Three AI workflows for the modern product leader

Turns messy meeting notes, context docs, and a rough goal into a strategy document written for a read-and-react session — then pressure-tests it against a panel of top product thinkers before a human ever sees it. The value isn’t the prose; it’s the interrogation up front and the stress test at the end.

1. Intake — reads your notes, context, and one-line goal.
2. Clarify (before drafting) — asks the 4–6 questions that most change the doc.
3. Draft — one-pager or 3–5 page narrative, and tells you which it chose and why.
4. Clarify again — targets its own weakest claims.
5. Stress test — runs the draft past a panel (Lenny’s-archive analyzer) and revises.

- onboarding is broken; drop-off spikes at step 3
- competitor shipped a 2-min setup; we're at 11 min
- eng: identity check is the bottleneck, "can't remove" (compliance)
- rachel wants incremental; marcus wants a rewrite

GOAL: get the exec team to fund a 2-quarter onboarding rebuild

“The ask: fund a two-quarter onboarding rebuild.
The number that should scare us — 11 minutes to first
value, against a competitor now at two…”

Turns a strategy deck into a single self-contained HTML page: a Crawl → Walk → Run selector on top, and a split view where the strategy and a clickable prototype evolve together as you advance stages. A room stops debating bullet points and aligns on the actual experience. No publishing needed — it’s one file you open and screenshare.

strategy: servicing copilot
stages:
  crawl — suggested replies, human sends
  walk  — retrieval + next-best-action, human approves
  run   — autonomous resolution (low-risk), human oversight
constant: a human is always accountable

Pulls historical Jira data and answers two questions leaders lose sleep over: is our time aligned to our stated priorities, and where are the early-warning hotspots (rising WIP, reopens, churn). It interviews you before and after seeing the data, so the dashboard serves a decision instead of dumping charts.

1. Interview first — what decision, which 3–5 priorities, what counts as a hotspot.
2. Pull — epics, points, labels, cycle time, reopens, WIP by team.
3. Interview again — surfaces what’s measurable and what’s surprising, then confirms the cuts.
4. Dashboard — effort-vs-intent, flagged hotspots, and a “so what / do this” narrative.

decision: quarterly reallocation review
priorities:  1) fraud  2) onboarding  3) mobile parity
hotspot = reopens rising OR WIP climbing 3+ weeks
audience: my leadership team (anonymized teams)

EFFORT vs INTENT (story points)
  fraud ........... 41%
  mobile parity ... 22%
  onboarding ...... 9%   ← priority #2, effort #4
  unmapped ........ 28%

HOTSPOT
  Team Atlas · reopen rate 3.1× median · WIP up 4 wks