Michelle Fitzpatrick

If you’ve clearly vibe coded your marketing site, I’m gonna assume you’ve also vibe coded your product and it’s prob very shallow and not worth my time to try

@jessegenet Haha awesome! Thats a step up from my 4yr old who says “can I hatch the eggs into the bowl” when we’re cooking. I am NEVER correcting him

[me frantically trying to unload 4 kids from car, already 15 minutes late] 4 yo: mom, really really quick I have a question Me: ok go 4yo: you know how there are chickens and they make eggs Me: yes 4yo: and then eggs make chickens Me: yes 4yo: at the super beginning of time do you think it was all eggs or all chickens to start? Me: 😵

@zarazhangrui Totally agree, and I’ve been doing the same starting with exploring a technology first. I built a pokemon asteroids style game that you control with head and hand tracking cause I saw someone on X post an app that could use the camera to track pushups and wanted to figure it out

@karrisaarinen The next step after both is opinion, which people are also starting to blindly outsource. What should I write? What should I eat? Where should I go on holidays? Is this product good? Etc The level of trust in AI answers/recs is crazy

"you can outsource thinking but not understanding" vs "you can outsource work but not understanding" There is a nuance here. I’m not sure “thinking” is something you can fully separate from understanding. Thinking is often the continuous process that creates understanding. There cannot really be understanding without some thinking. Someone else can think through a problem, analyze it, synthesize it, and hand you the output. AI can do the same. But what you receive is still an output, or a communication of that thinking. The actual understanding has to happen on your side. You have to integrate the output (thinking and output), test it against your own judgment, and your understanding (and thinking) is needed to decide whether it is right. Essentially, you have to do your own thinking to gain understanding. The more you passively outsource the thinking, the less you are likely to understand. That does not mean you cannot delegate or outsource work. Companies and groups do this all the time. You can create the parameters, set the direction, and trust others to do the thinking and the work within those constraints. In many cases, how it happens does not matter to you and your understanding is not required. But if you actually need to understand something, I don't you can outsource the thinking. You have to do the thinking yourself, using whatever people or tools you have to help you. That is the difference in my mind.

@dharmesh I’ve seen some and my first thought is honestly “there’s no way my mum would have a clue what they’re asking”

AI is getting better and better at answering CAPTCHAs. Me? I'm failing them more often. Soon, I'm going to have to start using AI to prove that I'm human.

@daveyheuser @adisbanda The reverse funnel 🤣

@shelliefitz It’s my new companies or accounts (IYKYK) cc @adisbanda

I still think about this on a daily basis. There is a lot of advice for designers out there in the world but "because I don't like the other options" should definitely be included to drive decisions

@pbakaus @FedericoNoemie Totally agree, taste is often focused on the visual side which is only one part of a valuable product

@FedericoNoemie yeah i think that's a great definition. i guess i was reacting to the fact that taste is now such an overused term, and people conflate it with "something that looks and feels good", but AI can definitely do that now. real taste goes much further.

pov + intent > taste

@lennysan I’d love to see the new user sign up stats for these products after you shared 📈 It’s like Oprahs fav things but for product nerds

A few lesser-known products I love and use a ton: 1. cleanshot.com for screenshots 2. supercut.ai replaced Loom for me, so clean 3. textexpander.com for frequent snippets 4. matthewpalmer.net/rocket/ for emojis 5. brain.fm for focus

@clairevo Ok now do all the ways you can use Claude and the various billing and usage options

Ok so: message = text instructions agent =LLM w tools, connectors + sometimes a computer that takes in messages and does things including sending messages back local agent = that computer is on your desk cloud agent = that computer is on the internet sandbox = that computer is in a real or virtual box for the mutual safety of you and your agent subagent = your agent gives some work to another agent tool = a way to get a specific input/output from AI hooks = things that trigger off specific events in your agent’s life connector = a way to get info from AI to/from a 3p system MCP = a standard for connectors skills = set instructions and code for an agent to use over and over again api = a way for software to talk to other software via code cli = a way to trigger code (incl APIs) in the terminal which is easier than having your agent try to click buttons plugin = bundle of skills + connectors harness = opinionated and bundled set of instructions, tools, etc so an agent can make maximal use of its model and computer to do a good job, usually coding agent SDK = a way to programmatically invoke a harness what did I miss and also what is wrong with us

@_ai_reviews @clairevo Rich message 💸

@clairevo message = text instructions. OK. What is a message + attached files called?

@shashpicious_ Come back in a WEEK after using for 20mins has to be the dumbest retention strategy I’ve seen

claude design faded out in a week like it never existed.

@jasondoesstuff I’ve been doing this too and it it works so well. I also use it to explain things “create html page to explain xyz”. My new fav one is “spin up 3 subagents to review and give me feedback on this”. Try it, just that and you’ll be impressed

This is neat. If you're working on a project but don't know how you want a UI (or UX) change to look... 💡 Tell Claude: "Mockup variations of how you think this feature/change should look and show them to me." Saves a TON of time (and tokens) building ugly/bad features!

@nikitabier @hnshah Omg finally!!! I’ve wanted this for years. now I can separate tech twitter from pop culture trash :)

Ladies and gentlemen, today we're launching one of our biggest changes to 𝕏 Introducing Custom Timelines This feature allows you to pin a specific topic to your home tab. With support for over 75 topics, you can dive deep into your favorite niche on X. It's powered by Grok's understanding of every post with the algorithm's personalization—meaning every timeline is made just for you. And it works even better when it's a topic you already engage with. This was a huge undertaking across many months, so we're excited for you take it for a spin. We're giving early access to Premium subscribers on iOS (and Android coming very soon).

@claudeai I dont exactly know what this will do for wireframe explorations but Im digging it

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.

@ben8128 Haha same! I always tell it to just give it an try and we’ll see

It’s funny when Claude Code says that something's going to take a couple of days or weeks of work…and then you finish it using Claude Code in about 20 minutes. It needs to forget the human-based timelines.

@daltonuiux I tried a bunch and landed on Claude code and Paper. Install the front end design skill, impeccable design skill and superpowers skill. Superpower will brainstorm with you before jumping in, and the @impeccable_ai skill up levels design quality.

Feeling a bit lost with the amount of design//code options out there right now 😅 Paper, Pencil, Cursor, Claude Code etc... In terms of product/UI design, what would be the best option to experiment with? Leaning towards Cursor/Claude? But not sure.

@shydev69 @felixrieseberg the universe has responded 🙌

@shydev69 @felixrieseberg lol every time there’s an update I think, surely they’ll fix the spacing in this one. Clearly a P0

Today is a big day! We're launching a ~ new ~ version of Claude Code in the desktop app. It's been redesigned from the ground up for parallel work and is a lot faster. It's been my main way to use Claude Code for the last few weeks.

@levie the rise of the semi-technical! There are so many people who have the aptitude for this and dont realise it. All the people in different depts who are excellent at creating spreadsheets, automations, processes etc, but dont consider themselves technical enough for eng

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.