# Arklex Platform

> Test, simulate, and evaluate AI agents. Connect any agent, run multi-turn simulations, and score performance with LLM-judged and human-calibrated metrics.

## Docs

- [Platform Overview](https://docs-platform.arklex.ai/overview.md): Arklex is a web platform for testing, simulating, and evaluating AI agents.
- [Quickstart](https://docs-platform.arklex.ai/quickstart.md)
- [FAQ](https://docs-platform.arklex.ai/faq.md): Common questions about connecting agents, running simulations, evaluating performance, and team workflows in Arklex.
- [Agents](https://docs-platform.arklex.ai/agents.md): Connect and manage the AI agents you want to test in Arklex.
- [Scenarios](https://docs-platform.arklex.ai/scenarios.md): Define the simulated users that interact with your agent during a simulation.
- [Simulations](https://docs-platform.arklex.ai/simulations.md): Run scenarios against a connected agent and record full conversation transcripts.
- [Evaluations](https://docs-platform.arklex.ai/evaluations.md): Score simulation conversations with an LLM judge and detect behavioral failures.
- [Annotations](https://docs-platform.arklex.ai/annotations.md): Add human judgment to evaluation results and calibrate LLM judge scores.
- [Knowledge](https://docs-platform.arklex.ai/knowledge.md): Manage documents and websites that simulated users can reference during a simulation.
- [Metrics](https://docs-platform.arklex.ai/metrics.md): Define what the LLM judge evaluates. Use built-in metrics or create custom ones with your own rubric.
- [Settings](https://docs-platform.arklex.ai/settings.md): Manage your profile, team members, usage, and billing.
- [Metric Alignment](https://docs-platform.arklex.ai/metric-alignment.md): Use human annotations to automatically improve a metric's scoring prompt.
- [Contact](https://docs-platform.arklex.ai/support.md): Get help with Arkdock or reach the Arklex team.

## OpenAPI Specs

- [openapi](https://docs-platform.arklex.ai/api-reference/openapi.json)