Lenny's Reads

A framework for prioritizing AI agent projects by architecture, not vague impact scores. A three-category taxonomy that separates deterministic automation, reasoning agents, and multi-agent networks. Practical signals for when to move from scripted workflows to LLM-driven decision making. Tool and metric guidance for choosing platforms and measuring success.

A cartoonist shares a pep talk with 12 visual steps to break free from creative paralysis. Topics include embracing embarrassment, using charts as recovery tools, and stopping overplanning to just start. Practical tactics cover breathwork, smart caffeine use, treating failed ideas as seeds, and recognizing progress so you keep moving forward.

A deep dive into using OpenClaw to run multiple autonomous AI agents. Practical setup choices from Mac Mini to VPS and hosted options. Six ready-to-copy workflows and a full nine-agent team blueprint. Integrations, maintenance tips, cost and security trade-offs for running powerful personal AI tooling.

A biannual check-in on the product job market with data-backed trends. PM openings are at a three-year high while engineering demand accelerates. Recruiter roles are surging, hinting at renewed hiring momentum. AI-specific jobs are skyrocketing and shifting role mixes. Design openings have flattened as PM demand overtakes design in several markets.

A designer turns a podcast transcript archive into a Pokémon-style trivia RPG. He walks through a six-step, AI-driven workflow from sketch to shipped game. Tools, pivots between frameworks, automated transcript processing, quiz generation, avatar art, audio sourcing, and realtime leaderboards are all discussed.

A deep dive into advanced B2B positioning tactics. They outline the five building blocks of strong positioning and the four roadblocks teams commonly hit. Hear why different teams see competitors differently and how to reframe competition from a prospect's view. Practical fixes for product pessimism and tips to tie unique capabilities to real buyer value.

A diagnostic model for fixing underperforming teams without defaulting to blame. A boat analogy that recommends checking surface systems before diving into individual faults. Clear steps covering structure, team dynamics, interpersonal tensions, and when to make decisive personnel calls. Tips on why self-preservation often drives behavior in broken environments.

They explore how AI can predict interview questions and mine your hidden stories. You hear about building AI workflows that give line-by-line feedback and mock interview drills. The Claude-based coach’s tools get covered, from interviewer profiles to timed practice and post-interview scripts. Practical setup steps and ways to stop sounding generic are also highlighted.

They dig into why AI analysis can sound confident but invents quotes and generic themes. You hear four common failure modes that break AI insights and practical fixes for each. The conversation compares major LLMs and which one performs best for deep analysis. Practical prompt and verification techniques for getting grounded, verifiable outputs are highlighted.

A practical ritual for surfacing AI failure modes before users do. Techniques include forcing models to be wrong, probing ambiguity, and stress-testing to find first breakpoints. Discussion of defining minimum viable quality with three thresholds and five context factors that shift quality expectations. Advice on estimating per-call cost early and building simple guardrails to protect user trust.