Matt Dailey (@reactiverobot) header
Matt Dailey (@reactiverobot) profile picture

Building https://www.teapawt.org/t.co/BC77CBJ2Gm, previously @figma & @PalantirTech

San Francisco, CA
Joined June 2015
Today, we're announcing @ref_tools open beta. Ref is your team’s shared space to decide what agents build before any code gets written. We’ve raised $4M from @villageglobal, @Daybreak_Fund, @tmrohan, @RitualVC, @tonigemayel @barrald @wesmckinn and @bentossell. Every engineering team is battling the same problem. I call it Velocity Sickness. It's the disconcerting feeling that you're moving fast but not having the impact you expect. It's affecting individuals, teams and especially leaders. It looks like: - Too many PRs to merge. - Brainfry and burnout. - Engineers running in different directions. - Critical decisions being made by agents. The last one is the most dangerous. At its core, software engineering is about two things: (1) what decisions matter for my system? and (2) making those decisions. When you let agents make critical decisions, you lose ownership of your system and product. You solve these problems with Ref. Learn more: ref.tools/blog/ai-broke-code…
44
25
15
179
268,696
i have a very Berkeley, techno-waldorf view on balancing family life and founder grindset. i'm not great at it (ask my wife lol) but i'm trying I want to raise helpful kids that turn into humans that want to help others. To do that, I need to actually let them help me with the things I care about the mental game is accepting that some of the things that could be really fast are going ot take way longer because I'm going to ask for help from my kids for example, my 4yo is learning letters and i work from home so my last few prompts of the day are often typed by her
Hill I'll die on: it is entirely possible to be a great entrepreneur & even greater parent/partner. When I built my first company, I had a Mount Rushmore of entrepreneurs that I looked up to. It included the usual suspects. I was in awe of what they achieved professionally. The hopeless entrepreneurial romantic in me aspired to be have the garage insight to IPO story that united most of them. But then I looked at their personal life, and it was largely...concerning. Divorce. Infidelity. Absent parenting. I wasn't willing to make the good founder-bad familyman tradeoff, but I didn't see any examples of founders that had shown you can have your cake & eat it too. This became my new north star as a 2nd time entrepreneur. Prove to myself (and others) that it's possible to be an A+ familyman & businessman. And in doing so, achieve two things: 1) As @JoshuaKushner says "[...] be excited to go to work and excited to go home." 2) Provide a roadmap for younger founders to "have it all." While the journey isn't over, I have several insights in my pursuit of filling all cups: 1) It entirely possible to be great at both. 10% of the time things feel like feng shui. 90% of the time you feel an imbalance and are trying to make adjustments to get back to equilibrium. 2) It is absolutely easier for me as a second-time founder to construct myself in a way that I can have the best of both worlds than it was as a first-time founder. Recognizing that privilege is important. 3) If I ever feel like I am being a shitty partner/parent and there's no solution/end in sight, I will drop literally every professional endeavor & get my #1 priority (family) in order. 4) Strong communication with your life & business partner are the foundation for this entire thing to work. 5) I make sure that I get to do wake-up, morning walk, and bedtime with my wife, daughter, and dog unless there are extenuating circumstances. 6) The opportunity cost of my time has never been higher. Not because of my business success. But because every minute i'm spending at work is a minute i'm not spending with my family. I'll continue to share how I'm approaching my new career mission, but I'm also so encouraged that folks like @mttgrmm, @marcrandolph, and others are painting a picture for crushing work & life.
1
3
280
i love model releases bc they reminds me to ask "what if...?"
