Engineering Leadership Coach. Builder at @fairlyfantastic. (If you golf, please try @18Recap.) Founder x 5, Emmy winner. Always hacking. Anti-racist.
Austin, TX
Joined August 2007
- Tweets11.2K
- Following3.9K
- Followers3.7K
- Likes9.8K
Brian Dainton retweeted
Impeccable 3.7 brings linting to design.
Until now it was a skill you asked for help. Now it's a design-system-aware feedback loop that runs while your agent builds, catching slop and design drift before they land.
🪝 Design hooks for Claude, Codex, and Cursor
They run after every UI edit and quietly nudge your agent to fix slop and drift. The output isn't another wall of lint: it separates new findings from already-seen ones, flags clean scans, and asks the agent to use judgment. Fix real issues, leave intentional demos alone, save exceptions to config instead of littering your source.
🎨 Slop detection is now project-aware
Reads your actual design system from DESIGN.md, your typography, palette, radius scale, and tokens, and flags drift from your system, not just generic AI slop:
• this font isn't in your design system
• this color is outside your documented palette
• this radius doesn't match your rounded scale
The same engine powers both the hooks and the CLI, and it's where we're investing next.
🖥️ Live Mode, ready for real projects
Svelte/SvelteKit now preview variants as temporary framework components with live params, then accept cleanly back into your source component. Manual text edits got evidence / apply / discard routes, insertions preserve their anchors, and mapped lists and JSX slots clean up far more reliably.
⚡ Leaner core, sharper detector
Rule-level evals across 3 providers and 4 niches cut guidance with no measurable lift and dropped examples that taught models bad patterns. The detector now skips hidden and screen-reader-only elements, understands OKLCH alpha and Sass-like inputs, and tightened checks for repeated kickers, oversized H1s, clipped overflow, and cramped padding.
🛠️ CLI caught up
impeccable detect loads DESIGN.md by default, motion findings name the exact token or cubic-bezier instead of just "bounce," and impeccable ignores gives real CRUD for exceptions. Hooks and CLI share the same ignores. No split-brain config. Plus a much-improved interactive installer with hooks setup built in.
Upgrade:
npx impeccable install
npm i -g impeccable
Brian Dainton retweeted
I built "zero2claude", a free course that takes people from zero terminal experience to shipping with Claude Code.
The curriculum goes from absolute zero → software basics → Claude Code fundamentals → advanced usage. No shortcuts, no assumptions.
17,000+ students. 7 languages. ~500 active hourly.
No marketing. No ads. Pure word of mouth.
The entire platform? Built and operated by one person
with Claude Code.
Lighthouse audit:
✅ Performance : 96
✅ Accessibility : 100
✅ Best Practices : 100
✅ SEO : 100
Production stats:
~6.4M requests/day. 74 req/sec sustained. <0.003% error rate.
Claude Code doesn't just write code. It builds production-grade, scalable products.
The best way to grow Claude Code adoption isn't to simplify the tool. It's to level up the people. Give fishing rods, not fish.
Free. No paywall. My contribution to the community.
Link in the comments 👇
Brian Dainton retweeted
Personal update: I've joined Anthropic. I think the next few years at the frontier of LLMs will be especially formative. I am very excited to join the team here and get back to R&D. I remain deeply passionate about education and plan to resume my work on it in time.
Brian Dainton retweeted
Joined a new AI-native company this week and it’s kind of wild how different it feels already.
The laptop arrived, I logged in, and an agent basically took over from there. It set up my dev env, pulled repos, fixed dependency issues, got permissions approved, pointed me at the backlog, linked the architecture docs, and surfaced the Slack debates I actually needed to read before touching production.
When I needed context on something, I asked the agent and it found the exact thread from months ago explaining why a decision was made, who owned it, the related Linear issues, and the PRs connected to it.
I’ve only been here 3 days but it honestly feels like I’ve worked here for a year because the usual friction and scavenger hunt for context just isn’t there anymore.
We should probably stop calling this “onboarding” and rename it to “mounting” because this feels a lot more like mounting a distributed filesystem called “institutional memory” than slowly getting drip-fed context over 6 months.
