Skip to main content
Promptbeat is designed to make real agent applications visible as test targets. This page lists the agent app types, their current readiness level, and how to connect each one. A target is useful when it has a concrete invocation contract, a workspace or service environment, a trace output, and assertions that can turn agent behavior into a pass/fail result. Validation evidence is tracked separately from documented support.

Readiness levels

LevelMeaningWhat you can do right now
Runnable nowA checked-in example exists with a saved end-to-end report.Copy the example, provide credentials, run generate and eval, inspect artifacts.
Adapter patternA YAML provider template is available and the contract is documented.Supply the endpoint, CLI binary, gateway, or workspace; Promptbeat handles scenarios, generation, and reports.
RoadmapDesigned for but no stable provider or adapter contract documented yet.Do not list as a supported target until a provider file and example exist.

Coding agents

These are the primary targets for Promptbeat’s coding-agent scenario suite, which covers secret handling, sandbox boundary enforcement, terminal injection, repository injection, and egress control.
AgentProvider stringStatusNotes
Codex SDKopenai:codex-sdkRunnable nowValidated through the saved Promptbeat broad Codex report in examples/codex_agent/artifacts.
Codex app-serveropenai:codex-app-serverAdapter patternUse when app-server events and approval requests matter alongside the standard CLI flow.
Claude Agent SDKanthropic:claude-agent-sdkAdapter patternRequires a local or container Claude Code runtime, credentials, workspace, and trace capture.
OpenCodeopencode:sdkAdapter patternCan start an OpenCode runtime or connect to an existing server. Supply OPENCODE_MODEL and OPENCODE_BASE_URL.
OpenClawopenclaw:agent:mainAdapter patternRequires a running OpenClaw gateway URL, API key, and agent ID.
Custom CLI agentCustom / script providerAdapter patternWrap any CLI coding agent with a script provider or Inspect solver that returns a final answer and trace.

Application agents

Beyond coding agents, the same target abstraction covers any agent that exposes a REST endpoint or can be wrapped in a provider adapter.
Agent classProvider / adapterStatusNotes
Browser agentHTTP or custom provider; Target Lab browser adapterAdapter patternUse Target Lab when Promptbeat needs to own browser startup, page seeding, and DOM trace capture.
Customer support agenthttp provider, OpenAI Agents wrapper, or custom providerAdapter patternRequires tenant and user fixtures, tool call records, and an action audit log.
Data analysis agentPython/JavaScript custom provider, notebook runner, or Inspect solverAdapter patternCapture SQL queries, notebook cells, generated files, and the final answer as trace evidence.
DevOps agentScript or custom provider; Target Lab adapterAdapter patternRun only against dry-run or disposable cloud environments. Capture commands, API calls, and diff plans.
Security triage agentHTTP or custom provider connected to SIEM/ticketing backendRoadmapNo stable contract documented yet. Do not list as a supported target until a provider file exists.

Target-ready checklist

Before you run promptbeat eval against a new target, confirm all of the following:
  • Expose a final answer — the target’s response must be a string that the judge can score.
  • Capture trace evidence when possible — return tool calls, commands, file reads/writes, network events, and policy decisions alongside the answer.
  • Expose a reset or setup mechanism for stateful agents — multi-turn or workspace-based agents need a clean starting state for each probe; document the reset path in your provider config.
  • Keep credentials out of provider YAML — use {{env.VAR_NAME}} references; never commit keys to the file.
  • Point working_dir at a safe fixture workspace — not your production repository.
  • Document which scenario risk types the target supports — so you can filter scenarios to the capabilities the agent actually has.
Start with the HTTP adapter pattern for any agent that already has a REST API — it works out of the box with providers.http.yaml, and you can add trace metadata to the JSON response incrementally. See Agent Configuration Examples for a complete HTTP walkthrough.