Voozh

dex

6,231 posts

dex

@dexhorthy

building the post-IDE IDE at humanlayer.com - @aitinkerers sf lead, prev @replicatedhq @SproutSocial @nasa - ai that works pod @ hlyr.dev/aitw

San Francisco, CA

Joined January 2017

Pinned
👁 user avatar
dex
@dexhorthy
6h
At HumanLayer, we’re on a mission to solve the AI slop code problem. In 2025 we open-sourced our Research, Plan, Implement framework, now deployed inside fortune 500s like Block and Uber - places where shipping slop is just not an option And that was just the beginning. Today,
👁 Image
00:00
👁 user avatar
dex
@dexhorthy
Apr 24, 2017
Deployed my blog on Kubernetes
👁 Image
👁 user avatar
dex
@dexhorthy
Jun 10, 2025
its so cute that claude suggests a 6 week timeline as if i'm not gonna make you fix this all in the next 2 hours
👁 Image
👁 user avatar
dex
@dexhorthy
Apr 18, 2025
may have hit a nerve here...it all started with trying to understand how production AI systems actually work FOLKS - I've tried every agent framework out there and talked to many strong founders building impressive things with AI BUT I was surprised to find that most successful
👁 Image
👁 Image
👁 Image
👁 Image
👁 user avatar
dex
@dexhorthy
Nov 4, 2025
there's a new concept I'm seeing emerging in AI Agents (especially coding agents), which I'll call "harness engineering" - applying context engineering principles to how you use an existing agent Context engineering -> how context (long or short, agentic or not) is passed to an
👁 Image
👁 user avatar
dex
@dexhorthy
Jul 29, 2025
as had been true for over a year, if you’re using subagents to play house and anthropomorphize roles, you’re hosed. Claude subagents are context management + prompt shortcuts. That is all. That is all you need. If you wield them right they are incredibly powerful. There are
👁 user avatar
dex
@dexhorthy
Oct 16, 2025
superthread of every resource I have published about advanced claude code usage, research-plan-implement, and advanced context engineering for coding agents 👇 (mostly chronological)
👁 Image
👁 user avatar
dex
@dexhorthy
Sep 20, 2025
Wow looks familiar 🤔
👁 user avatar
eric zakariasson
👁 Cursor
@ericzakariasson
Sep 20, 2025
until this is native in product (which is soon), here's an approach you can take to implement the pattern of research, plan and implement
👁 Image
👁 user avatar
dex
@dexhorthy
Jun 22, 2025
todo list in @claude_code has more metadata than you think, incl priorities! AND you can build a custom renderer if you use stream-json format 🙂
👁 Image
👁 user avatar
dex
@dexhorthy
Sep 23, 2025
excellent conversation on HN today on how to get AI to be productive in large codebases - come share your experiences, debate approaches, call the whole thing a scam, whatever gets you going 😀
👁 Image
👁 user avatar
dex
@dexhorthy
Aug 27, 2025
Context7 is so freaking well engineered in terms of token efficiency for your model
👁 user avatar
dex
@dexhorthy
Jun 12, 2025
Everything is context engineering
👁 Image
👁 user avatar
Walden
👁 Cognition
@walden_yan
Jun 12, 2025
I see a lot of people make the same mistakes building agents. So we shared a few of the principles we use cognition.ai/blog/dont-buil…
👁 user avatar
dex
@dexhorthy
Sep 26, 2025
excellent post on MCP vs. CLI
👁 Image
👁 user avatar
dex
@dexhorthy
Sep 19, 2025
kinda unhinged that none of the agent frameworks that were hot a year ago are used in any of the top coding agents and now @opencode @CodebuffAI @claude_code are all adding agent-framework-y things... at sprout we used to call this "refactor AFTER patterns emerge". its a good

URL: https://x.com/dexhorthy

⇱ dex (@dexhorthy) / X