Better with Kent
Solo episodes from Kent C. Dodds on durable skills for people who ship software: judgment, accountability, problem clarity, and what stays valuable as AI takes on more implementation. Kent teaches directly on camera — no guest, one idea at a time. Complements guest interviews on Become a Product Engineer (Chats with Kent). Episode 1 adapts The Last Software Engineer; later episodes cover traps like building the wrong thing faster and skills like making user pain visible. Subscribe for evergreen episodes as the series grows.
Episodes
How to Put Your Codebase on Autopilot
I shipped 122 PRs in 24 hours straight out of my software factory, mostly while I was doing something else. Here's the system that lets agents file their own friction, make good PRs, catch their own mistakes, and keep the blast radius small.Here's what 122 PRs in one day looks like: https://github.com/kentcdodds/kody/releases/tag/v2026.10.11(00:00) - 122 PRs in 24 hours
(00:17) - Agent-fi
Steal My App (I'll Show You How)
Self-hosting Kody off Cloudflare used to sound thermonuclear. Deno Celld changed the math — and Kent's Grok bot handed the experiment to Devin. Then docker compose up actually worked.(00:00) - Cold open: Kody running in Docker
(00:10) - Better with Kent
(00:16) - Self-hosted Kody is real — here's the path
(00:58) - Ask: self-host Kody off Cloudflare
(01:10) - Clarify: Kody, not Jev
(01:42
Build a Software Pipeline: Help your agent help you
Package apps on Kody turn a package into something you can install and use on your phone. This episode walks morning briefing, package-app-kit, and a phone demo of a swipe deck over Gmail, GitHub, and Calendar.Better with Kent - durable skills for people who ship software.Thank you to Devin (Cognition) for sponsoring this episode: https://10xn.link/kcd-cognitionKent shows package apps on
Make your agent safe and autonomous
Gmail has no drafts-only OAuth scope. If an agent can draft, it can send. Two Kody locks make drafts-never-send actually true.(00:00) - Cold open: agent sent email without review
(00:52) - Better with Kent
(01:25) - PocketOS: overscoped token callback
(02:20) - Gmail has no drafts-only scope
(02:46) - Two locks: token + package
(03:40) - Elephant: your current Gmail plugin
(05:47) - Ask t
Introducing Kody: Your Personal Software Factory
You already paid an agent to figure it out. Tomorrow you ask again. Kody turns the good answer into a package you keep, so any agent can run it forever.(00:00) - You ask again
(00:22) - What if you only had to ask once?
(00:43) - A personal software factory
(01:05) - Then it keeps running
(01:25) - Still running
(01:50) - Not another agent
(02:06) - Secrets stay in Kody
(02:36) - Say it o
How Kody Gives Your Agents a Shared Home
You already pay for more than one agent. Give them a shared home so Cursor, Grok, and Devin share software, memories, and tasks instead of starting from zero every chat.(00:00) - Meet Kody
(00:22) - Better with Kent
(00:46) - How Kody works
(01:08) - Cursor asks what the bot shipped
(01:40) - Search, conversation ID, memories
(03:03) - Execute + secrets stay in Kody
(04:35) - Code mode: o
Turn your agent on auto-pilot with ADRs
New agent chats keep asking product questions you already answered. Write short ADRs so the next agent opens the no instead of making you the memory.(00:00) - Fill the agent's mind
(00:36) - Better with Kent
(00:46) - The problem: decisions die in chat
(02:06) - The solution is ADRs
(03:06) - Epic Stack + Remix origin
(03:32) - Template + AGENTS.md pointer
(04:21) - What to write ADRs abo
Here's how the new MCP spec works
MCP is stateless now. Any instance can answer a tool call. Kent walks the 2026-07-28 release: sticky sessions vs a normal load balancer, CIMD vs DCR, multi-round-trip elicitations, and how to run both lanes until the metrics say you can drop the old one.(00:00) - They fixed MCP
(01:13) - Better with Kent
(01:37) - Cloudflare + the dual-lane upgrade
(03:13) - MCP is now a stateless protoco
The craft "dying" is your OPPORTUNITY
People worry AI is destroying craft and making developers lazy. Kent says that is incomplete: most will hand judgment to the agent. The differentiators own the system, the UX, and what the agent learns to care about.(00:00) - AI is destroying the craft?
