What's the one thing you wish you could see inside your AI agent's brain?
I've been building ClawMetry for past 5 weeks. 90k+ installs across 100+ countries.
The observability features I built first were the ones I personally needed: a live execution graph (Flow tab), full decision transcripts (Brain tab), token cost tracking per session, and visibility into sub-agent spawns.
But I keep hearing variations of the same thing: "I don't really know what my agents are doing." And everyone means something slightly different by that.
For some it's costs. For some it's timing (why did this take 4 minutes?). For some it's trust (did the agent actually do what I think it did?). For some it's failures (where exactly did it break?).
So I want to ask you directly:
If you're running AI agents today -- what's the one thing missing from your observability setup? What would make you feel like you actually understand what's happening inside your agents?
Options I'm thinking about next:
- Alerting (get notified when an agent fails or goes over budget)
- Cost per task breakdown (not just per session)
- Agent run comparisons (before/after a prompt change)
- Memory snapshots (what did the agent "know" at each decision point)
Drop your answer below. The next feature I build will be heavily influenced by this thread.
(ClawMetry is free to try locally: pip install clawmetry. Cloud: app.clawmetry.com, $5/node/month, 7-day free trial.)
Replies
Memory snapshots would be huge, seeing exactly what context the agent had when it made those weird decisions :)
ClawMetry
@rohanrecommends 100% agree Rohan. That's actually the one that keeps coming up in my own debugging too. The agent makes a weird call and I'm left thinking "what did you even know at that point?"
We already have the Memory tab that shows the current state of MEMORY.md, SOUL.md, and workspace files. But what's missing is the timeline view: what the agent's context window looked like at each decision point. Not just what files existed, but what was actually loaded into context when it chose to call that tool or write that response.
Thinking about it as a "rewind" feature. Pick any event in the Brain tab, click it, and see: here's the full context the agent had at that exact moment. Files, recent messages, tool results, everything.
Bumping this up the roadmap. Thanks for validating it.