Observability & governance
If an agent did it, it's on record.
Because AgentGuide sits on the path of every model call, tool invocation, and agent turn, observability isn't an SDK you hope every team integrates — it's a property of the traffic. And the same position makes governance enforceable, not advisory.
Usage events
Four event families, one attribution model.
LLM, MCP, ACP, and builtin traffic each produce durable, typed usage events. Every event carries the agent that caused it — so cost, latency, and errors roll up per agent, not just per endpoint.
| time | kind | agent | target | tokens in / out | latency |
|---|---|---|---|---|---|
| 14:02:11 | llm | support-triage | anthropic · claude-sonnet-5 | 8,412 / 1,203 | 2.1s |
| 14:02:13 | mcp | support-triage | crm-tools · lookup_account | — | 340ms |
| 14:02:19 | builtin | report-writer | turn · plan-execute | 31,908 / 4,551 | 18.7s |
| 14:02:24 | acp | codex-dev | turn · session 7f3a | 12,050 / 2,340 | timeout |
Cost-grade token detail
Prompt, completion, cached, and reasoning tokens are recorded separately — the numbers you actually need to explain a bill or tune a cache.
Spans, not just counters
Agent turns open interaction spans; inner model calls and tool executions nest underneath. You see the chain of causation, not four disconnected logs.
Failures classified
Client errors, upstream failures, and internal faults are distinguished per event — so an agent misbehaving and a provider outage never blur together.
Analytics & integration
Query it here. Aggregate it anywhere.
Metrics Admin API
Summaries with pipeline health, per-protocol timeseries and breakdowns, recent interaction events, and per-agent usage and activity views — queryable the moment the gateway is running.
- Per-agent rollups Usage, activity, interactions, and health per registered agent.
- Prometheus exposition Scrape the gateway; build trends and alerting in Grafana.
- OpenTelemetry seam A sink adapter designed for exporting events to your tracing stack.
- Retention control Configurable retention with automatic cleanup — observability that respects your storage.
Governance
Enforcement at the only place it can't be skipped.
Guidelines in a wiki don't stop an agent at 3 a.m. Controls at the gateway do. AgentGuide's governance is structural: if traffic doesn't satisfy policy, it doesn't reach the model, the tool, or the agent.
Identity & keys
- Virtual keys per app, team, or agent — issue, rotate, revoke centrally
- Upstream secrets never leave the gateway
- Route-level auth requirements, fail-closed
Permission gates
- Deny by default; auto-approve where safe; interactive human approval where it counts
- Unanswered requests time out to denial
- Every decision attributable and on record
Runaway protection
- Agent recursion-depth limits stop agent-calls-agent loops at the gate
- Per-agent concurrency caps and turn timeouts reject rather than queue
- Panic containment: one bad turn never takes down the gateway
Scoped capability
- Agents reach only the model routes and MCP tools bound to them
- Managed coding agents run in pooled, isolated processes confined to allowed filesystem roots
- Missing tools fail loudly — no silent fallback behavior
- One route, one owning agent: attribution stays unambiguous
Put your agents on the radar
Start observing before you scale to a fleet.
The teams that succeed with multi-agent systems are the ones that could see their single agents first. Deploy the gateway, route one agent through it, and watch the picture appear.