(00:22) - Humans were never deterministic
(01:17) - Judgment was always easy to outsource
(02:27) - Your opportunity
(04:21) - Ownership
Stop Burning Your Context Cash
A giant AGENTS.md feels responsible. It is often just burning tokens. Kent walks the Claude Code 80% cut, a research paper that found +20% cost for little gain, a live prune of his own file, and homework: make the always-on file a router, not an encyclopedia.(00:00) - Cold open: you're burning context dollars
(00:43) - Better with Kent intro
(00:59) - Claude Code cut 80% of the system pro
Use AI to make product decisions
Most people use agents to write code. Watch Kent use one to decide what to build: gather evidence, argue primitives, peel cleanup into side quests, keep the judgment - and only then type go.(00:00) - Cold open: I think we are aligned, so let's go
(00:05) - Better with Kent intro
(00:24) - The durable skill: making a product decision with your agent
(00:31) - Start at the top: hand the age
How to increase your leverage with agents
Agents are doing the work you did months ago. That is not doom - it is how abstraction travel works. Kent shows the climb-dont-cling timeline, a conductor-of-orchestrators example, and a one-week homework handoff.0:00 Cold open: agents take the job / you climb0:13 Better with Kent intro0:24 Tweet claim: agents do months-ago you-work0:51 Uncle Bob / climb layers of abstraction1:15 History:
I Delete Tests Every Night (On Purpose)
Better with Kent - durable skills for people who ship software.Every morning Kent wakes up to a PR that deletes more lines than it adds. Not flaky tests. Not broken tests. Low-signal ones — tiny wrappers, magic-number asserts, edge cases that will never happen — the kind AI agents love to generate overnight.This episode walks the trap (more green checks ≠ more confidence), the bar (fewer,
Forget "read the code," I don't even merge PRs myself
Your agent opened the PR. Now you're refreshing CI and arguing with bots. Kent shows the ship-pr skill that closes that loop - mark ready, fix CI, triage review, Discord handoff - so you spend attention on risk, not chores.
(00:00) - Still reading the code?
(01:18) - "I read the code" kicked off a war
(01:51) - I do read the code sometimes
(02:31) - You're the PR babysitter
(03:33) - I tu
Stop Reviewing Diffs. Start Reviewing Systems.
Agent PRs are too big to read line by line. Kent shows a visual system recap in the PR description - classify what changed as composes, extends, or adds - so you review the architecture first, then the code that matters.(00:00) - Still reviewing git diffs?
(00:25) - Spectrum: not every line, not zero review
(00:43) - Review the system, not just the diff
(00:51) - Steve's visual recap (Bui
My Agent Ships Across 6 Services Without Seeing a Secret
Want the system from this episode? Check out Kody at https://heykody.dev/
Kent replays a real publish night — one Cursor conversation where the agent drove Notion, Canva, Kit, Transistor, Bluesky, and LinkedIn through Kody packages, with every secret kept out of the agent's reach.
(00:00) - Stop copy-pasting between your agent and your services
(01:25) - What we're learning today
(01:49)
Fable nailed my production YOLO infra migration
One orchestrator prompt, six platform swaps, and a real production cutover on kentcdodds.com — the workflow, the review loop, the perf scare, and where the agents were wrong.(00:00) - One prompt, 40,000 lines
(00:44) - The site and why migrate
(06:38) - PR #813 — 483 files
(07:09) - Kickoff prompt anatomy
(11:35) - Orchestrate with subagents
(16:13) - Steering + scope expansion
(21:33) -
Your Coding Agent Needs Better Primitives
If your coding agent keeps producing garbage, better prompting may not fix it. Kent shows how intentional system primitives make agents more reliable, efficient, composable, and auditable.(00:00) - Bad agent output starts in the system
(00:37) - We are all tech leads now
(01:28) - What is a primitive?
(04:57) - Four moves: create, combine, delete, expand
(06:01) - Create: role-based acces
The Framework wars are over. Why no one dethroned React
Kent reacts to Dax's question on X — why no framework dethroned React — and connects it to Jobs Theory, network effects, and why framework choice matters less when agents write the code.Chapters00:00 — Why did nobody dethrone React?00:24 — Dax's question on X00:49 — React is the last UI library (2020)02:47 — Functional first, then social and emotional03:36 — What made React functionally b
What the devil is a Factory Engineer?!
