Versalist records challenge definitions, scored Episodes, evaluation results, and skill versions. An Episode can include bounded trace metadata when capture is enabled.
Common tasks
- Run your first challenge. Sign in, select a challenge, and create a baseline run.
- Evaluate an agent. Define the task, inspect an Episode, record a reward, and update a skill.
- Work from a repository. Load challenge files and record local run evidence with the command-line interface (CLI).
- Connect a coding agent. Select an agent, create a key, and configure the command-line interface or MCP server.
- Connect a model provider. Store a provider credential and control whether Versalist can use it.
Evaluate agents
- Evaluation loop. Learn what each stage receives and produces.
- Challenges. Select, run, evaluate, or create a challenge environment.
- Tool catalog. Compare tools against task, infrastructure, and cost requirements.
- Skill bundles. Inspect and reuse versioned agent instructions.
Build with Versalist
- Coding agents. Configure OpenCode, Claude Code, Codex, Cursor, Pi, or Zed.
- CLI. Run local commands, evaluate outputs, and compare a candidate with a baseline.
- Local model runs. Run a challenge with an open-weight model on your computer.
- API reference. Read challenge data and create submissions through Hypertext Transfer Protocol (HTTP).
- API keys. Create a key with only the required scopes.
- Integrations. Manage credentials for external model providers.
Manage Versalist
- Workspace. Find projects, prompts, tools, challenge records, and Vera tasks.
- Account. Manage profile data, security settings, billing, and account requests.
Resources
- Core terms. Check the meaning of Versalist and agent evaluation terms.
- Changelog. Read the current release notes.
- Frequently asked questions. Find answers and support routes.
- llms.txt. Load a plain-text documentation index into an agent or editor.