@kentcdodds: It's time to stop doing that
Summary
A live event featuring talks by Theo Browne, Angie Jones, Kent C. Dodds, and John Lindquist on integrating AI agents into software development workflows, with sessions on autonomy, designing with AI, and practical prompting.
View Cached Full Text
Cached at: 08/25/26, 12:08 PM
It’s time to stop doing that https://t.co/EhmTvmAPb2
It’s Time: The Work Changed [MEGA.dev LIVE] · Luma
Source: https://luma.com/mega-its-time?tk=z80Od9 A year ago you could still debate whether AI belonged in serious software. That debate is over. Agents write real code, run real tasks, and break in real ways - and most of us are improvising our way through it alone.
Four people who aren’t improvising are comparing notes, in public, for 90 minutes. These are the sections each of them walks through on screen:
**Theo Browne**(t3.gg)-Thinking bigger
- Surviving the slop-ocalipse.
- “Prompting bigger” (end to end demos).
- Experimenting and pushing your limits.
- Keeping your environment flexible.
**Angie Jones**-Building for Autonomy
- Better models and wider adoption are not enough to make engineering autonomous.
- Agents need context, access, and feedback from the systems around them.
- Teams can give agents more independence without giving up control.
**Kent C. Dodds****- Thinking in Primitives**: How to make your agents produce better results with looser specs
- What is a primitive?
- How do you design primitives?
- How do you make sure your agents use your primitives?
**John Lindquist**(egghead.io)
- Designing with AI(easily prompting for image batches, establishing themes, locking in storybooks).
- Prompting with Videos(How to dictate and annotate).
- Tight Iteration Loops(Making sure compiles/tests/apis/etc aren’t slowing down your goals).
Then all four together, live, for 30 minutes of Q&A. Bring the questions you’ve been solving alone at midnight.
**Who it’s for:**developers already working with AI agents who suspect they’re using 10% of what their tools can do.
The plan: Four sessions: Theo → Angie → Kent → John Live Q&A with all four Done. Back to shipping.
Free. Recorded for registrants.
Waiting for the event? Check out what your agent thinks about you and get your first MEGA card: 👉https://mega.dev
Similar Articles
@kentcdodds: I'm live now talking about @kodykoala!
Kent C Dodds announces a live talk about Kody, an AI tool, discussing its development, agentic loops, and integrations with Cursor and Sentry.
@techwith_ram: https://x.com/techwith_ram/status/2064925285003542820
Explores the shift from human-in-the-loop to autonomous agent loops in AI coding, where agents self-prompt and iterate, discussing both the promise and the hidden costs of reduced human control.
@kentcdodds: Thrilled to have been able to spend 45 minutes talking with @unclebobmartin about software architecture, AI coding agen…
Kent C. Dodds announces a 45-minute podcast conversation with Robert C. Martin (Uncle Bob) about software architecture, AI coding agents, and product engineering.
@kentcdodds: This is the sort of prompt I can give my agent because I have @kodykoala. We're removing a feature with a month sunset …
Kent C. Dodds describes using an AI agent tool called Kody to schedule a wake-up call for feature sunset, demonstrating the utility of AI agents in development workflows.
@deployengineer: https://x.com/deployengineer/status/2071803742996115597
Notes from day 1 of the aiDotEngineer conference featuring Kent Dodds' talk on product engineering in the AI world. Covers core thesis that product judgment is the last skill needed when AI commoditizes implementation, the Arrow Metaphor, differentiation between product engineer and product manager, validation techniques like The Mom Test, Jobs-to-Be-Done Framework, Kano Model for prioritizing features, and user feedback loops.