I've been saying for a while that apprenticeship is the path forward for junior engineers in this new landscape, but, holy smokes, @tobi has taken it to a new level at Shopify. I love love love this.
Brian Dainton retweeted
Grocery is a $1.5T domestic market — bigger than restaurants, bigger than hotels. But it's running on technology from the Reagan administration.
We just raised a $22M Series B for @VoriHQ to make every supermarket in America autonomous.
Brian Dainton retweeted
OpenClaw is the fastest-growing open source project, but there are no stories of running it safely in production at scale. As we started deploying agents internally at @brexHQ, we couldn’t stop thinking about this question.
Agents work, but nobody wants to give them real credentials. Instead of waiting for a solution to emerge, we decided to try a novel approach: using LLMs to judge the network traffic of an AI agent.
Today we’re announcing CrabTrap, an open-source proxy that intercepts every outbound request and blocks risky activity using LLMs, before it ever hits an external API. The results are promising; we believe it’s a meaningful step forward in the security of agent harnesses in production environments.
Try it out today.
(As a side note, it was really fun to work personally on a real systems problem again. And btw, if you want to work at a place where the CEO is building proxies at night, we’re hiring!)
Woohoo! Absolutely killer update from the @warpdotdev team. LFG 👏
Brian Dainton retweeted
The more enterprises I talk to about AI agent transformation, the more it’s clear that there is going to be a new type of role in most enterprises going forward. The job is to be the agent deployer and manager in teams. Here’s the rough JD:
This person will need to figure out what are the highest leverage set of workflows on a team are (either existing or new ones) where agents can actually drive significantly more value for the team and company.
In general, it’s going to be in areas where if you threw compute (in the form of agents) at a task you could either execute it 100X faster or do it 100X more times than before. Examples would be processing orders of magnitude more leads to hand them off to reps with extra customer signal, automating a contracting review and intake process, streamlining a client onboarding process to reduce as many straps as possible, setting up knowledge bases than the whole company taps into, and so on.
This person’s job is to figure out what the future state workflow needs to look like to drive this new form of automation, and how to connect up the various existing or new systems in such a way that this can be fulfilled. The gnarly part of the work is mapping structured and unstructured data flows, figuring out the ideal workflow, getting the agent the context it needs to do the work properly, figuring out where the human interfaces with the agent and at what steps, manages evals and reviews after any major model or data change, and runs and manages the agents on an ongoing basis tracking KPIs, and so on.
The person must be good at mapping the process and understanding where the value could be unlocked and be relatively technical, and has full autonomy to connect up business systems and drive automation. This means they’re comfortable with skills, MCP, CLIs, and so on, and the company believes it’s safe for them to do so. But also great operationally and at business.
It may be an existing person repositioned, or a totally net new person in the company. There will likely need to be one or more of these people on every team, so it’s not a centralized role per se. It may rile up into IT or an AI team, or live in the function and just have checkpoints with a central function.
This would also be a fantastic job for next gen hires who are leaning into AI, and are technical, to be able to go into. And for anyone concerned about engineers in the future, this will be an obvious area for these skills as well.
Another 🙌 for the @cloudflare workers platform: the CF API and the API MCP on top of it.
Today: "duplicate this long WAF rule across all my zones".
Done in seconds. 🎉
"Radical humility and endless paranoia are the only product strategies that make sense right now"
What a fricking quote.
"PR >> PRD"
Yep. the handoff era is over. but it's not just the roles collapsing. it's the tools.
Every PM tool was built for a world where humans did the coordination.
tickets
docs
roadmaps
presentations
all of that was scaffolding for work AI now does faster and cheaper. slapping AI on top doesn't fix it. The foundation is already out of date.
I build @chatprd every day knowing i have to replace its core before something else does: claude code, another startup, something i haven't imagined yet.
Radical humility and endless paranoia are the only product strategies that make sense right now.
So sure. the PRD is dead.
But I'll kill it before you do.
The big gap I see: context is not direction.
A world model that reveals and routes information in real time solves a genuinely hard problem, but it leaves some others wide open: prioritization in a fog of ambiguity, accountability without hierarchy, and knowing where the model ends and human judgment begins.