1
171
this is my design process (plus "give me 5 variants")
ok claude, take screenshots of my whole app and use the mcp to put them into my tldraw-notes. I'll review on my ipad, make some annotations and comments, and let you know when I'm done
1
54
3,377
Matt Dailey retweeted
One of the most fun parts of building @ref_tools is experimenting with ways we collaborate internally. AI-native teams should be asking fundamental questions about who meets, how often and when.
its fun figuring out how to make agents work together but we still need to talk about how the humans work together
1
3
216
its fun figuring out how to make agents work together but we still need to talk about how the humans work together
6
3
1
11
1,075
Matt Dailey retweeted
true, malleable multiplayer is hard
12
2
2
123
15,530
this is already happening in a lot of places and coming to you soon the only thing i'd add is that this task queue will live in a dynamic, malleable surface that agents mold to best explain their work to busy humans
I predict in 2-3 years SWEs will no longer directly use coding agents. It doesn’t make sense to have several engineers individually commanding agents to work on a stream of tasks. The future will be a shared task queue for elastic agent swarms that SWEs write and prepare evals for - but it will be minimal and expanded by agents into more robust versions. Pricing will shift to CICD style pricing in addition to token costs to accommodate virtual machines. Most tasks in the queue will originate automatically from logs and failed evals. Remember QA automation engineering? That’s all that’s left for us albeit with prompts and evals.
2
1
3
386
We built Ref to solve exactly this problem for ourselves: an easy to read, shareable surface to work in with your teammates + their agents. We each wanted to use our own agent config (cloud vs. local; Claude, Codex, Cursor, etc), but also wanted to see all of the context of our teammates' agents, and be able to hand them off to each other as needed. The doc abstraction has been way better for collaborative velocity than viewing individual chat threads.
in 9 days my team and I are homeless looking for an alternative to conductor cloud My requirements are: - uses codex and claude subs - runs in the cloud with local bridge - support team multiplayer so we can handoff and query each others threads
5
4
2
13
1,465
Ref has a one-line install to get up and running with your setup (including ACP support, and an MCP app) Give it a try, and let me know what you think. We're a bunch of builders working on the fastest way to build the right thing, together ref.tools
1
124
this is super cool! And, unfortunately, explains why i prefer using claude/codex via mcp rather than the built-in agent i'm sure the fine-tuned edit model is much better at point edits like "add a button here" but I just don't do point editing anymore. I still use Figma for capturing, organizing and iterating on big ideas. Looking forward to when they get to models for that!
1
6
623
this is beautiful. i think of these as "level 2" ui my agents are doing so much complex work and some small fraction of the time i need to visualize that complexity to understand it but most of the time i want level 1 ui: a button that says "ship this" and i don't see any of this detail
Generative UI #2 - Merge conflicts 🚫 ✨
1
7
813
Ref September Update You don't need to visit github․com anymore. 👀 Review diffs next to the ref. ✅ Approve a ref and forward that approval to PRs. Also, bundle size ⬇️ and cache hits ⬆️ so everything is way faster!
6
595
this is what a ref is it's the notebook of everything you've done to explore and solve a problem. it's easy to share with your team
it's basically impossible for someone to just "show you their prompt" now, because everything is about references, skills and examples I often ask my agent to look at 3 other repos I've made first, search the web for references, use other AI APIs, etc.
2
9
952
this is the fundamental ai content problem: if you spend a lot of time looking at decks, its easy to tell which ones are thoughtless if you rarely engage with slide decks, the ai generated ones will look amazing with zero thought the timeline is full of it in every medium (design, slides, games, video etc) if your audience is at all sophisticated in the medium you're producing, you can't skip thinking
please stop sending me your ai-generated decks. they smell like total lack of thought
162
I'm changing how i review my teammate's work (code or plan) it used to be i'd mostly read, react and throw out questions to start discussion and prompt the owner's research. I was a good collaborator by identifying problems or nudging in better direction now it's the opposite. If i'm leaving comments and pulling your agents out of flow, the comments deserve more weight. Gone are the days of "did you consider <X> approach?". The barrier to answering that myself is now so low that I owe you better the goal is still not to gatekeep or take ownership of my teammates work. the bar for a good review is simply higher now that I can research, riff and test with a prompt
2
399
the designers+machines meetup last night was so good (s/o @ben_issen) i go to a lot of ai meetups and the vibe was noticeably different than most. it was cheerful and creative and curious if you're in SF and like design and ai you should try to get in on the next one
2
7
537