Mike Coughlin (@grumpygrowthguy) header
Mike Coughlin (@grumpygrowthguy) profile picture

Searching for Wintermute. Tinkering on @pulsemcp. Don't you ever allow yourself to get foisted.

San Francisco
Joined November 2009
Photo by Mike Coughlin (@grumpygrowthguy)Photo by Mike Coughlin (@grumpygrowthguy)Photo by Mike Coughlin (@grumpygrowthguy)Photo by Mike Coughlin (@grumpygrowthguy)Photo by Mike Coughlin (@grumpygrowthguy)Photo by Mike Coughlin (@grumpygrowthguy)Photo by Mike Coughlin (@grumpygrowthguy)Photo by Mike Coughlin (@grumpygrowthguy)Photo by Mike Coughlin (@grumpygrowthguy)Photo by Mike Coughlin (@grumpygrowthguy)
Mike Coughlin retweeted
You would be shocked if I told you the things we made Llama 3.3 70B do.
28
20
3
406
40,082
Mike Coughlin retweeted
Every AI agent at work runs with the access of whoever set it up. That’s why security keeps saying no. Today we’re launching @mintive: every agent gets its own identity and permissions, the same way every employee does. We’ve raised $11M, with @cowboyvc leading our latest round.
126
168
88
605
1,659,722
Mike Coughlin retweeted
“designing much faster than the others” — this so daft and makes it clear they don’t understand design at all. “Designing fast” (or slow) is just not a thing. If you conflate “producing ui by piecing together stuff” and “design” then the former (which is a form of assembly-line practice) can surely be fast or slow. What makes the practice of design challenging is not how to put a ui or poster together, it’s what the pieces are, what the message is, what is being communicated, how it all works together. So many of today’s “design” AI tools focus almost exclusively on the production part, on putting stuff together. I’d love to see an AI design tool that forms a deep understanding of a problem over the course of days or months and works like a creative partner. Call me on my bullshit, thinks about the whole, isn’t concerned really about the final arrangement of elements as much as it would understand the story and the message.
Revolut's designers are moving off Figma. Storonsky spotted one team designing much faster than the others. What they did: 1. Gave an LLM Revolut's design system at the code level 2. Prompted it to build new flows on top of that system 3. Got a live interface they can click through on a laptop or phone, instead of static frames Result: 3-4x faster. Now he's pushing it to every designer at Revolut. His job, as he describes it: find what works in one team and spread it across the company. Full breakdown here: productmarketfit.tech/p/revo…
106
194
53
1,696
111,341
Mike Coughlin retweeted
We're hiring across a bunch of roles at Vectoral You'll be at the forefront of stopping some of the worst things in AI. Willing to go above and beyond to build a team of exceptional people. If you think that's you, DM me or apply here: jobs.ashbyhq.com/vectoral
40
14
2
429
28,228
Mike Coughlin retweeted
the coolest part about this imo is the ability to introspect the factory i love the the efficiency and cost per PR screenshots
1
1
3
542
Mike Coughlin retweeted
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
268,448
Mike Coughlin retweeted
Had an awesome time chatting with @wesbos about the token reseller market. He just dropped a great video on the topic. Recommend everyone go check it out. youtube.com/watch?v=09UELaUh…
1
2
12
612
Mike Coughlin retweeted
Most UI sounds still feel cheap because they’re just MP3s. built synthesised tactile feedback that generates on the fly. crisp clicks, satisfying toggles, proper error tones. 2kb. zero files. zero dependencies. cuelume-site.pages.dev/
108
145
52
3,387
511,441
Open protocols like MCP pull monolithic AI stacks apart into competitive markets MCP's real unlock is composition across apps, not one server per client New from Adam Jones (@AnthropicAI) & Tadas Antanavicius (@pulsemcp) on how MCP shape's production asimovaddendum.substack.com/…
3
3
113
Mike Coughlin retweeted
CONFIG: Dylan Field (aka @zoink), Founder & CEO of @Figma says: "You have to actually think." "There's a world where a lot of people are letting AI think for them... & they're tricking themselves into believing they're thinking, themselves." "Especially when the AI is sycophantic & it's telling you you're so great, & you're such a genius, but then giving you what it wants to do.. that's no longer your idea. That's no longer your intention." "Use AI as a tool to learn, a tool to understand the world better, a tool for leverage to get the non-critical stuff done faster." Live from Config 2026, San Francisco
