# Claude agent sdk evals

The Claude Agent SDK is the harness behind Claude Code, published so you can build your own
agent on the same loop: gather context, act, check the result, repeat. It gives you the tool
loop, file and shell tools, subagents, MCP support, sessions you can resume or fork, and hooks at
fixed points in the loop.

Hooks and subagents are the two features that matter for evaluation. A hook is a callback at a
named point, such as before a tool call or after one. That is where a check or a trace emit
attaches without touching the agent's prompt. A subagent runs in its own context and returns a
result to the main loop, so it is a natural unit to grade on its own instead of through whatever
the main agent finally says.

Telemetry is OpenTelemetry, turned on with CLAUDE_CODE_ENABLE_TELEMETRY and pointed with the
standard OTEL exporter variables. Metrics and events are the settled part: tokens and cost per
session, and an event for each prompt, response, API request, API error, tool result, and tool
decision. Spans are still behind a beta flag, and their names are Claude Code's own rather than
the OpenTelemetry GenAI ones, so anything reading them has to map them first.

## Questions answered under this concept

- [Can untrusted text trigger a file read in the Claude Agent SDK?](https://tessary.ai/answers/claude-agent-sdk-evals/can-untrusted-text-trigger-a-file-read-in-the-claude-agent-sdk)
- [How do I catch a regression in a Claude Agent SDK agent?](https://tessary.ai/answers/claude-agent-sdk-evals/how-do-i-catch-a-regression-in-a-claude-agent-sdk-agent)
- [How do I check a Claude Agent SDK tool call without touching the prompt?](https://tessary.ai/answers/claude-agent-sdk-evals/how-do-i-check-a-tool-call-without-touching-the-prompt)
- [How do I evaluate a subagent separately from the main loop?](https://tessary.ai/answers/claude-agent-sdk-evals/how-do-i-evaluate-a-subagent-separately-from-the-main-loop)
- [How do I trace a Claude Agent SDK agent?](https://tessary.ai/answers/claude-agent-sdk-evals/how-do-i-trace-a-claude-agent-sdk-agent)
- [Is the Claude Agent SDK open source?](https://tessary.ai/answers/claude-agent-sdk-evals/is-the-claude-agent-sdk-open-source)
- [What can a Claude Agent SDK hook check?](https://tessary.ai/answers/claude-agent-sdk-evals/what-can-a-claude-agent-sdk-hook-check)
- [What does Claude Code's OpenTelemetry output contain?](https://tessary.ai/answers/claude-agent-sdk-evals/what-does-claude-codes-opentelemetry-output-contain)
- [What's the difference between the Claude Agent SDK and AWS Strands Agents?](https://tessary.ai/answers/claude-agent-sdk-evals/whats-the-difference-between-claude-agent-sdk-and-aws-strands)
- [What's the difference between the Claude Agent SDK and Claude Code?](https://tessary.ai/answers/claude-agent-sdk-evals/whats-the-difference-between-the-claude-agent-sdk-and-claude-code)
- [What's the difference between the Claude Agent SDK and Claude Managed Agents?](https://tessary.ai/answers/claude-agent-sdk-evals/whats-the-difference-between-the-claude-agent-sdk-and-claude-managed-agents)
- [What's the difference between the Claude Agent SDK and Deep Agents?](https://tessary.ai/answers/claude-agent-sdk-evals/whats-the-difference-between-the-claude-agent-sdk-and-deep-agents)
- [What's the difference between the Claude Agent SDK and Google's Agent Development Kit (ADK)?](https://tessary.ai/answers/claude-agent-sdk-evals/whats-the-difference-between-the-claude-agent-sdk-and-google-adk)
- [What's the difference between the Claude Agent SDK and LangChain?](https://tessary.ai/answers/claude-agent-sdk-evals/whats-the-difference-between-the-claude-agent-sdk-and-langchain)
- [What's the difference between the Claude Agent SDK and LangGraph?](https://tessary.ai/answers/claude-agent-sdk-evals/whats-the-difference-between-the-claude-agent-sdk-and-langgraph)
- [What's the difference between the Claude Agent SDK and the Claude API?](https://tessary.ai/answers/claude-agent-sdk-evals/whats-the-difference-between-the-claude-agent-sdk-and-the-claude-api)
- [What's the difference between the Claude Agent SDK and the OpenAI Agents SDK?](https://tessary.ai/answers/claude-agent-sdk-evals/whats-the-difference-between-the-claude-agent-sdk-and-the-openai-agents-sdk)

---

Source: https://tessary.ai/answers/claude-agent-sdk-evals
All concepts: https://tessary.ai/answers
From Tessary, agent reliability for AI agents in production: https://tessary.ai