iiinova — where your digital self keeps evolving

Kyle @kylestratis.com · 28/09/2026

My physical copy of AI Agents with MCP showed up...it's real! You can order the ebook now, and the print edition should be shipping soon, with pre-orders open. Over 330 pages on the Model Context Protocol, up to date with the July spec rewrite and Python SDK v2. kylestratis.com/books/ai-ag...

A super handsome guy holds AI Agents with MCP in Harvard Bookstore, a bookstore that doesn't actually carry the book.

0193

Reposted by Kyle

Simon Späti 🏔️ @ssp.sh · 27/09/2026

Picasso would not have bothered to start a painting if he knew the outcome. That line stuck with me while sitting near a beach in Italy, writing without knowing where it leads. www.ssp.sh/blog/on-cre...

ssp.sh

The Act and the Outcome of Creation

A reflection on why we create: for joy, for flow, for others, and for the self. On creation as a gift with no strings attached and success beyond outcomes.

151

Kyle @kylestratis.com · 23/09/2026

This wraps up a few problems: publish or perish for those who want to stay in academia and papers being an antiquated medium of knowledge communication. These issues predate LLMs, but they're accelerating it for sure.

111

Kyle @kylestratis.com · 23/09/2026

I can tell you right now the correct answers are: Meet Pointe Drive By Pies Athan's (although I really need to try Arwa it looks so good)

000

Reposted by Kyle

Eugene Vinitsky 🍒 @eugenevinitsky.bsky.social · 18/09/2026

Weird request; we've had a fairly big breakthrough that we've been mostly keeping a lid on for the past year. We're looking to talk to some science / AI writers about this and I know a lot of y'all are out here on bsky...

815732

Kyle @kylestratis.com · 17/09/2026

I started building MCP clients and servers when the docs were almost non-existent and every answer lived in the spec, source, or a GitHub issue. I thought that sucked, so I wrote a book about it. AI Agents with MCP is available now (as an ebook, the dead tree version should be out in a few weeks)

kylestratis.com

AI Agents with MCP — Model Context Protocol for Building Clients, Services, and End-to-End Agents

Anthropic released the Model Context Protocol at the end of 2024, and it quickly became the standard way to turn a chatbot into an agent that can act, plan, and use tools on its own. This book goes …

1112

Kyle @kylestratis.com · 15/09/2026

Got my @aaif.io MCP-A exam results back: 96/100. This means that writing an entire book on the subject works for passing the exam, but I don't recommend it. Read the book instead, then sign up for the 120-question, 120 minute in-depth exam and still breeze through it with your newfound expertise.

kylestratis.com

AI Agents with MCP — Model Context Protocol for Building Clients, Services, and End-to-End Agents

020

Kyle @kylestratis.com · 10/09/2026

Got the cover proof and QC2 for AI Agents with MCP and now I’m getting really excited! Can’t wait to share it with everyone. @joereis.bsky.social’s and @aparker.io’s quotes on the back look especially good :D

030

Reposted by Kyle

Hendrik Mans @hmans.dev · 07/09/2026

Hashing things out with an LLM works not because the LLM magically has all the answers, but because this process forces you to structure and reflect on your thoughts in a way that helps you find the answer yourself. Software developers worth their salt know this as "rubber ducking"

516118

Reposted by Kyle

Mike Caulfield @mikecaulfield.bsky.social · 05/09/2026

The key skills people are going to need to use LLMs effectively are around evaluation and verification. I think many people see that as "Oh, so I have to be the LLM's copy editor now" but this is because most people don't understand evaluation and verification in any systemic way.

911716

Kyle @kylestratis.com · 03/09/2026

At @martinfowler.com's site, a great piece by Rachel Laycock on how agentic development has changed the code review process and how we can get the things we used code review for (hint: not finding bugs) by rethinking our process

martinfowler.com

Maybe We Shouldn't Be Reviewing All This Code

Or, perhaps the problem isn't that AI has broken code review, maybe it’s that we've been using code review to solve the wrong problems

120

Kyle @kylestratis.com · 27/08/2026

MCP just had its biggest rewrite. I joined ODSC’s AI X Podcast to talk through statelessness, designing tools agents can actually use, agent skills, what the changes mean for people building with the protocol, and how fun it is writing a book on a rapidly changing protocol. Listen here:

linktr.ee

ODSC AI Official Music - Listen to songs on Soundcloud | Check for Videos on Linktree

View odsc’s Linktree to discover and stream music from top platforms like Soundcloud here. Your next favorite track is just a click away!

