AI practice

Official · updated Nov 4, 2026 · v1.0.1

Maps one customer or team workflow, FDE style: shadowing questions, a swimlane of steps with time and pain, data, exceptions, where AI fits, and a pilot.

When to use it

• You're about to sit with a team to find where AI can help
• A team wants 'AI for X' and nobody has mapped X

What you give it

• The workflow's start and end
• 2 to 3 people who do the work
• Example inputs and outputs

What you get

Discovery notes with a swimlane table, data and exceptions, an AI-fit table, one success metric, and a pilot proposal.

Changelog

• v1.0.1 · Nov 4, 2026 · Example: the observation notes now give the 30 seconds to open and save each invoice, the 2 minutes to write the buyer email, the clerk's own word on tedium and typos, and the bank details on invoices, so every figure in the swimlane comes from the input; the scanned-image exception says only what the notes say (harder to read).
• v1.0.0 · Nov 4, 2026 · First release.

Sources

1. Trading Margin for Moat: Why the Forward Deployed Engineer Is the Hottest Job in Startups - a16z (2026-11-04)
2. Contextual Inquiry: Inspire Design by Observing and Interviewing Users in Their Context - NN/G (2026-11-04)
3. Building effective AI agents - Anthropic (2026-11-04)

Related skills

• AI automation opportunity scan Scores a team's recurring tasks on frequency, time, rule clarity, and risk to find AI candidates, then picks the top 3 with a first experiment each.
• SOP from an explanation or recording Turns an explanation or screen-recording transcript into an SOP with a trigger, roles, exact-label steps, decision points, checks, and an owner.
• Customer onboarding plan Builds an onboarding plan for a new customer: success criteria in their terms, milestones to first value with owners, a kickoff agenda, cadence, and risks.
• Eval set for an AI task Builds a 20-to-50-case eval set for an AI task: normal, edge, and adversarial cases, expected results or rubrics, pass criteria, and a re-run routine.

← All skills