Xpersona

Crawler Summary

agent-scenario-testing answer-first brief

Simulation-test a CrewAI travel agent with a user-simulator agent and a judge agent via LangWatch Scenario and pytest. Agent Scenario Testing Test an LLM agent with **other agents**: a simulated user drives a conversation with the agent under test, and a judge agent grades the transcript against plain-language criteria. The agent under test here is a small $1 travel planner; the simulation and judging come from $1; $1 runs everything. Why Classic tests pair a fixed input with an exact expected output. Agents answer in natural languag Capability contract not published. No trust telemetry is available yet. Last updated 10/9/2026.

Freshness

Last checked 10/9/2026

Best For

agent-scenario-testing is best for crewai, multi-agent workflows where OpenClaw compatibility matters.

Not Ideal For

Contract metadata is missing or unavailable for deterministic execution.

Evidence Sources Checked

editorial-content, GITHUB REPOS, runtime-metrics, public facts pack

CardFactsSnapshotContractTrust
Agent DossierGITHUB REPOSSafety: 66/100

agent-scenario-testing

Simulation-test a CrewAI travel agent with a user-simulator agent and a judge agent via LangWatch Scenario and pytest. Agent Scenario Testing Test an LLM agent with **other agents**: a simulated user drives a conversation with the agent under test, and a judge agent grades the transcript against plain-language criteria. The agent under test here is a small $1 travel planner; the simulation and judging come from $1; $1 runs everything. Why Classic tests pair a fixed input with an exact expected output. Agents answer in natural languag

OpenClawself-declared

Public facts

4

Change events

1

Artifacts

0

Freshness

Oct 9, 2026

Verifiededitorial-contentNo verified compatibility signals

Capability contract not published. No trust telemetry is available yet. Last updated 10/9/2026.

Trust evidence available

Trust score

Unknown

Compatibility

OpenClaw

Freshness

Oct 9, 2026

Vendor

Crzyc0d3r

Artifacts

0

Benchmarks

0

Last release

Unpublished

Executive Summary

Key links, install path, and a quick operational read before the deeper crawl record.

Verifiededitorial-content

Summary

Capability contract not published. No trust telemetry is available yet. Last updated 10/9/2026.

View Source

Setup snapshot

  1. 1

    Setup complexity is LOW. This package is likely designed for quick installation with minimal external side-effects.

  2. 2

    Final validation: Expose the agent to a mock request payload inside a sandbox and trace the network egress before allowing access to real customer data.

Evidence Ledger

Everything public we have scraped or crawled about this agent, grouped by evidence type with provenance.

Verifiededitorial-content
Vendor (1)

Vendor

Crzyc0d3r

profilemedium
Observed Oct 9, 2026Source linkProvenance
Compatibility (1)

Protocol compatibility

OpenClaw

contractmedium
Observed Oct 9, 2026Source linkProvenance
Security (1)

Handshake status

UNKNOWN

trustmedium
Observed unknownSource linkProvenance
Integration (1)

Crawlable docs

6 indexed pages on the official domain

search_documentmedium
Observed Apr 15, 2026Source linkProvenance

Release & Crawl Timeline

Merged public release, docs, artifact, benchmark, pricing, and trust refresh events.

Self-declaredagent-index

Docs Update

Docs refreshed: Sign in to GitHub · GitHub

search_documentmedium

Fresh crawlable documentation was indexed for the official domain.

Observed Apr 15, 2026

Artifacts Archive

Extracted files, examples, snippets, parameters, dependencies, permissions, and artifact metadata.

Self-declaredGITHUB REPOS

Extracted files

0

Examples

3

Snippets

0

Languages

python

Executable Examples

text

agent-scenario-testing/
├── travel_agent/
│   ├── __init__.py          exports TravelPlanner, build_travel_crew, TravelAgentAdapter
│   ├── crew.py              CrewAI planner: one Agent + one Task; TravelPlanner.reply()
│   │                        turns the conversation into a transcript and runs the crew
│   └── adapter.py           TravelAgentAdapter(scenario.AgentAdapter) - the single call()
│                            method Scenario needs; accepts an injectable reply_fn for tests
├── tests/
│   ├── test_travel_agent.py end-to-end simulations (user simulator + judge); need an API key
│   └── test_adapter_offline.py  unit tests for transcript formatting and the adapter, no LLM
├── pytest.ini               asyncio mode + the agent_test marker
├── .env.example             placeholder env vars (copy to .env)
└── requirements.txt

mermaid

flowchart LR
    T[pytest test] -->|scenario.run| S[Scenario executor]
    S -->|turn| U[User Simulator Agent<br/>LLM plays the persona]
    S -->|turn| A[TravelAgentAdapter.call]
    A --> C[CrewAI Travel Planner crew]
    C --> A
    S -->|end of conversation| J[Judge Agent<br/>grades against criteria]
    J -->|success / reasoning| T

bash

python -m venv .venv && source .venv/bin/activate
pip install -r requirements.txt
cp .env.example .env            # add OPENAI_API_KEY (used by CrewAI and Scenario)
export $(grep -v '^#' .env | xargs)

pytest tests/test_adapter_offline.py      # no network, runs in seconds
pytest -s tests/test_travel_agent.py      # full simulations, calls the LLM
# or: uv run pytest -s tests/test_travel_agent.py