210

Kyle @kylestratis.com · 20/08/2026

My recharge time is ending, which means my books are opening back up: 15-20 hours a week this fall. Agent builds, the evals that show you where they break, cloud infrastructure, and custom MCP workshops. Message me or book a consult: stratisdatalabs.com

stratisdatalabs.com

Stratis Data Labs

Stratis Data Labs is an AI, data engineering, and cloud engineering consultancy

000

Kyle @kylestratis.com · 12/08/2026

Now that the book is mostly done, The Signal Path is back! In it, we talk about the new awkward teenage phase of agents: MCP’s enterprise-focused overhaul, @scoiattolo.mountainherder.xyz’s article on best practices on using agents, and stories of agents getting too big for their sandboxes.

thesignalpath.xyz

Coming Up for Air

It's been a while, hasn't it? I've been incredibly busy, juggling my part-time work, a string of big enterprise contracts (Koch's Principle Companion, a new learning agent for Microsoft, and an MCP wo...

040

Kyle @kylestratis.com · 28/07/2026

The MCP 2026-07-28 spec is final today, and v2 of the Python SDK has shipped with it. Congrats to the spec maintainers, SEP authors, and SDK teams - so much hard work went into maturing the protocol, and the SDK folks ran an epic marathon to keep everything in sync with the spec.

120

Reposted by Kyle

dan @danabra.mov · 30/06/2026

i want to spread the word about atproto. if you’re running a podcast, i’d be happy to hop in to talk about it. i understand it decently well and can explain it without much jargon. it’s one of the most interesting developments in the last 30 years of web, and i can defend that. please dm to set up!

3745455

Kyle @kylestratis.com · 03/06/2026

Thanks to @sequoia.pub my blog is now on the ATProto! Do I do the Ghost newsletter next?

030

Kyle @kylestratis.com · 19/05/2026

One of the things I've been heads down on lately has been this AI companion for the book Becoming a Principle-Driven Leader by Charles and Chase Koch. I got to work on some interesting problems, develop techniques based on modern andragogy research, and deploy a multiagent system to the public.

linkedin.com

Chase Koch on the Principles Companion App that Tribe AI Built | Tribe AI

Most AI is being built to think for you. This one was built to elevate your thinking. Koch, Inc. asked Tribe a different question than the one most companies are asking: could AI develop human judgme...

000

Kyle @kylestratis.com · 02/05/2026

I should be more active on this account, maybe when I’m not spending all my waking hours writing

010

Kyle @kylestratis.com · 03/03/2026

What I think is the most important chapter of AI Agents with Model Context Protocol (MCP), and most difficult to research and write, is now available in early release. In chapter 7, you'll learn how to test, secure, and distribute your MCP servers.

111

Kyle @kylestratis.com · 01/02/2026

I've finished the first draft of chapter 7 of AI Agents with MCP, which you should be able to see on @oreilly.bsky.social's learning platform either later this month or in March. Before edits, I've written just over 69,000 words, made 22 images, made ~227 physical pages (est), w/ 2 chapters to go

111

Reposted by Kyle

Ed @ed3d.net · 27/01/2026

Code has never been worth much of anything by itself, though. patio11’s advice has been true my entire career. Companies aren’t going to stop needing the product cycle. They might need fewer people whose entire world is the computer, but the practice of making computers do stuff will persist.

kalzumeus.com

Don't Call Yourself A Programmer, And Other Career Advice | Kalzumeus Software

141

Reposted by Kyle

Steve Klabnik @steveklabnik.com · 27/01/2026

i think the biggest issue where i split ethically in a meaningful way with people is that i have long been against intellectual property as a concept. i think IP helps disney, not small artists. a lot of people want to strengthen IP in response to ai stuff and i just don't think that's a good thing

5244

Kyle @kylestratis.com · 22/01/2026

This bout of mania (not really) also got me to write a new issue of The Signal Path, where I talk about the recent explosion in usage patterns for agent coding, memory agents like @void.comind.network, agent orchestration, and goings-on in the MCP world, including chapter 6 of my book going into ER

thesignalpath.xyz

How to Wrangle Claude Code, New MCP Book Chapters, Agent Orchestration and More

I'm finally emerging (kind of) from the haze of the holidays, surgery recovery, and the entire household getting the flu with a bevy of news for you. We drove from Boston to Florida for the holidays t...

120

Kyle @kylestratis.com · 22/01/2026

The image of him fearfully at his door as a disgusting ice pig looms over him is heart rending and enraging.

