S/O to @antifreeze @gogogadgetneil @natwar86 and team