(Said differently: who decides, who's accountable, and how do you earn the credibility to be that person when there's no title doing it for you?)
Excited to see how this evolves (and try it myself!).
our lead independent director @roelofbotha and i wrote about the history of organizational structures, and our intent to rebuild block as a mini-AGI. xitter.cf/jack/status/2039003879…
There is no better guide than Claire. Snap snap.
I’ve spent at least 100 hours setting up, training, and working with @openclaw
Read the docs. Peeked into the source code. Edited config files by hand. Walked friends though their setup.
Then, I wrote down everything I know.
Here it is: The Ultimate 0 > 🦞 Guide
ty ty to @lennysan @nateliason @davemorin @steipete @lindsmccallum @elawless for early feedback.
gl hf snap snap 🦞lennysnewsletter.com/p/openc…
Man, a lot of competitive harnesses are gonna get a lot better today.
Brian Dainton retweeted
Claude code source code has been leaked via a map file in their npm registry!
Code: pub-aea8527898604c1bbb12468b…
Brian Dainton retweeted
I’ve found myself explaining LLMs to more and more friends and family.
One component I’ve been covering a lot lately is model weights.
If you aren’t totally clear on what these are, here’s a simple(ish) overview - no calculus knowledge required.
A “what the heck are model weights” 🧵
Is Claude Code /remote-control Super flaky for anyone else? Got several CC sessions running (all start w RC enabled) on a caffeinated box at home, but on my phone, not all sessions appear, the ones that do show as idle, and trying to send messages is just met with a spinner.
WOW. Quite probably the best interview I've ever watched. Long, yes, but holy smokes, it's SO chock full of gold nuggets. Thanks to both of you.
My conversation with Tobi Lütke (@tobi), co-founder and CEO of Shopify.
0:00 Companies as Social Technology
5:27 The Value of Reading Books: Cheat Codes for Life
7:28 Post-IPO Crisis: Cosplaying as a CEO
7:54 Competition vs Rivalry: The Power of Healthy Competition
16:02 COVID as a Turning Point: Rebuilding the Executive Team
18:21 Hiring Founders: Building a Team of High-Agency People
26:49 Shopify OS: Engineering the Company from First Principles
36:48 Compensation Innovation: Giving Employees Full Agency
40:41 The Psychology of Identity and Affirmations
48:43 Differentiation Over Perfection: Making It Your Own
50:31 Context Podcast: Documenting Decision-Making
1:26:36 The IPO Decision: Going Against Silicon Valley Orthodoxy
1:35:08 Building a Company Worth Working For
1:41:50 Hiring for Spikiness: Finding Non-Conformists
1:48:28 Office Design Philosophy: Creating Space for Excellence
1:58:54 Video Games as Business Training: StarCraft Lessons
2:07:06 AI Revolution: 2026 and Beyond
2:11:44 Focus on Craft: The Unquantifiable Elements of Excellence
2:21:08 Survivorship Bias: The Importance of Entrepreneurial Exposure
2:23:22 Closing
Includes paid partnerships.
Respect this and the Every team's thinking, but I'd flip the order: architect first, pirate second.
Set the constraints (routes, API boundaries, repo separation, lib/component usage), THEN vibe code inside them. Speed without slop.
The architect shouldn't be the cleanup crew. The architect sets the bones: the boundaries, the patterns, the foundation. Not a full blueprint for every feature; just enough structure to ensure that the pirates/builders are coloring inside the lines.
I like to assume builders have architectural competency, but honestly that might be the hardest thing to hire for, and maybe why you're advocating for a separate role. For founders, you have to be both. As teams grow, I could see it becoming a real specialization.
new model for engineering team structure in 2026:
2 people only
one pirate and one architect
the pirate's job is to move as fast as possible to develop valuable, shipped product features by vibe coding.
the architect's job is to turn the product surface discovered by the pirate into a reliable, structured machine—also by vibe coding, but at a slower, more well-reasoned pace.
every product needs a pirate but most product's only need an architect once they some form of PMF, and in that case they usually don't need one full-time. architects can work across many codebases and solve interesting technical challenges. pirates go hard on a product that they own end-to-end.