051

Kyle @kylestratis.com · 22/01/2026

I wrote up an internal guide to Claude Code use, then I cleaned it up and made it public. It's wicked long, but use the TOC and use it more as a reference library than a singular article, and I think it should be really helpful!

kylestratis.com

A Better Practices Guide to Using Claude Code

A comprehensive guide to getting the most out of Claude Code

1191

Kyle @kylestratis.com · 21/01/2026

A Better Practices Guide to Using Claude Code A comprehensive guide to getting the most out of Claude Code

kylestratis.com

A Better Practices Guide to Using Claude Code

A comprehensive guide to getting the most out of Claude Code

010

Reposted by Kyle

Ed @ed3d.net · 15/01/2026

Just got everything lined up to release `ed3d-plugins`, the Claude Code harness I use in my day-to-day. While they're yelling about gas towns, I present an e-bike, just don't drive it on the sidewalk. I'm biased, but I think it's good. I've tried a few similar, and I keep going back.

github.com

GitHub - ed3dai/ed3d-plugins

Contribute to ed3dai/ed3d-plugins development by creating an account on GitHub.

912419

Kyle @kylestratis.com · 14/01/2026

It's Early Release Day! AI Agents with MCP just had a major release, with additional details added to all existing chapters, as well as the addition of Chapter 6, which covers advanced techniques for building MCP servers.

120

Kyle @kylestratis.com · 24/12/2025

I’ve started doing this with simple games for my daughter. It’s really fun and I can quickly spin up simple educational word games at her level based on what she likes.

040

Kyle @kylestratis.com · 14/12/2025

I got inspired by @simonwillison.net's simple HTML tool workflow: simonwillison.net/2025/Dec/10/... So I decided to spend a few minutes today to do something similar: tools.kylestratis.com

simonwillison.net

Useful patterns for building HTML tools

I’ve started using the term HTML tools to refer to HTML applications that I’ve been building which combine HTML, JavaScript, and CSS in a single file and use them to …

080

Reposted by Kyle

Nicole Hennig @nic221.bsky.social · 16/11/2025

Empire of AI is wildly misleading on AI water use - Andy Masley andymasley.substack.com/p/empire-of-ai… (worth reading the details) #AI #water

andymasley.substack.com

Empire of AI is wildly misleading on AI water use

I discovered at least one major error that gets a number off by 3 orders of magnitude

1142

Kyle @kylestratis.com · 16/11/2025

Just presented this! You can check out the code here: (note: the layout is screwy and config options don't get shown, but not bad for coding by voice while out and about and not even looking at the results until around midnight). No code was actually touched by me. github.com/kylestratis/...

github.com

GitHub - kylestratis/vibedialer: A completely vibe coded Wardialer for the Practical Data Discord vibecoding hackathon

A completely vibe coded Wardialer for the Practical Data Discord vibecoding hackathon - kylestratis/vibedialer

041

Kyle @kylestratis.com · 15/11/2025

I have a toddler birthday party right now, and an adult birthday party at a brewery this afternoon, so I’m participating in @joereis.bsky.social’s Practical Data Discord vibe coding hackathon purely via mobile using Wispr Flow and @anthropic.com’s Claude Code web. This is wild.

130

Kyle @kylestratis.com · 09/11/2025

Apparently I’ve been consulting full(ish) time for a year now. I’ll have to write some thoughts on it soon but I still can’t see myself doing anything else (despite taking a halftime role with a client because I love what they’re building)

010

Kyle @kylestratis.com · 05/11/2025

So apparently you *can* listen for notifications in the MCP SDK - both in servers and it looks like in clients too. I haven't tested the latter yet, but you better believe this is going in the book!

000

Reposted by Kyle

mr. TIM @timkellogg.me · 04/11/2025

MCP Colors A riff off of the lethal trifecta for addressing prompt injection, this is a simple heuristic to ensure security at runtime red = untrusted content blue = potentially critical actions An agent can't be allowed to do both timkellogg.me/blog/2025/11...

timkellogg.me

MCP Colors: Systematically deal with prompt injection risk

3324

Kyle @kylestratis.com · 30/10/2025

Time to just sit through a panic attack while I wait for my first real workshop to start 🙃

120

Kyle @kylestratis.com · 28/10/2025

This weekend, I set out to answer an ages-old (10 days, to be exact) question: what are Claude Skills and will they replace MCP?

360

Kyle @kylestratis.com · 28/10/2025

Paying the Bills (or not) with Claude Skills My impressions of Claude Skills after building an MCP server with one.

kylestratis.com

Paying the Bills (or not) with Claude Skills

My impressions of Claude Skills after building an MCP server with one.

000