//pragmatic leaders

Library

Choose a complete program, follow a goal-led path, or begin with one focused course.

23 learning options
1032 lessons

Programs

Build a capability end to end, in a deliberate sequence.

Harness Engineering

Ship agent systems with loops, tools, memory, evals, orchestration, and production recovery.

5 courses44 lessonsopen track
  1. 01The Agent Loop — what's actually running when an agent "works for hours"8 lessons
  2. 02Tool & Memory Design — when the agent's effective IQ depends on its toolbelt7 lessons
  3. 03Eval Harnesses — how you know your agent isn't lying to itself9 lessons
  4. 04Multi-Agent Orchestration — fan-out, swarms, and the cost of doing both badly9 lessons
  5. 05Production Harnesses — observability, recovery, the bill11 lessons

Learning paths

Follow the most useful lessons, cases, and practice for one goal.

AI for Product Builders

A 2026-era curriculum for PMs and product builders who need to design, ship, and judge AI-powered products — built around the twelve-chapter AI Manual spine. Decide whether AI is the right answer, pick the smallest model that clears the bar, spec the prompt, gate on evals, design for uncertainty, and own cost, latency, and safety as first-class product constraints.

ai role route8 weeks8 stagesView path

AI Judgment for Engineers Making Product Decisions

A seven-week path for engineers, ML practitioners, and technical founders who can build the AI feature but now have to make the product call. Learn to choose the right problem, pick the smallest model that clears the bar, write the prompt like a spec, evaluate against user value, and brief leadership on cost, latency, and safety in plain English.

engineering route7 weeks7 stagesView path

AI Strategic Briefing for Functional Leaders

A four-week path for functional leaders who now own an AI-touched surface and need to brief a board, a CEO, or a customer without slipping into either hype or paralysis. It is built for the operator who will not pick the model or write the prompt, but will absolutely own the strategic frame, the economics story, the safety posture, and the few irreversible calls underneath them.

leadership route4 weeks6 stagesView path

Designing AI UX That Survives Reality

A six-week path for designers now owning AI surfaces, where deterministic interaction instincts are no longer enough. It gives you a practical vocabulary for uncertainty, a pattern library for streaming/citations/confidence/recovery, and a way to design for hallucination as a permanent product condition. Built for teams who need to ship trustworthy AI UX without waiting to become ML experts.

design route6 weeks6 stagesView path

Interview Prep for PMs

A four-week path for mid-to-senior PMs targeting FAANG, unicorns, and Series C+ companies — structured answers, worked examples, and real practice reps.

interview sprint4 weeks6 stagesView path

Learning to Learn in the AI Step-Change

For anyone whiplashed by influencer cycles and unsure what to learn next. This path builds the metacognition and epistemic-hygiene skills that let you pick the compounding AI skills and ignore the churn — and it gives you a personal learning operating system that holds up across every model cycle.

learning system6 weeks6 stagesView path

Ship Your First AI Product (Founder Track)

A six-week sprint for founders, solopreneurs, and indie hackers who need to ship a real AI feature fast, not talk about one. The path moves from customer pain to model choice, prompt spec, evals, and failure-tolerant UX so you can launch this week and learn from live users instead of demos.

builder route6 weeks6 stagesView path

The Customer-Facing PM

A six-week path for PMs and CSMs stepping into B2B roles where they own retention, expansion, and the customer relationship alongside the product.

customer-facing route6 weeks6 stagesView path

Courses

Learn one practical capability without committing to a full program.

BOOM Modeling

Turn fuzzy product intent into a buildable object model and artifact set.

framework5 lessonsView course

Pricing Tactics

Choose and defend a pricing move under uncertainty.

strategy5 lessonsView course

Metacognition

Build a personal learning filter for AI and product skill changes.

judgmentintermediate5h8 lessonsView course

Reading the AI Discourse

Read AI claims without getting pushed around by launch theater.

judgmentintermediate4h4 lessonsView course

Model Selection and Evals

Select the smallest viable model and design evals tied to user value.

focused buildintermediate6h8 lessonsView course

Prompt as Spec

Write prompts as executable product specifications instead of vibes.

focused buildintermediate5h7 lessonsView course

Agent Loop Anatomy

Explain what is actually running when an agent works for hours.

focused buildintermediate5h8 lessonsView course

Tool and Memory Design

Design tool and memory surfaces that raise agent reliability.

focused buildintermediate6h7 lessonsView course

Eval Harnesses for Agents

Build eval harnesses that catch agent failure before users do.

focused buildintermediate6h9 lessonsView course

Multi-Agent Orchestration

Decide when multiple agents multiply capability and when they add tax.

focused buildadvanced6h9 lessonsView course

Production Harnesses

Plan observability, recovery, and cost controls for production agent systems.

focused buildadvanced7h11 lessonsView course

Career Fit and Transition

Map role fit, company fit, and career tradeoffs before committing.

planned refresh21 lessonsView course