which metric? which denominator?scorecard? ROI? root cause?+19% or +11%?Getting the right insights from your data takes expertise. Watch Omar pick a playbook, press Run and get the answer read the right way, with last quarter’s run there to compare.
60 seconds
Each playbook packages how Milestone measures AI in engineering: the questions to ask, the data to pull, the metrics and denominators that hold up, and the traps that change a conclusion. It is built from the questions engineering leaders ask Milestone most and the analyses that answered them best.
Nine playbooks, one for each big question about AI spend, AI impact, performance and your own usage. Pick one, set the scope and window, press Run. The prior period comes from the window, and the self-check knows who you are.
Because the method is fixed, a playbook comes out the same way on every run: same playbook, same parameters, same data, same figures, verdict and sections. Every run is kept as it was, so this quarter’s report sits next to last quarter’s.
Spend, model efficiency, throughput impact and waste for a single developer, ending in a budget call.
Cost per PR, tokens not landing in code, and model efficiency against the prior period.
How a developer, team or group works with coding agents: tools, compaction, delegation, model mix and outlier sessions, against fixed thresholds.
Adoption, throughput, delivery, cost and quality against the prior equivalent period.
Before/after or period-over-period impact, normalized per developer, written for a named audience.
Adoption per group on the right denominator, who is not adopting, and whether gaps are closing.
Per-member metrics against the BU median, with anomalies, trend and PTO adjustment.
Finds the long tail, classifies where time is lost, and ranks the fixes.
Your own usage tier, adoption, spend and delivery against your team median.
Which playbooks you see follows your role, the same as AI Chat.
A playbook runs the analysis an expert would run for that question. It already knows the right metrics, definitions, denominators and exclusions, and it lays out the answer first. You pick it, set the scope and press Run. Asking the assistant works well for one-off questions; for the ones that matter, the playbook brings the method.
From Milestone. Each playbook is built on Milestone’s know-how in measuring AI in engineering: the questions engineering leaders ask most and the analyses that answer them best. Milestone maintains every playbook, and every report shows the method it used.
No. A prompt library gives you someone’s words. A playbook gives you Milestone’s method: a vetted analysis with guardrails, metric definitions, a fixed set of sections and a saved run. You never write or see a prompt.
Same playbook, same parameters, same data: the same figures, verdict and sections. Refresh with today’s data and you get a new run, saved beside the original, so you can compare.
Yes. “Ask about this report” opens AI Chat with the report attached. The report stays as it is. To change what it’s built on, adjust the scope or window and re-run.
Access follows the user, the same as AI Chat. A run can’t show anyone data the product wouldn’t show them. Runs are private to the person who ran them, and you can export a report to take it with you.
Not in this release. Each playbook uses Milestone’s standard definitions and shows them before you run. For a different cut, ask in AI Chat with the report attached.
If you use Milestone, Playbooks are already in your assistant: Playbooks in the left nav, or “Run a playbook” on the assistant home. Which playbooks you see follows your role.
Book a demo. We’ll run a playbook on a sample org with you, from the gallery to the export.