Alex Wurts

@joebarnard If you’re feeling adventurous, try vibe coding your own website to track everything. It feels pretty cool to work with a product designed exclusively for yourself.

I'm trying to upgrade my project management. Between making rockets, all their parts, and then videos about that process, I need a tool that helps me keep track of these to-do lists and timelines. What do y'all use?

You open your terminal. You type a prompt. Claude writes the code. You review the diff. But where did you save the prompt? AI outputs code. Humans output prompts. Don't we want to track the intent behind the code? What are you doing to track such an important piece of the puzzle?

@joebarnard Sit in a room for 20 minutes and talk about all the stuff you want to include steam of conscious. Try to get some quotes and lines in, so it pulls those verbatim. Then dump it into AI to get a rough outline, and refine from there. Skips the most annoying part for me.

YouTuber/writer friends, how do you speed up the process of writing scripts? I love making videos and they're so much better with a good script, but I have a hard time staying focused when writing so that process takes forever 😅

Our engineers, Reagan and Alex, walked through what onboarding with Coworker actually looks like and how to start using it from day one. #AIProductivity #Coworker #EnterpriseAI #DevTools #WorkplaceAutomation #AIAssistant #MakeWorkMatter

Your team spends 20 minutes every day just scheduling meetings. They're juggling calendar apps, chasing down availability, sending endless "what time works for you?" messages. The bigger the meeting, the worse it gets. Sound familiar? That's why we built Calendar Write. Now you can just tell Coworker: "Schedule a team standup for tomorrow at 9 AM with the engineering team" Here's what happens automatically: 1. Smart Scheduling → Creates the event, adds Google Meet, sends invites to all team members. 2. Conflict Detection → Checks everyone's availability and suggests optimal times if conflicts exist. 3. Intelligent Updates → "Move my 3 PM to 4 PM and add John" - handles rescheduling and new invitations seamlessly. 4. Global Team Support → Automatically handles timezone coordination for distributed teams. Most calendar tools make you do the work. Coworker does the work for you. What scheduling headaches are slowing down your team? 🗓️ hashtag#CalendarsShouldntSuck hashtag#WorkFriction

@dremnik @mathemagic1an I see a sandbox as fundamentally just a place to run unix-based tools. What runs them, and how will depend on the specific application.

@mathemagic1an @AlexWurts so how do you see it evolving?

Consider me a sandbox maximalist The formula for AGI is hyper-intelligent models interacting with classic unix VMs. Infra companies will reorganize themselves to make this efficient This is the bitter lesson in motion

You gotta stop babying your CLI coding agent. You aren't working with the first iteration of CLI agents from a year ago, they have gone from competent software engineers, to very capable senior engineers. They can and will solve large problems, just let them try.

@ATCalder @AnthropicAI If I were Anthropic I would have made the same choice. It's an obvious side-step from Claude Code, but I just don't see it working long term. It's too easy to copy, and doesn't solve real user problems.

As the CEO of Coworker, a lot of people asked me this week what I think of Claude Cowork... Firstly, the name is an inspired choice – we've drafted a lil letter to let @AnthropicAI know we think so too! That aside: 1. Claude Code's great, but being great at understanding structured code ≠ being great at understanding the messy, unstructured ‘code’ that is company context. Claude Cowork is a wrapper on Claude Code: give it tools, time, and ungodly token use and it'll hack at work tasks. But ask basic things like 'what happened in our all-hands last week' and it spends 2 mins trawling Jira (!?), Notion, and Drive before admitting defeat. The problem is it's the same 'tool maximalist' approach that @OpenAI and Claude enterprise use. Neither work great. Understanding company context is brutal. Conflicting/outdated info, weird data structures, people disagreeing... An agent tool RAGing through that minefield gets blown up by errors and irrelevant data - all the stuff that's already broken enterprise AI trust. Agents do better when they've done their homework. When we connect to company data, we run a stupid amount of models in the background constantly generating a dense context graph. This 1. gives agents the right context quickly, and 2. info on how to operate: 'how does this company structure Salesforce', 'who works on what', 'which conflicting source is correct.' 2. Speed matters. We moved away from the Claude Code architecture b/c we found business users are hyper sensitive to speed (<10 secs outputs vs meandering through tools). 3. The consensus view that foundational players ultimately win enterprise AI is wrong. We're big fans of Anthropic, but the 'Claude Code built Claude Cowork in 1.5 weeks' brag is actually a bearish indicator for how seriously they're taking this category. Their 'prep my day' can't yet connect to calendar, email or Slack. 'Organize my desktop' as a hero use case lacks user understanding– there's a reason no-one's done this since 2002: work happens in the cloud, not your machine. It’s the same reason ChatGPT Enterprise is subpar and why @glean dominates the space despite being 'just fine.' There's a fundamental incentive misalignment between foundational labs and companies. Most companies are hedging across model providers. They want systems that maintain context across agent infrastructure with the flexibility to swap models. That's a path to commoditization for foundational, and an opportunity for 'neutral' operating systems to manage context and route workloads to the ‘cheapest cost per successful task’ model (many will be open-source). After all, you wouldn't let your electricity provider control your thermostat. True superintelligence will emerge when companies can deploy lightning fast agent swarms with shared, learned context across enterprise data. No platform is close to that today. But our team at @coworkerapp is squarely focused on the exact enterprise neurosurgery that'll deliver it.

You know your eng team is going to have a bad week when the base model can't get the days of the week right.

Introducing: Deep Work by @coworkerapp Start any project 80% complete with AI that has deep company context and memory. Check it out: coworker.ai/deep-work

@eshear @coworkerapp This is what we do. No more writing annoying prompts, or trying to copy paste your data into your chat. And it's more than just Github + Asana, we're adding more connections daily.

I want a weekly status update on everything happening at the company, drawn from GitHub and Asana primarily but probably including other sources over time. With summaries and drilldowns. As far as I can tell, no one makes a dedicated tool that just does this? Why???

You don't have to work at Anthropic or OpenAI to work on world-leading AI. While they focus on model development, that's only a small part of the picture. How you use the model is much more important. wurts.bearblog.dev/how-tool-use-i…

Thrilled to announce @coworkerapp and our $13M seed funding! We've built the first enterprise AI that truly understands context and can do complex work across your company's apps and data. Powered by our breakthrough OM1 memory, it's ready to transform how teams work.

@AmericanAir I paid for a flight from Sydney to Boston and that’s not what I got. I know it cost more than $297 to go from Hawaii to Boston. That’s a very convenient and stingy calculation from American. What about my premium economy?? That was never refined

@AlexWurts As explained in DM, we've provided a refund of the unused portion of the fare.

@AmericanAir I was supposed to go from SYDNEY to BOSTON and instead I was left in Honolulu airport at 1:30 am. The original flight didn’t end up leaving for over 15+ hours later so I had to find a different way home

@AmericanAir Since when does it cost $297 in premium economy to go from HNL to BOS. Thats a very convenient calculation for AA. When I asked how you did the calculation no explanation was provided.

@AmericanAir @AmericanAir is this how you treat your customers? @PeteButtigieg @USDOT

@AlexWurts We've reached out to our Refunds team on your behalf. Meet us in DMS, so we can provide you with additional details on your refund.