Kent reacts to Zach Lloyd's Warp memo on "factory engineers" — where the software-factory vision is right, where it misses product context, and why factory work still comes back to users.Better with Kent — durable skills for people who ship software.Warp CEO Zach Lloyd told his team they are now factory engineers, not product engineers. Kent reads the memo aloud and pressure-tests the fra
I got attacked! - How I used my AI agent to fight back!
Kent walks through a real bot/crawler flood against kentcdodds.com, how agentic tooling helped diagnose and mitigate the outage, and what he changed so anonymous traffic is cheaper next time.Better with Kent — durable skills for people who ship software.Kent got a Sentry alert that kentcdodds.com was down. A bot or crawler flood had pushed his single Fly.io machine past its request limit,
I built my own OpenClaw
Kent shows how Kody gives the coding agent he already uses search, execute, and saved packages so exploratory workflows can become durable personal automation.(00:00) - Kody handled the demo
(00:41) - Why personal agents have not stuck
(02:21) - Search and execute
(04:31) - Kitchen glare walkthrough
(06:47) - Turning one action into a package
(08:48) - Scheduling deterministic workflows
(
Pragmatic Loop Engineering for AI Coding Agents
Kent shows how he closes agentic loops in real Cursor workflows: manual testing, PR review loops, Cursor Automations, and the stop conditions that keep humans in the right place.(00:00) - Loop engineering before the name
(00:11) - Boris on loops
(00:33) - Better with Kent
(01:01) - What the loop is
(02:59) - Tests were already a loop
(03:24) - Browser mode and manual testing
(05:35) - Hum
Stop Taking Tickets, Start Applying Jobs Theory
Kent walks Clay Christensen's jobs-to-be-done lens on a food-delivery shared-cart ticket — three questions that turn a solution into a job statement, plus Wayne Allan's Australia flop and Aaron D. Francis on deciphering feature requests.(00:00) - Your backlog is full of solutions
(01:27) - Jobs to Be Done
(03:12) - Shared cart ticket
(04:04) - When it goes wrong — Wayne
(06:01) - Three qu
How an AI Agent Deleted PocketOS Production in 9 Seconds
When an AI coding agent guessed its way through bad permissions and deleted months of PocketOS production data in nine seconds — and what durable skills would have stopped it.(00:00) - Cold open — car rental
(01:49) - Today's story
(10:29) - Railway recovery
(14:57) - Three questions
(16:29) - Close
Better with Kent — durable skills through story.Episode 3 is a cautionary tale: on April 2
How to Prioritize Software Tasks
Kent walks the Kano model on a real food-delivery backlog: Must-be, Performance, and Delighter — why GPS was a wow in 2015 and a basic today, and why you cannot delight your way out of broken basics.Chapters0:00 The backlog fight1:39 What type of feature is this?2:15 Basics (Must-be)3:47 Performance needs5:38 Delighters6:32 GPS lifecycle reveal7:56 Why silence misleads teams10:00 Cannot d
What Software Engineers Need in 2026
Kent maps the durable skills that stay valuable as agents take more implementation: clarity, judgment, empathy, feedback loops, systems thinking, agent fluency, and ownership — with practical homework for each cluster.(00:00) - Intro: Google stat and durable skills
(00:20) - Why now
(01:08) - Durable skills map
(01:25) - Clarity & judgment
(03:40) - Wayne Allan: build the right thing
Introducing Better with Kent
AI is accelerating change for software engineers. Kent introduces Better with Kent — solo episodes on durable skills, judgment, and knowing what to build — plus Chats with Kent guest interviews on Become an Epic Product Engineer.Better with Kent — Durable skills for people who ship software.The landscape is moving fast. Agents can implement more every month, which means the expensive mist
Recommended
Learn English B1 with Daily News | English Listening Practice
Talk About Talk - Executive & Leadership Communication Skills
English with Olivia | Slow Conversations & Vocabulary
Stand In The Circle
SLOW ENGLISH PODCAST (A1-A2) With Subtitles | Daily Videos | English With Us Podcast
Learn English A2 with Daily News | Simple English Listening Practice
پلی لیست | PlayList
Conspiracy Files with Paige Carter
Bad Friends
Learn 50 English Phrases While You Sleep | Everyday English Phrases & Vocabulary
This Past Weekend w/ Theo Von
Dateline NBC
