🧭
Reading for Product
Direction and intent when execution gets cheap.
The New Ways of Working7 posts
How the job itself is changing.
- 01 · The New Caste System: Who's Drowning in Agentic Dev — and Where the Life Rafts Are A new caste system is forming around agentic AI. It has nothing to do with talent and everything to do with fluency. Here is the ladder — and how to climb it before the cheap-token party ends.
- 02 · Upgrade Your Workflow Working with agents isn't a faster version of the old job — it's a different operating system. Here are the six meta-skills that run on it, and the series that unpacks each one.
- 03 · Voice-Driven Dictation You can talk roughly three times faster than you type, and your agents don't care which one you use. Here's why voice is a first-class input to an agentic workflow — and where it's still genuinely clumsy.
- 04 · Loops The one-shot prompt is the training wheels of agentic work. The real leverage is the standing loop — a job that runs on an interval or runs until a condition is met, working while you don't.
- 05 · Code the Interface, Delegate the Implementation The interface is intent made precise and verifiable. The implementation is the cheap, fungible part now. Here's the working pattern: you write the contract, the agent fills in the body.
- 06 · When Agents Take Over the Office The migration from organic intelligence to AI feels like a threat because we keep framing it as replacement. It's a promotion — here's how to make the transition painless and free up the part of your brain that's worth paying for.
- 07 · Ambition → Intention → Execution Every built thing travels the same path: from wanting it, to specifying it, to making it. Agentic development didn't change the path — it changed which step is scarce. Execution got cheap. Intention became the whole job.
Leadership in the Agentic Era7 posts
Leading teams + orgs through the shift.
- 01 · Acquiring Talent in the Age of AI The interview became an open-book exam and everyone brought the book. Companies are responding by trying to catch the AI — banning tools, dragging candidates back on-site. They're solving the wrong problem. The job changed; the test didn't.
- 02 · Leveraged Time You learned to code by getting fast at one instrument, heads-down, single-threaded. That skill is now the trap. The unlock is putting the violin down and picking up the baton — spreading your will across a team of agents instead of spending your hours.
- 03 · Lean on the Tools Conduct ten agents and you stop being the soloist — you become the bottleneck. Not your typing. Your review capacity. The fix isn't reviewing harder; it's letting specs, evals, and tests take the first pass so your judgment lands only where it's needed.
- 04 · Measure the Right Thing Story points, velocity, tickets closed — those instruments were built to measure the one thing that just got cheap. In an agentic world they don't just miss the point. They actively point the wrong way.
- 05 · The Incongruent Org A team doesn't climb the stack all at once. When half of it conducts agents while half still plays solo — and dev races ahead of product — the org doesn't just slow down. It tears along the seam where intent runs out.
- 06 · Leading the Change You can't org-chart your way through this. Leading the agentic shift is empathy first, foundation second, language third — in that exact order. Skip the first and you lose people; skip the second and you scale chaos; skip the third and no one can reason together.
- 07 · Mandate, Then Get Out of the Way You can't tell people to trust these tools — trust is earned by using them, and the payoff is back-loaded, so people quit before the reps land. The fix is a forcing function: mandate the reps, coach hard, then take the whip away.
Agentic Foundations4 posts
The on-ramp — read this first.
- 01 · Terms I Need to Know The whole catalog leans on a handful of words and assumes you already have them. This is the on-ramp's on-ramp — an opinionated field guide to the vocabulary you need before the rest of the series lands.
- 02 · What Agentic Development Actually Is Everyone says 'agentic' and nobody defines it. Here's the line that actually separates it from chat, copilot, and autocomplete — the agent takes multi-step action, in a loop, against a goal you set.
- 03 · Context Is King Every post in this series leans on one word and never defines it: context. It's not the setting for the work — it's the medium. Here's what a context window actually is, and the four moves that separate engineers who get structured output from ones who get slop.
- 05 · Don't Just Give Your LLM Tools — Give It Systems A tool bolts one capability onto one agent for one session. A system teaches every agent you'll ever connect. Here's the difference, and why the vault — not the tool list — is the real leverage.
PCMS2 posts
Personal context management, systematized.
- 01 · Your AI Doesn't Know You: The Case for a Personal Context Management System LLMs are powerful but context-blind by default. A PCMS — your notes, daily logs, and projects, structured so an AI can read them — is the real leverage in an AI-first world.
- 02 · The PCMS Manifesto: Building a Personal Context Management System Why Personal Knowledge Management Systems fall short in the age of AI agents — and how a Personal Context Management System built on Obsidian, Qdrant, and Supabase changes everything.