Understand every
AI agent run.
Cost. Tokens. Latency.
Problems.
Analyze an AI agent run and see exactly where your tokens, money, and latency went — without digging through logs.
Agent Run
customer-support-agent
Total Cost
$0.284
Tokens
37,031
LLM Calls
7
Duration
8.73s
Potential issue detected
Context increased 7.2× during this run.
Step 06 accounts for 48% of total cost.
Your agent works. But do you know what it's costing you?
One user request can trigger multiple model calls, tool calls, retries, and increasingly large contexts. The final answer may look simple while the execution underneath is anything but.
Single Request Execution Flow
From chaos to clarity
Without analysis
request startedllm requesttool callllm requestretryllm requesttool callllm request...request completed
With Agent Analyzer
What we analyze
Everything that matters
in an agent run.
Cost
Track total cost and cost per step. Find which step is burning your budget.
Tokens
See exactly where input and output tokens are going across every LLM call.
Latency
Find the slowest steps in an agent run. Pinpoint exactly where time is lost.
Tool Calls
See which tools were called, how often, and whether any are being called unnecessarily.
Context Growth
Detect rapidly growing context that inflates token costs on every subsequent call.
Problems
Automatically surface potential inefficiencies — before they become expensive habits.
Not just numbers. Explanations.
Raw traces tell you what happened. Agent Analyzer helps you understand why it happened.
Run Analysis
customer-support-agent
Context increased 7.2× during this run.
Step 06 represents 48% of total run cost.
search_orders was called 4 times.
How it works
Three steps from run to insight.
Bring a trace
Upload a supported agent trace or paste a run. We accept common formats from popular frameworks.
We analyze it
We calculate cost, tokens, latency, calls, context growth, and potential issues — automatically.
Fix what matters
See where your agent is spending time and money and what to investigate next.
Developer-first
Get answers without
the overhead.
No complicated setup. Bring a single agent run, analyze it in seconds, and see exactly where your tokens, time, and money went.
Go from trace to actionable insights without configuring a monitoring stack.
Analyze your first run immediately. No signup wall, no commitment.
Designed to work with the tools and models developers already use.
Find out what your agent
is really doing.
Stop guessing where the tokens, time, and money went.
Free to try