Docs & README

Full documentation captured from public sources, including the complete README when available.

Self-declaredGITHUB REPOS

Docs source

GITHUB REPOS

Editorial quality

ready

Simulation-test a CrewAI travel agent with a user-simulator agent and a judge agent via LangWatch Scenario and pytest. Agent Scenario Testing Test an LLM agent with **other agents**: a simulated user drives a conversation with the agent under test, and a judge agent grades the transcript against plain-language criteria. The agent under test here is a small $1 travel planner; the simulation and judging come from $1; $1 runs everything. Why Classic tests pair a fixed input with an exact expected output. Agents answer in natural languag

Full README

Agent Scenario Testing

Test an LLM agent with other agents: a simulated user drives a conversation with the agent under test, and a judge agent grades the transcript against plain-language criteria. The agent under test here is a small CrewAI travel planner; the simulation and judging come from LangWatch Scenario; pytest runs everything.

Why

Classic tests pair a fixed input with an exact expected output. Agents answer in natural language, so there is no single correct string to assert on, and a real user rarely says everything in one message. Simulation testing fixes both problems:

  1. A User Simulator Agent plays a persona described in a sentence or two and keeps the conversation going for several turns.
  2. The agent under test replies as it would in production.
  3. A Judge Agent reads the whole exchange and decides whether each criterion was met, returning a pass/fail with reasoning.

The canonical failure this catches: a judge asked to verify "the destination is less than 4 hours from the user" cannot do so if the planner never asked where the user lives. The fix is a prompt change (ask for the starting location), and the test now guards against regressions.

Code map

agent-scenario-testing/
├── travel_agent/
│   ├── __init__.py          exports TravelPlanner, build_travel_crew, TravelAgentAdapter
│   ├── crew.py              CrewAI planner: one Agent + one Task; TravelPlanner.reply()
│   │                        turns the conversation into a transcript and runs the crew
│   └── adapter.py           TravelAgentAdapter(scenario.AgentAdapter) - the single call()
│                            method Scenario needs; accepts an injectable reply_fn for tests
├── tests/
│   ├── test_travel_agent.py end-to-end simulations (user simulator + judge); need an API key
│   └── test_adapter_offline.py  unit tests for transcript formatting and the adapter, no LLM
├── pytest.ini               asyncio mode + the agent_test marker
├── .env.example             placeholder env vars (copy to .env)
└── requirements.txt

How the pieces fit: scenario.run() alternates between the agents in its agents list. Each turn it builds an AgentInput (full OpenAI-style message history) and calls TravelAgentAdapter.call(), which formats the history as a transcript and kicks off the crew. When the simulator decides the conversation is done (or max_turns is hit), the judge is asked for a verdict.

flowchart LR
    T[pytest test] -->|scenario.run| S[Scenario executor]
    S -->|turn| U[User Simulator Agent<br/>LLM plays the persona]
    S -->|turn| A[TravelAgentAdapter.call]
    A --> C[CrewAI Travel Planner crew]
    C --> A
    S -->|end of conversation| J[Judge Agent<br/>grades against criteria]
    J -->|success / reasoning| T

Run

python -m venv .venv && source .venv/bin/activate
pip install -r requirements.txt
cp .env.example .env            # add OPENAI_API_KEY (used by CrewAI and Scenario)
export $(grep -v '^#' .env | xargs)

pytest tests/test_adapter_offline.py      # no network, runs in seconds
pytest -s tests/test_travel_agent.py      # full simulations, calls the LLM
# or: uv run pytest -s tests/test_travel_agent.py

-s lets Scenario print the live conversation and the judge's reasoning. The simulation tests are skipped automatically when OPENAI_API_KEY is unset. Any provider supported by LiteLLM works for the simulator/judge; set SCENARIO_MODEL (for example openai/gpt-4o-mini) and TRAVEL_AGENT_MODEL for the crew.

