Free, weekly
Field notes from building with agents.
Newsletter
Never miss a Drop
Get every MEGA Drop first: deep-dive articles, working repos, agent skills, and tools you can plug into your setup the same day.
Free, every artifact included. Unsubscribe anytime.
Model pricing isn't reliable anymore
Model families keep multiplying and provider prices keep changing. Choosing the right one for a real task takes more than a single glance at the price tag.
Olaf Sulich · Oct 19, 2026 · 8 min read
#agents#models#pricing
Agents shouldn't live on your laptop anymore
Build a remote home for coding agents with an always-on VPS, Tailscale, Herdr, Pi, and Moshi, then control the same sessions from any device.
Olaf Sulich · Oct 19, 2026 · 5 min read
#agents#pi#infrastructure
Accessible web for humans and agents
We've made a better web for humans. Semantic HTML, alt text, and captions help agents read and act, too. Treat agents as a new kind of user.
Olaf Sulich · Oct 14, 2026 · 6 min read
#agents#accessibility#web
Rethinking AI with Jev
John Lindquist's October 8 MEGA livestream on Jev: a fast, cheap decision model that picks from a menu you wrote and returns a score your code can act on.
John Lindquist · Oct 8, 2026 · 6 min read
#agents#models#workflows
Whole products can now be prompts
Theo Browne on the MEGA podcast: features and whole products can now be prompts or markdown files, and the engineering that still has to stay software.
Theo Browne · Oct 5, 2026 · 5 min read
#agents#product#workflows
How Kent Ships Features Without Reading the Code
Kent C. Dodds' real delivery loop on his own SaaS: fifteen principles for shipping agent-written code you haven't read, with the full session recording.
Kent C. Dodds · Oct 1, 2026 · 6 min read
#product#verification#agents#workflows
We're system designers now
Angie Jones on the MEGA podcast: typing code may be solved, and the job that remains is designing the system agents can run without you in the middle.
Angie Jones · Sep 24, 2026 · 4 min read
Towards Autonomous Product Development
Language models got smarter, but they still lack our context. Shape the environment so agents can work without us: always on, in the cloud, with real limits.
Adam Gospodarczyk · Sep 8, 2026 · 13 min read
#agents#automation#product
Your reasoning effort level is too high
Every model now comes with a reasoning dial. Higher settings give the model more room to think, but choosing the right level is less obvious than it looks.
Olaf Sulich · Aug 27, 2026 · 4 min read
#agents#models#reasoning
AI Changed Programming. But How?
AI changed more than how we write code. Packages, cloud agents, durable context, and bounded autonomy shift programming toward shaping reliable environments.
Adam Gospodarczyk · Aug 27, 2026 · 6 min read
#agents#automation#workflows#programming
Don't make the agent remember how to do its job
How Pi and Kody turn exploratory agent work into a tested package with remote runtime, durable state, and a schedule that keeps running after the laptop closes.
Olaf Sulich · Aug 27, 2026 · 6 min read
#agents#pi#kody#automation#testing
It's time: the work changed
The four short opening tutorials from MEGA's August 25 live: Angie, John, Kent, and Theo on autonomy, images, primitives, and prompting the whole outcome.
Aug 27, 2026 · 7 min read
I was wrong about MCPs
I treated MCPs as service connectors. The useful shift is a capability layer: search, execute, and reusable primitives an agent can compose on its own.
Adam Gospodarczyk · Aug 20, 2026 · 11 min read
#agents#mcp
From Visual Editors to an Agentic-First Web
What moving 924 pages from Webflow to Astro unlocked: an agentic-first website, connected documentation, and publishing workflows that go beyond the visual editor.
Adam Gospodarczyk · Aug 19, 2026 · 8 min read
#agents#migration
