Connic
Debug with confidence

See Everything
Your Agents Do

Stop guessing why agents fail. Every run tracked, every tool call traced, every token counted. Built-in and ready to use. No logging infrastructure to build.

100%

Runs tracked

0

Setup required

ms

Trace precision

Agent Runs
Last 7 Days
All Statuses
247 runs
Agent
Status
Duration
Tokens
Time
invoice-processor
Completed
2.3s
1.2k
2 min ago
support-agent
Running
12s
-
Just now
data-enricher
Completed
890ms
456
5 min ago
document-analyzer
Failed
1.1s
234
8 min ago
email-classifier
Queued
-
-
Just now

Complete visibility, zero effort

Everything you need to understand, debug, and optimize your agents. Built-in from day one. No additional setup required.

Run History

Every agent execution is automatically tracked. See status, duration, inputs, outputs, and errors at a glance. Filter by time, status, or deployment.

  • Automatic tracking of every run
  • Filter by time range, status, deployment
  • Real-time status updates
  • Click to inspect full details

Execution Traces

Step-by-step breakdown of what your agent did. See every LLM call, tool invocation, and intermediate result with precise timing.

  • LLM agent reasoning steps
  • Tool call inputs and outputs
  • MCP server interactions
  • Middleware execution hooks

Token Usage

Know exactly what each run costs. Track input, output, and total tokens per run with detailed breakdowns. No surprises on your AI bill.

  • Total tokens per run
  • Input vs output breakdown
  • Cost estimation
  • Usage trends over time

Instant status at a glance

Completed
Running
Queued
Failed

Trace every operation type

LLM Agent
Tool Call
MCP Tool
Middleware

Define tools and middleware in your agent config. Learn about the SDK

Powerful debugging built-in

Click on any run to see the complete execution trace. Understand exactly what happened, step by step.

Run Details#a1b2c3d4 Completed
invoice-webhook
Dec 5, 2024, 2:34:12 PM
2.34s
1,234 tokens

Input

invoice_url
https://storage.example.com/inv-2024-001.pdf

Output

{
  "invoice_id": "INV-2024-001",
  "vendor": "Acme Corp",
  "amount": 1250.00,
  "status": "processed"
}

Traces (5)

Runinvoice-processor
2,341msok
LLM Agentinvoice-processor
1,892msok
Tool Callparse_pdf
234msok
MCP Tooldatabase.query
156msok
Tool Callsave_invoice
89msok

Visualize trends over time

Agent Runs History

Last 7 days

Completed
Failed
Mon
Tue
Wed
Thu
Fri
Sat
Sun

What you don't need

Traditional agent monitoring requires building custom infrastructure, learning query languages, and maintaining dashboards.

Log aggregation systems
Custom tracing code
Monitoring infrastructure
Alert configuration
Query languages
Dashboard builders

What you get instead

Complete observability out of the box. Every run tracked, every trace recorded, every token counted. Automatically.

Automatic run tracking
Built-in trace viewer
Real-time status updates
Token usage breakdown
Click-to-inspect details
Zero configuration

Debug without expertise

When something goes wrong, any engineer can trace through the execution, see exactly what happened, and understand why. No specialized knowledge required.

Click on a run. See the traces. Find the problem. Fix it. That simple.