mbriggs (@mbriggs) header
mbriggs (@mbriggs) profile picture

My first name is a random set of numbers and letters and other alphanumerics that changes hourly forever

Montreal
Joined December 2007
Photo by mbriggs (@mbriggs)Photo by mbriggs (@mbriggs)Photo by mbriggs (@mbriggs)Photo by mbriggs (@mbriggs)Photo by mbriggs (@mbriggs)Photo by mbriggs (@mbriggs)Photo by mbriggs (@mbriggs)Photo by mbriggs (@mbriggs)Photo by mbriggs (@mbriggs)Photo by mbriggs (@mbriggs)
Principles of successful "factory" building 1. Don't build a factory, don't think of it as a factory, don't say the word "factory". It's a bad analogy and it puts the emphasis and goals at the wrong parts. Just erase that from your head. You are building focused automations, and getting compounding value from them. 2. Go slow, don't skip steps. If you start feeling a lack of control, that means its time to slow down, and reorient. You should have high confidence, trust, and be deriving value each step of the way. The only way to maintain your ability to judge is to go extremely incrementally. 3. Focus on verification before any other automation. This doesn't mean create-verification-skill from @poteto (although that is excellent and you should check it out), it means taking a step back and thinking about all the ways you could be confident your app works, and getting those into a good spot. For example, the first goal should be a skill that is able to generate unit tests to the point that you are happy with them. If you aren't happy, change the skill, regenerate. Move on, generate another set of unit tests. Rinse and repeat till you build confidence, take bigger swings. Your first milestone is getting to the first atom of verification, which is a test suite you could confidently regenerate if you needed to. 4. Verification (in the broadest sense of the word) is your lever to building trust. This includes your type system, your linter, your architectural choices, infrastructure, test environments and isolation, benchmarking, and automated agent runs. Probably more stuff then that. Focus on automating building that to world class levels. Verification is an easier problem to solve reliably then "all programming work", so start by solving for that. As that gets better, trust will go up. If you can get to the point where "verification passes means my app is functional" you are in the promised land. You wont get there, but that is what you are aiming for. 5. Only trust what is trustworthy. Don't start by saying "i want to fart out an idea and have the agent build it for me" that is the end of the road. Start with something like "when an exception is caught in prod, and the fix is easy, fix it automatically". Start at the edges, as you build trust you can build on top of that. The devil is in the details, but this is my mental model of basically what has been figured out so far. Caveat emptor, I am not sitting at the pinnacle of the mountain and sharing my wisdom, it is largely based on conversations with people I trust further along then me, reading the tea leaves, and matching that to my own experience of successes and failures. Also, we're in a world right now that is changing month over month, I feel like I am trying to articulate current thinking, but the rules could all change tomorrow.
12
1
4
89
6,580
Hot damn I’m seeing first-hand how AI makes non-developers build production software: The personal trainer at my gym has been talking for 3+ years about building a scheduling + workout app one day. Nontechnical. He now has his app!! GitHub + Cloudflare BE&DB + Resend. All built with Claude They guy spent 3 months on it, and has not slept as much as before since getting hooked on building software with AI
220
56
33
1,779
118,948
I'm thinking the duo folio is the way to go if you rarely use the front screen (aka the correct way to be a duo enjoyer)
19
Why aren't custom keybinds a normal part of ADEs?
44
Weird how half the internet seems to have gone down this week due to every major tech company botching server upgrades
1
1
325
mbriggs retweeted
Rewrite it in Rust stopped being a meme the day it started costing $60
13
10
414
12,702
Rex demo time: magical and automatic remote copy/paste, drag/drop, and port forwarding (e.g. open web servers running on remote machines in your local browser). Plus, showcasing some of the internal plumbing that powers this and how you can hook into it with Lua scripting. Our goal with Superlogical and Rex is for everything to feel local. I've said before: the moment any UI shows a selector between "local" and "cloud", the product has failed. The lines should blur, and we should build the foundational technology that makes it happen performantly, securely, and beautifully.
192
208
98
3,918
276,805
Hot take: your AI workflow matters way less than the thing you're building. We've all burned more time tuning the setup than it would've taken to ship. Stop sharpening the axe. Cut the tree.
2
1
1
13
562
The iPhone Duo is not a phone, its an iPad mini you can fold in half and talk into. If that makes you be like "Oh wow, cool, now I don't need a phone!" you are in the target demographic. If you are like "But don't you miss having a phone?" you are not.
1
182
mbriggs retweeted
the problem with markdown is that agents write it as data and read it as code
93
79
19
1,796
110,850
mbriggs retweeted
software factories feel like a temporary problem. the models will learn to build them for you the more interesting question to me is how to build a workspace where agents can collaborate with you
583
336
184
7,498
546,214
Building software in the land of the Agentic can feel foreign, just remember, if you're tempted to encode everything in Markdown, you're going to have a bad time. Instead adopt the upside-down pyramid where your codebase is the loudest voice. h/t @poteto
2
1
1
8
350
The best agent orchestrator is a well rested, fully caffeinated human brain.
AI workflows are the 'what IDE do you use' of the agentic era. Fun to compare, but they barely matter. The model is what matters. Everything else is cope.
2
1
13
411
I don't usually do these, but damn this was fun
2
1
3
132
Realizing just how many people on X are running very markdown heavy complex workflows still. I strongly believe at this point that AI workflows for the most part are unnecessary at this point. The place you need to think that way still is automation, but even automation is so much easier in the opus 5.5 era. If you feel like I am calling you out, maybe just try and see how it goes. If I am wrong I am wrong, but it is always valuable to experiment with baseline and update your priors.
48
mbriggs retweeted
you'll never see anyone on our team evangelizing their ai workflows all we care about are the outputs showing off how fancy the inputs are is useless especially when 99% of the magic is coming from the model
120
82
25
2,439
95,239
i genuinely think a lot of people are struggling to cope with their job being completely wiped out and the software factory and custom harness pushes are ways for them to justify continuing to have large engineering teams. The software factory is actually a factory that produces WORK. > They need to validate each step in the software factory. > More component based systems > Constant maintenance Meanwhile everything the software factory creates can be prompted by a non-dev & QA'd & then cleaned up by a dev in a day. All done at the same speed or marginally slower than the software factory if you don't include the cost of initial setup and maintenance. If you include the maintenance cost, software factory is clearly a cost center. Not saying that any abstractions and automations are bad, just saying what I'm seeing out there when I talk to different companies. It feels like a lot of engineers are just scrambling to justify their roles instead of just enjoying the wave.
bro AI is solving millennium math problems and you think you need a "software factory" to build a crud app
39
5
8
186
31,899
I feel like I am also going to be getting the Duo 2 😬 But this thing feels freeing for development the way that laptops felt freeing when they got good / popular in dev jobs, hard to put a price on it nitter.gq/MacRumors/status/21220…
Apple Aiming to Upgrade the iPhone Duo in Four Ways macrumors.com/2026/11/15/app…
56
its find to let your agent compact
1
3
467
Stuff I think generally considered a bad idea now that was considered a good idea at the start of the year - ralph loops / deterministic orchestration - elaborate agents.md files - prompt engineering generally / cot prompting - context engineering - spec driven development - planning mode / files - tdd - handoffs - pretty much any markdown files
76
17
7
530
83,927
I didn't realize claude code sessions could talk until they started doing it one day. You can put the session name in your statusline pretty easily, once you have session names you can ask some sessions to coordinate with other sessions on work by name
4
5
467