“we've just started pulling off the shelf like Treasure Island.”
Treasure Island
By Robert Louis Stevenson
1 recommend/use · 1 sourced episode
Every sourced reference
Short attributed excerpts only. Timestamps are approximate.
Related frameworks
Diagnose Agent Failure as Structural, Not Stupidity
When an agent does the wrong thing, check its context, tools, and scope — not its intelligence.
Make the End User Feel Like a Winner
Design agents that don't just do tasks — they make the user look good and feel like a winner.
One Agent Per Lane
Beat context overload by running many narrow, purpose-built agents instead of one do-everything agent.
Pull the Thread on New Tools
Judge a new AI tool by where it'll be in a week or a month, not where it is on day one.
Ramble-Mode Onboarding
Onboard an AI agent by voice-rambling everything you need, not by wiring up APIs and structured fields.
Solve the Problem Behind the Problem
When an agent can't do a task, escalate API-to-browser, then reframe to the underlying need it can solve.
The Hire-an-Agent Onboarding Model
Set up an AI agent exactly like you'd onboard a human EA: own identity, delegated access, earned trust.
People in these episodes
Related resources
- 1Password
- Alice's Adventures in Wonderland
- Apple Watch
- BotFather
- Brave Search
- Buffer
- ChatPRD
- Chrome
- Claude
- Claude Code
- Claude Cowork
- Codex
- DeepWiki
- Eight Sleep
- Exa
- Gamma
- Google Workspace
- Homebrew
- Hoop Analytics
- How I AI
- iTerm
- Lenny's Newsletter
- Lenny's Podcast
- Lenny's Product Pass
- Linear
- Mac mini
- Maven
- Mercury
- Omni
- OpenClaw
- Orkes Conductor
- Oura Ring
- Replit
- Telegram
Spot an error or want this page removed? Request a correction or removal.