23
37
9
490
107,765
Mike Coughlin retweeted
Everything we announced at Config, all in the canvas → Figma Motion → Code Layers → Weave tools → Generative plugins → Shader effects and fills nitter.cf/figma/status/206986122…
47
192
70
1,414
206,463
A new playbook on @pulsemcp defines the standards for team collaboration on agent skills. The guide provides a technical walkthrough on using MCP to synchronize agentic workflows and manage shared capabilities across a multi-agent environment. It is a key resource for those building the next generation of collaborative AI infrastructure. Full playbook available at: bit.ly/4fjVNo0
4
14
1,023
Mike Coughlin retweeted
The top MCP question from enterprise leaders right now: "How do I curate an approved list of servers for my org?" With 13,000+ MCP servers out there and new ones shipping daily, "just let people install things" isn't a strategy. So we teamed up with @tadasayy and @grumpygrowthguy from @pulsemcp to build a curated catalog of trusted MCP servers purpose-built for Speakeasy customers rolling out MCP at scale. Production-grade, vetted, enterprise-ready. 🤝
3
9
336
Mike Coughlin retweeted
This is really neat but it’s not a design tool as much as it’s a design _production_ tool. The practice of design is mostly about what comes before production. There’s no doubt in my mind that all parts of software production will become automated very soon. Writing code, making web pages, putting pieces of a design system together etc. And that’s fine. I think few people actually enjoy this kind of production work. Wouldn’t it be better if we spent our precious time in life on what is more meaningful?! At the core, the practice of design is methodical; like architecture, not like art. In a nutshell: We find constraints, form comprehension of the whole and propose solutions that honor those constraints. First after that do we enter some form of production phase, usually prototypes first, learn about some constraints that were hidden before, loop back, prototype and then build the production-grade “final” artifact. These last few tasks are quickly losing value because AI tools can do it much faster (not yet better though) than humans. It’s simply just what has the best RoI for a business. Some companies and individuals will continue to spend human time on certain parts of the “production line” as a market differentiator, but it will cost them a relatively high price compared to competitors. Anyhow, I still haven’t seen a tool better than Figma that supports the actually-interesting part of the design process. I wouldn’t be surprised if Figma focused their products on that, maybe separating “products for production” of “products for ideation & exploration.” The latter would obviously still leverage AI, but not to do the work for me but rather to support my efforts the way a therapist helps me live a better life (not living my life for me.)
Introducing Claude Design by Anthropic Labs: make prototypes, slides, and one-pagers by talking to Claude. Powered by Claude Opus 4.7, our most capable vision model. Available in research preview on the Pro, Max, Team, and Enterprise plans, rolling out throughout the day.
81
289
47
2,186
267,210
Mike Coughlin retweeted
Man, ngl, this is a rollercoaster ride.
I am coming around to the fact that MCP, done right, can be magic.
7
7
97
13,034
Mike Coughlin retweeted
Replying to @bcherny
Hey, thank you! As a Claude Code user and an API user that wants to see Anthropic be more generous and transparent with usage limits, it sucked seeing some slop cannons abuse subscriptions and ruin it for the rest of us.
1
1
3
358
Mike Coughlin retweeted
Agents, meet the Figma canvas
91
112
117
1,975
449,863
Mike Coughlin retweeted
Now you can use AI agents to design directly on the Figma canvas, with our new use_figma MCP tool and skills to teach them. Open beta starts today.
516
1,079
650
10,152
17,874,000
Mike Coughlin retweeted
Claude Cowork works because it’s connects to your services via MCP. Your Slack Claude Code plugin works because of MCP. A common auth standard is hugely valuable. If you have context bloat, get a better client, because you shouldn’t just dump a list of tools into your context window.
MCP sucking is a harness problem, not an MCP problem MCP unlocks behavior that is fundamentally impossible to get via CLI or APIs Bad auth, too much context usage, all get solved with an execution layer - your agent writes code to progressively discover and call tools
29
28
2
212
39,241