Extending

  • Add a scenario: copy one of the tests, change the description (the persona) and the judge criteria.
  • Script part of the dialogue with scenario.user(...), scenario.agent(), scenario.proceed(turns=n) and scenario.judge() when you need control over specific turns.
  • Swap the agent: any callable that maps a message list to a reply can be passed to TravelAgentAdapter(reply_fn=...), or subclass scenario.AgentAdapter directly.

Contract & API

Machine endpoints, protocol fit, contract coverage, invocation examples, and guardrails for agent-to-agent use.

MissingGITHUB REPOS

Endpoints

Dossier APISnapshot APIContract APITrust API

Contract coverage

Status

missing

Auth

None

Streaming

No

Data region

Unspecified

Protocol support

OpenClaw: self-declared

Requires: none

Forbidden: none

Guardrails

Operational confidence: low

No positive guardrails captured.
Invocation examples
curl -s "https://www.xpersona.co/api/v1/agents/crewai-crzyc0d3r-agent-scenario-testing/snapshot"
curl -s "https://www.xpersona.co/api/v1/agents/crewai-crzyc0d3r-agent-scenario-testing/contract"
curl -s "https://www.xpersona.co/api/v1/agents/crewai-crzyc0d3r-agent-scenario-testing/trust"

Reliability & Benchmarks

Trust and runtime signals, benchmark suites, failure patterns, and practical risk constraints.

Missingruntime-metrics

Trust signals

Handshake

UNKNOWN

Confidence

unknown

Attempts 30d

unknown

Fallback rate

unknown

Runtime metrics

Observed P50

unknown

Observed P95

unknown

Rate limit

unknown

Estimated cost

unknown

Do not use if

Contract metadata is missing or unavailable for deterministic execution.
No benchmark suites or observed failure patterns are available.

Media & Demo

Every public screenshot, visual asset, demo link, and owner-provided destination tied to this agent.

Missingno-media
No screenshots, media assets, or demo links are available.

Related Agents

Neighboring agents from the same protocol and source ecosystem for comparison and shortlist building.

Self-declaredprotocol-neighbors
Github ReposUpdated 4h agoRank 70

AionUi

Free, local, open-source 24/7 Cowork app and OpenClaw for Gemini CLI, Claude Code, Codex, OpenCode, Qwen Code, Goose CLI, Auggie, and more | 🌟 Star if you like it!

MCPOPENCLAW
Github ReposUpdated 6mo agoRank 70

activepieces

AI Agents & MCPs & AI Workflow Automation • (~400 MCP servers for AI agents) • AI Automation / AI Agent with MCPs • AI Workflows & AI Agents • MCPs for AI Agents

OPENCLAW
Github ReposUpdated 6mo agoRank 70

cherry-studio

AI productivity studio with smart chat, autonomous agents, and 300+ assistants.

MCPOPENCLAW
Github ReposUpdated 7mo agoRank 70

CopilotKit

The Frontend for Agents & Generative UI. React + Angular

OPENCLAW
Agent hubMore from this sourceOpenClaw agents
Machine Appendix

Contract JSON

{
  "contractStatus": "missing",
  "authModes": [],
  "requires": [],
  "forbidden": [],
  "supportsMcp": false,
  "supportsA2a": false,
  "supportsStreaming": false,
  "inputSchemaRef": null,
  "outputSchemaRef": null,
  "dataRegion": null,
  "contractUpdatedAt": null,
  "sourceUpdatedAt": null,
  "freshnessSeconds": null
}

Invocation Guide

{
  "preferredApi": {
    "snapshotUrl": "https://www.xpersona.co/api/v1/agents/crewai-crzyc0d3r-agent-scenario-testing/snapshot",
    "contractUrl": "https://www.xpersona.co/api/v1/agents/crewai-crzyc0d3r-agent-scenario-testing/contract",
    "trustUrl": "https://www.xpersona.co/api/v1/agents/crewai-crzyc0d3r-agent-scenario-testing/trust"
  },
  "curlExamples": [
    "curl -s \"https://www.xpersona.co/api/v1/agents/crewai-crzyc0d3r-agent-scenario-testing/snapshot\"",
    "curl -s \"https://www.xpersona.co/api/v1/agents/crewai-crzyc0d3r-agent-scenario-testing/contract\"",
    "curl -s \"https://www.xpersona.co/api/v1/agents/crewai-crzyc0d3r-agent-scenario-testing/trust\""
  ],
  "jsonRequestTemplate": {
    "query": "summarize this repo",
    "constraints": {
      "maxLatencyMs": 2000,
      "protocolPreference": [
        "OPENCLEW"
      ]
    }
  },
  "jsonResponseTemplate": {
    "ok": true,
    "result": {
      "summary": "...",
      "confidence": 0.9
    },
    "meta": {
      "source": "GITHUB_REPOS",
      "generatedAt": "2026-10-09T23:09:36.546Z"
    }
  },
  "retryPolicy": {
    "maxAttempts": 3,
    "backoffMs": [
      500,
      1500,
      3500
    ],
    "retryableConditions": [
      "HTTP_429",
      "HTTP_503",
      "NETWORK_TIMEOUT"
    ]
  }
}

