Traccia LogoTraccia Logo Dark
About TracciaPricingGovernanceSecurityBlogDocs
Book a demoStart free
Overview
Quickstart
Installation
Agents
Traces
Spans
OpenTelemetry
@observe()
Agent Identity
Auto-Instrumentation
Exporters
Metrics
Pricing & Costs
Guardrail Detection
Governance
Prompts
Evaluate
Advanced
LangChain
Claude Code
Cursor
GitHub Copilot
CrewAI
OpenAI Agents SDK
Gemini SDK
Overview
OpenAI SDK
Anthropic SDK
Gemini SDK
LangChain
LiteLLM
Vercel AI SDK
LlamaIndex
CrewAI
OpenAI Agents SDK
n8n
HTTP
Getting Started
OTLP Ingestion
Dashboard
Compliance Hub
Policies
Guardrail Posture
Prompts
Prompt Playground
Datasets
Scorers
Experiments
Teams
Costs
Traces
EU AI Act Compliance
HIPAA Controls for AI Agents
Cap Refunds And Purchases
Approve A Refund Or Purchase
Stop A Dangerous Tool
Multi-Agent Tracing
Parallel Runs
Local Jaeger Setup
Grafana Tempo Setup
Cost Optimization
Run Experiments From Code
Run Evals In CI
Compare Two Experiments
Troubleshooting
Python SDK API
TypeScript SDK API
CLI Commands
Configuration
Events
Errors
Release Notes
FAQ
Coupon Codes

Guides & Recipes

Task-focused walkthroughs for refund and purchase caps, dangerous tools, local tracing, experiments, multi-agent systems, and costs.

Cap Refunds And Purchases

Stop an agent from refunding or buying above a dollar amount you set, before that function runs.

Approve A Refund Or Purchase

Let a person approve the refunds and purchases your AI agent may not make alone, then run the approved action from your own server.

Stop A Dangerous Tool

Deny a named function, or a shell command that contains text you listed, before that function runs.

Multi-Agent Tracing

Trace complex multi-agent systems and understand agent collaboration.

Parallel Runs in One Process

Run multiple agents safely from a single process using run_identity() and force_flush().

Local Jaeger Setup

Set up Jaeger locally to view your traces.

Grafana Tempo Setup

Set up Grafana Tempo locally for trace visualization with powerful querying.

Cost Attribution & Optimization

Reduce LLM costs with Traccia insights and SDK features.

Run Experiments From Code

Install the SDK, point it at a dataset, call evaluate(), and open the saved run under Evaluate → Experiments.

Run Evals In CI

Run an eval on every pull request and fail the check when quality, cost, or latency gets worse.

Compare Two Experiments

Pick a baseline and a candidate on the same dataset, then read score, cost, and latency deltas before you promote.

Troubleshooting Guide

Diagnose and fix common Traccia SDK issues.

© 2026 Traccia.