Capture every hard-won fix buried in your agents' sessions.

1Signal turns every Claude Code, Codex, and Pi session into intelligence the whole team can use, so no one ends up reinventing the wheel.

Replay any session

See what your agent did and how it got there, instead of guessing from memory.

  • Browse sessions by time, sorted by user, activity, or cost.
  • Read user input and agent output as a conversation; see tool activity including skill and MCP usage.
  • Per-turn token usage, cost, latency, errors, and event order.
  • Drill from a session overview all the way down to the trace that produced a result.

When an MCP call fails, the session shows the failing step, its duration, and the error — right next to the conversation. The intelligence report links straight to that trace, so nobody re-reads a whole session to verify a conclusion.

1Signal sessions list: browse sessions by time, user, activity, or cost

Skip the read-back

Reviewing every session isn't worth the focus it takes. 1Signal surfaces what you'd have missed.

"Did the agent follow our CLAUDE.md?"

Your plugin snapshots the AGENTS.md / CLAUDE.md that were actually in effect. 1Signal judges each applicable rule — followed violated or not observable — with source, file line, an explanation, and a link to the evidence.

"Was that complaint actually the agent's fault?"

1Signal only flags explicit, significant user feedback — and attributes it honestly: supported when the evidence is there, insufficient evidence when it isn't. An accusation is never treated as proof. Negative feedback is then tracked to addressed, unaddressed, or unclear.

"Did this session introduce risk?"

Code Risks are reported only from code changes actually captured in the session — with direct evidence. No claims about your live repo, no risk without proof.

"What was the agent even trying to do?"

Work intent — implementation, review, debugging, testing, planning, research, release — extracted with evidence snippets, alongside sampled tool, skill, and MCP activity: successes, failures, unknowns, latency.

Open any finding and land on the original turn or trace. Verify everything in context.

Frequently asked questions

Do I need to change my code?
No. You install a plugin into Claude Code, Codex, or Pi; it captures sessions in the background without changing how you work.
How is this different from an observability dashboard?
Dashboards stop at metrics. 1Signal reads the session itself and makes evidence-linked judgments — about instructions, feedback, and risk — that you can verify in one click.
What exactly gets collected?
Conversations, tool activity, usage/cost/latency, and snapshots of the instruction files in effect for that session.

1Signal is the evidence layer of the loop.

Govern what agents can do → 1Connector — one governed path from every agent to real tools.
Publish what worked 1Knowledge coming soon

Stop guessing. Start reading the evidence.

Be among the first to see what your agents actually do. 1Signal is launching soon.