[/PLATFORM]

ONE PLATFORM.
FOUR LAYERS OF CONTROL.

Everything an engineering team needs to operate fleets of AI agents in production — without bolting together six vendors.

[LIVE_VIEW]

SEE EVERY DECISION.

The trace waterfall is the product surface your engineers will live in. Every span is clickable, every prompt diffable, every tool response inspectable.

live_trace_view.exeSTREAMING
trace_id 8821-9f2c-7d11
agent finance.classifier
tokens 14,228
cost $0.084
3.62s total
0ms
router.dispatch
12ms
144ms
llm.reason [gpt-4o]
1.24s
1512ms
tool.sql_query
182ms
1728ms
policy.guard:read-only
9ms
1800ms
llm.reason [gpt-4o]
718ms
2592ms
tool.http_get
287ms
2916ms
critique.loop
446ms
3420ms
agent.complete
0ms
reasoning tool_call llm complete
01

Orchestration

Declarative workflows for multi-agent systems. DAG routing, durable state, branching loops, human-in-the-loop pauses. Resume agents hours or days later — execution context is persisted.

  • [+] Type-safe SDK (Python, TypeScript)
  • [+] Model-agnostic routing
  • [+] Durable checkpoints
  • [+] Versioned agent definitions
02

Observability

Full execution trace per run. Every reasoning step, tool invocation, and token cost indexed and searchable. Replay any production session, diff two runs side-by-side.

  • [+] Per-step token & latency
  • [+] Trace replay
  • [+] OpenTelemetry exports
  • [+] Search across millions of runs
03

Governance

Policy-as-code engine. Define which tools an agent can call, under what conditions, with what spend ceiling. PII redaction, manual approval gates, immutable audit trail.

  • [+] Per-agent budget caps
  • [+] Tool allow/deny policies
  • [+] Approval workflows
  • [+] Audit log export
04

Evaluation

Continuous evals against production traffic. Catch regressions before a prompt or model change ships. CI integration so every PR is graded.

  • [+] Backtest on production traces
  • [+] LLM-as-judge & code grading
  • [+] Regression alerts
  • [+] GitHub Actions integration
[INTEGRATE]

SHIP THIS AFTERNOON.

Wrap your existing agent. Push a deploy. Open the dashboard. You're done.

agent.pyv1.4.2
from agenticplane import Plane, policy

plane = Plane(api_key="ap_8f2x...")

@plane.agent(id="finance.classifier")
async def run(ctx, prompt: str):
result = await ctx.reason(
model="gpt-4o",
tools=[sql_query, http_get],
policy=policy.READ_ONLY,
budget_usd=0.50,
)
return result.summary
SEE_PRICING →