Trust JSON

{
  "status": "unavailable",
  "handshakeStatus": "UNKNOWN",
  "verificationFreshnessHours": null,
  "reputationScore": null,
  "p95LatencyMs": null,
  "successRate30d": null,
  "fallbackRate": null,
  "attempts30d": null,
  "trustUpdatedAt": null,
  "trustConfidence": "unknown",
  "sourceUpdatedAt": null,
  "freshnessSeconds": null
}

Capability Matrix

{
  "rows": [
    {
      "key": "OPENCLEW",
      "type": "protocol",
      "support": "unknown",
      "confidenceSource": "profile",
      "notes": "Listed on profile"
    },
    {
      "key": "crewai",
      "type": "capability",
      "support": "supported",
      "confidenceSource": "profile",
      "notes": "Declared in agent profile metadata"
    },
    {
      "key": "multi-agent",
      "type": "capability",
      "support": "supported",
      "confidenceSource": "profile",
      "notes": "Declared in agent profile metadata"
    }
  ],
  "flattenedTokens": "protocol:OPENCLEW|unknown|profile capability:crewai|supported|profile capability:multi-agent|supported|profile"
}

Facts JSON

[
  {
    "factKey": "vendor",
    "category": "vendor",
    "label": "Vendor",
    "value": "Crzyc0d3r",
    "href": "https://github.com/crzyc0d3r/agent-scenario-testing",
    "sourceUrl": "https://github.com/crzyc0d3r/agent-scenario-testing",
    "sourceType": "profile",
    "confidence": "medium",
    "observedAt": "2026-10-09T13:52:39.601Z",
    "isPublic": true
  },
  {
    "factKey": "protocols",
    "category": "compatibility",
    "label": "Protocol compatibility",
    "value": "OpenClaw",
    "href": "https://www.xpersona.co/api/v1/agents/crewai-crzyc0d3r-agent-scenario-testing/contract",
    "sourceUrl": "https://www.xpersona.co/api/v1/agents/crewai-crzyc0d3r-agent-scenario-testing/contract",
    "sourceType": "contract",
    "confidence": "medium",
    "observedAt": "2026-10-09T13:52:39.601Z",
    "isPublic": true
  },
  {
    "factKey": "docs_crawl",
    "category": "integration",
    "label": "Crawlable docs",
    "value": "6 indexed pages on the official domain",
    "href": "https://github.com/login?return_to=https%3A%2F%2Fgithub.com%2Fopenclaw%2Fskills%2Ftree%2Fmain%2Fskills%2Fasleep123%2Fcaldav-calendar",
    "sourceUrl": "https://github.com/login?return_to=https%3A%2F%2Fgithub.com%2Fopenclaw%2Fskills%2Ftree%2Fmain%2Fskills%2Fasleep123%2Fcaldav-calendar",
    "sourceType": "search_document",
    "confidence": "medium",
    "observedAt": "2026-04-15T05:03:46.393Z",
    "isPublic": true
  },
  {
    "factKey": "handshake_status",
    "category": "security",
    "label": "Handshake status",
    "value": "UNKNOWN",
    "href": "https://www.xpersona.co/api/v1/agents/crewai-crzyc0d3r-agent-scenario-testing/trust",
    "sourceUrl": "https://www.xpersona.co/api/v1/agents/crewai-crzyc0d3r-agent-scenario-testing/trust",
    "sourceType": "trust",
    "confidence": "medium",
    "observedAt": null,
    "isPublic": true
  }
]

Change Events JSON

[
  {
    "eventType": "docs_update",
    "title": "Docs refreshed: Sign in to GitHub · GitHub",
    "description": "Fresh crawlable documentation was indexed for the official domain.",
    "href": "https://github.com/login?return_to=https%3A%2F%2Fgithub.com%2Fopenclaw%2Fskills%2Ftree%2Fmain%2Fskills%2Fasleep123%2Fcaldav-calendar",
    "sourceUrl": "https://github.com/login?return_to=https%3A%2F%2Fgithub.com%2Fopenclaw%2Fskills%2Ftree%2Fmain%2Fskills%2Fasleep123%2Fcaldav-calendar",
    "sourceType": "search_document",
    "confidence": "medium",
    "observedAt": "2026-04-15T05:03:46.393Z",
    "isPublic": true
  }
]

Sponsored

Ads related to agent-scenario-testing and adjacent AI workflows.