Skip to main content
BotGauge finds out how your AI agent fails before your users do. It attacks the agent the way a real attacker would, records the full execution path behind every result, and lets you replay a finding to confirm a fix.
Get started free →Book a demo

​
Choose your quickstart

Red-team an agent

Best for: teams that want to know how an agent breaks under attack.Connect an endpoint, approve a plan, and read the results. About 15 minutes, with a sample agent included.

Trace an agent

Best for: teams that want to see every prompt, tool call, and span behind a result.Use the Python SDK or any OpenTelemetry exporter. About 5 minutes.
You can start with either one. Red teaming needs only your agent’s endpoint, and tracing needs the SDK or an exporter in your app.

​
How the pieces fit together

A red-team run tells you what broke. Tracing shows how the agent got there. Once you’ve fixed the agent, replaying the attack confirms the fix.

​
Find your way

​
Explore the docs

Get started

Core concepts and account setup.

Red teaming

Connect, recon, plan, run, and read results.

Tracing

Sessions, turns, agents, and spans over OpenTelemetry.

Integrations

Eleven frameworks, plus any OTLP exporter.

Platform

Organizations, workspaces, projects, roles, keys, and secrets.

Reference

CLI commands and environment variables.

​
Common questions

For red teaming, no. BotGauge needs only your agent’s endpoint, and a small optional wrapper unlocks deeper tests. See black box and grey box. For tracing, the zero-code launcher traces a Python app without edits.
BotGauge never attacks until you approve a specific plan, it acts only within the scope you approved, and it refuses real actions in production. See Approve and run.
LangChain, LangGraph, OpenAI SDK, Anthropic SDK, LlamaIndex, CrewAI, OpenAI Agents, Google ADK, AutoGen AgentChat, PydanticAI, and MCP. Any other OpenTelemetry source can send traces through OTLP.
No. It means the tested rules held under the attacks tried. Only a result of Held is a pass, and a rule that couldn’t be tested is a gap, not safety. See Read your results.
Tracing uses project API keys. Red teaming reads credentials your agent needs from project secrets, and BotGauge never shows the values back.

See BotGauge in action

Get a 30-minute walkthrough of red teaming and tracing for your agent.
The tracing SDK is an early release (0.x). Public API shapes may still change before 1.0.