Build, test, and improve Cognigy.AI agents from your AI assistant — MCP tools, workflow skills, and subagents for Claude Code, Codex, and more.
Agent
Builds a new Cognigy AI Agent end to end — discovers projects, ensures a working LLM (reusing one via packages before creating a new one), creates the agent, tests it, and refines its persona/job config. Use when the user wants to create, build, or set up a new AI agent from scratch. Runs the multi-step build loop in…
Agent
Audits a Cognigy voice AI agent against the Voice Go-Live Checklist and applies safe fixes. Use when the user wants to make a voice agent production-ready, run a go-live audit, validate voice settings, or fix voice configuration. Runs the dry-run audit, summarizes findings, applies auto-fixable fixes on approval, then…