Trace every step, get root-cause explanations, and cut token cost with actionable fixes.
No credit card. First trace in about 3 minutes.
Why did my agent fail?
Which prompt caused this issue?
Why is cost increasing?
Which tool broke?
Full run tracing across your agent
Root cause analysis for failures
Prompt, response, and tool visibility
Cost and latency tracking
Visualize every step of your agent with spans, tools, and LLM calls in a clear timeline.
Automatically detect why runs fail and pinpoint the exact step that broke.
Get suggestions to improve prompts, reduce latency, and lower cost.
Copy your API key, run a local demo app, and inspect traces in under a minute.
Watch your run live with workflow graph updates, active spans, streaming logs, and artifacts as they happen.
[10:24:41] span_started planner.llm_call
[10:24:41] token_stream +42
[10:24:42] artifact_created prompt.rendered
Quickly move from a broken run to a clear explanation and actionable fix.
External API endpoint timeout. This endpoint has a 94% failure rate in the last hour.
Increase timeout to 10s or add retry logic with exponential backoff
Install SDK, add API key, and verify trace delivery.
# 1) Install SDK pip install agentscope-sdk # 2) Add your API key export AGENTSCOPE_API_KEY=proj_live_xxx # 3) Send a minimal trace import os import agentscope os.environ["AGENTSCOPE_API_KEY"] = os.getenv("AGENTSCOPE_API_KEY", "") agentscope.auto_instrument() print("trace received: run_01H...")
Track token usage, latency, and cost across every run and model.
Organize your work by team and project
Secure access with API keys
Signup includes organization + project context and guided setup
Your data is isolated and protected
Understand failures, improve performance, and ship better AI faster.