Guide an agentops-stacks project through its full production lifecycle — data preparation, agent development, evaluation gates, CI/CD promotion, and production monitoring — following the Single-Account Single-Agent pattern from the Big Book of AgentOps. Use…
Operate and troubleshoot the UC Functions tools component in an AgentOps Stacks project — register new functions, update EXECUTE grants, list available functions, re-run the registration job. Use when the user needs to add, update, or grant access to UC…
Set up and operate usage tracking / cost attribution for an AgentOps Stacks project — tag resources with project/environment/agent, attach a serverless usage policy, retrofit tags onto a project scaffolded without them, tag newly added compute, and query…
Add a new agent to an existing AgentOps Stacks project. Creates the agent folder, app resource, experiment, and manifest entry. Triggers on "add agent", "new agent", "create another agent", "add-agent".
Add a custom LangGraph supervisor agent that routes across an AgentOps Stacks project's agents, scaffolded into databricks.yml and the manifest so it rides the same eval-gate + dev/staging/prod lifecycle as every other agent. First checks whether a supervisor…
Comprehensive AgentOps reference and advisory guide, distilled from Databricks' The Big Book of AgentOps (Rao, Choo, Wulffert, Baur; Jul 2026) and kept current with platform state. Covers deploying quality, reliable, safe, observable agentic systems on…
Scaffold a new AgentOps Stacks project — a multi-agent LangGraph bundle (DAB) with shared components, per-agent Databricks Apps, evaluation, and CI/CD. Use when the user wants to start a new AI agent project on Databricks. Triggers on "scaffold a new agentops…
Operate and troubleshoot the Lakebase (Autoscaling Postgres) memory component in an AgentOps Stacks project — check endpoint health, mint credentials, inspect or clear checkpointer (short-term) and store (long-term) tables, manage the Postgres schema. Use…
Operate and troubleshoot the Vector Search component in an AgentOps Stacks project — check index status, trigger sync, test the retriever, update the DLT data pipeline. Use when the user needs to manage their VS index or debug retrieval quality.
Decide whether a new agent capability should be a UC-function tool, an MCP server, or an Agent Skill — and push back when the user names the wrong one. Runs an invariant cascade, then a falsification pass that argues against the requested option before…