See every step
your agent takes
End-to-end request tracing for AI agents. Follow every request through retrieval, generation, tool calls, and guards - with timing, tokens, and cost at every step. Powered by traceAI, our open-source library with 30+ framework integrations built on OpenTelemetry.
Full observability
for your AI pipeline
Every request produces a trace tree with full span hierarchy - from the root agent call through LLM generation, tool invocations, retrieval, chain steps, and guard checks. Each span captures input, output, latency, token counts (prompt + completion), cost, model name, provider, status, and custom attributes.
See tracing in actionVisualize execution as a nested waterfall timeline showing parallel and sequential operations. Click any span to see its full detail - input/output payloads, token breakdown, latency, evaluation scores, and annotations. Trace trees show the parent-child relationship between agent, LLM, chain, tool, and embedding spans.
Explore timeline viewFilter traces by trace name, trace ID, user, session, model, provider, status, span kind (agent, LLM, tool, chain, embedding), latency range, token count, cost, tags, prompt name/version, or any custom span attribute. Combine multiple filters with AND logic. Results update in real-time.
Learn about searchtraceAI is our open-source instrumentation library built on OpenTelemetry. Install a framework-specific package (pip install traceAI-openai, traceAI-langchain, traceAI-anthropic...), call .instrument(), and every LLM call is traced automatically. 30+ integrations - OpenAI, Anthropic, Bedrock, Vertex AI, LangChain, LlamaIndex, CrewAI, AutoGen, DSPy, Haystack, MCP, Pipecat, VAPI, LiveKit, and more. Python and TypeScript. Vendor-neutral - works with any OTel-compatible backend.
View on GitHub Debug, optimize,
and audit with confidence
Debug production issues
When a user reports a problem, search by user ID or session to find the exact trace. See every span the agent executed, what it sent to the LLM, and where it failed.
Find latency bottlenecks
The waterfall timeline shows exactly where time is spent - retrieval, generation, tool calls, or chain orchestration. Sort spans by duration to find the slowest steps.
Track token cost per request
Every span records prompt tokens, completion tokens, and cost. Roll up to see cost per trace, per user, or per session. Identify expensive patterns before the bill arrives.
Audit agent reasoning chains
Review the full decision chain for any agent action - what context was retrieved, what the LLM received, what tools were called, and what was returned. Critical for compliance.
Debug RAG retrieval quality
See exactly what documents were retrieved, what chunks were sent to the LLM, and whether the generation used them correctly. Trace the gap between retrieval and generation.
Compare across deployments
Filter traces by prompt version, model, or tag to compare performance before and after changes. Validate that your optimization actually helped.
From blind to
full visibility in minutes
Install traceAI for your framework
pip install traceAI-openai (or traceAI-langchain, traceAI-anthropic, traceAI-crewai...). Call .instrument() and every LLM call, tool use, retrieval, and chain step is auto-traced. 30+ framework packages. Built on OpenTelemetry.
Traces flow in real-time
Every request produces a trace with full span hierarchy, timing, tokens, cost, and input/output at each step. Search by any attribute - user, session, model, status, latency, or custom tags.
Debug and optimize
Use the waterfall timeline to find bottlenecks. Click any span for full detail. Attach evaluation scores to traces. Feed insights into experiments to continuously improve your agent.
Powering teams from
prototype to production
From ambitious startups to global enterprises, teams trust Future AGI to ship AI agents confidently.