# 90-day agentic analytics rollout playbook Thirteen weeks, one business domain, and a written decision at the end. Source: https://agenticanalyticsnow.com/rollout-playbook/ (Alex Merced, Agentic Analytics Now). ## Roles - **Analytics leader:** Accountable for the outcome. Chooses the domain, sets success measures, makes the week 13 decision. - **Domain owner:** A business lead from the chosen domain. Supplies real questions, settles definition disputes, recruits pilot users. - **Analytics engineering lead:** Writes and maintains the metric and dimension definitions and the evaluation question set. - **Data platform lead:** Owns the catalog, the authoritative copies, the interfaces the agent uses, and freshness checks. - **Security and governance lead:** Owns access policies, identity propagation, audit, and the review of what the agent can do. - **Agent owner:** Configures and runs the agent: model, harness, connections, logging, cost tracking. ## Weeks 1 to 2: Frame the pilot **Goal:** Choose one domain, name the people, and write down what a right answer is before anything is built. **Owners:** Analytics leader (accountable), Domain owner, Data platform lead **Work** - Take the readiness assessment with the platform and analytics engineering leads, and keep the result link. - Choose one domain using the readiness result and the use-case library. Prefer the domain with the best existing definitions over the one with the most enthusiasm. - Collect 30 to 50 real questions from that domain, with the answers analysts actually gave. - Record how long those questions take to answer today. - Write the success measures: share of the question set answered correctly, time to answer, and which failures are unacceptable. **Exit criteria** - [ ] A named accountable owner and a standing group with the roles above. - [ ] A question set with known answers, stored where the team can version it. - [ ] Written success measures and a one-page scope that names what is out of scope. **Risks** - Scope grows to several domains before one works. - Questions are written by the project team instead of collected from users, so the set is easier than real use. **Read:** [Readiness assessment](https://agenticanalyticsnow.com/readiness/), [Use-case library](https://agenticanalyticsnow.com/use-cases/) ## Weeks 3 to 5: Definitions and access **Goal:** Make every question in the set answerable from written definitions, through access rules the agent cannot get around. **Owners:** Analytics engineering lead, Security and governance lead, Data platform lead **Work** - Write the metrics and dimensions the question set needs as code in the semantic layer, each with an owner and a description. - Settle the term collisions the questions expose, and give each meaning its own name. - Confirm the authoritative copy of each dataset involved, and record it in the catalog. - Put row and column rules in the catalog or policy layer, and design how the user’s identity reaches it through the agent. - Add freshness and basic quality checks to the datasets in scope. **Exit criteria** - [ ] An analyst can answer every question in the set from the definitions alone. - [ ] Access rules tested on the agent path with at least two users who have different permissions. - [ ] Freshness checks running, with an owner for each dataset. **Risks** - Definition work takes longer than planned. It is the most common schedule slip, and it is the work that decides accuracy. - Security review starts late and blocks the build phase. **Read:** [The semantic layer as an agent contract](https://agenticanalyticsnow.com/knowledge-base/semantic-layer-as-contract/), [Governance for agents](https://agenticanalyticsnow.com/knowledge-base/governance-for-agents/) ## Weeks 6 to 8: Build and evaluate **Goal:** Connect an agent to the governed definitions and measure it against the question set before any user sees it. **Owners:** Agent owner, Analytics engineering lead, Domain owner **Work** - If you are selecting a product, run the evaluation checklist and a trial on your own question set. - Connect the agent through open interfaces (SQL, APIs, or an MCP server) to the semantic layer, running as the user. - Run the full question set, log every generated query, and review each wrong answer. - Fix failures in definitions and descriptions first. Treat prompt patches as a last resort and write each one down. - Decide and test what the agent does when it is unsure or the data is not covered. **Exit criteria** - [ ] The question set passes the threshold agreed in week 2. - [ ] Every answer shows the definitions used and the data as-of time. - [ ] The audit trail names the person behind every query. - [ ] A written list of known failure types, shared with pilot users. **Risks** - Accuracy is improved by prompt patches that do not generalise, instead of by better definitions. - The question set is quietly trimmed to the questions that pass. **Read:** [Evaluation checklist](https://agenticanalyticsnow.com/evaluation-checklist/), [Evaluation and trust](https://agenticanalyticsnow.com/knowledge-base/evaluation-and-trust/) ## Weeks 9 to 11: Pilot with real users **Goal:** Put the agent in front of one team for real work, and learn from every correction. **Owners:** Domain owner, Agent owner, Analytics leader **Work** - Give access to one team in the chosen domain, with a named channel for reporting wrong answers. - Review corrections and refusals every week. Each correction becomes an item on the definition backlog. - Track cost per question and time to answer alongside accuracy. - Watch for workarounds: new extracts, copied tables, or questions routed around the agent. **Exit criteria** - [ ] Pilot users rely on answers for real decisions in the domain. - [ ] Corrections per week are falling, and each one has been resolved or logged. - [ ] Cost per question is known and fits the success measures. - [ ] No access incidents, confirmed from the audit trail. **Risks** - Users accept plausible wrong numbers because the answers read well. - Usage costs arrive higher than the trial suggested. - Teams outside the pilot build their own copies to get access sooner. **Read:** [Cost and latency](https://agenticanalyticsnow.com/knowledge-base/cost-and-latency/), [One copy, many readers](https://agenticanalyticsnow.com/knowledge-base/one-copy-many-readers/) ## Weeks 12 to 13: Decide and plan the next domain **Goal:** Make a written decision against the week 2 measures, and if the answer is expand, expand by domain. **Owners:** Analytics leader, Executive sponsor, Data platform lead **Work** - Compare results with the success measures written in week 2. - Decide to expand, extend the pilot, or stop, and write down why. - If expanding, choose the second domain and start its definitions work. Adding users to a domain that already works is a permissions change; adding a domain is a definitions project. - Move the question set into the change process so it runs whenever the model, prompts, or definitions change. - Retake the readiness assessment and compare it with the week 1 result. **Exit criteria** - [ ] A written decision, shared with the standing group and sponsor. - [ ] If expanding: the second domain, its owner, and its question set are named. - [ ] An operating runbook: who maintains definitions, who reviews corrections, who owns cost. **Risks** - Expansion by user count instead of by domain, which spreads the pilot’s definition gaps across more people. - Success declared on enthusiasm rather than the written measures. **Read:** [Rolling this out enterprise wide](https://agenticanalyticsnow.com/knowledge-base/enterprise-rollout/), [Enterprise AI agents (builder view)](https://agenticlakehouse.com/kb/enterprise-ai-agents/)