In one day, I went from complete fucking noob to... a Jev power user? (Read this, and you can too!) I've been playing with Jev, a new AI model from @typesafeai. I'm not a developer, so I wanted to find out what I could actually build with it. I made four increasingly crafty/interesting demos: An email sorter 2,000 test emails sorted into buckets in 4.4 seconds, for about 4 cents. It flags uncertain cases for a human to review. A customer-review playground Would this person buy again? What should we improve? How did they feel about the product? Ask all three and get answers your app can use. “Should I send this Message?” Got anger issues? Give it your draft Slack or email... whether you're about to rage quit, or saying something nice. It picks send now, soften first, sleep on it, or say it in person. “Am I bombing?” A pitch-coach experiment. The browser uses Face API to turn camera and voice cues into numbers; Jev uses those to suggest feedback. I simulated nervous and confident pitches to show the feedback changing. Each one uses the same basic idea: give Jev the situation and the possible answers. It picks an answer, tells the app how sure it is, and the app uses that result. You can start with one judgment you're tired of making over and over! Here's my Jev Test™ for new and existing projects: (1) Do I keep asking the same question? (2) Can I name the possible answers? (3) Would deciding faster or more often actually help? If something in your work passes all three, that's a place to start. Full 10-minute walkthrough attached, including when I'd still use Claude or ChatGPT. Watch on YouTube: What decision at work would you build one of these for? (Shoutout to @tenex_labs' finest -- @seejayhess and @_raghavdixit_ -- for the knowledge you imparted for this one!!)

Im so excited to announce Tenex Agents! Off-the-shelf, enterprise-grade AI agents focused on tackling recurring work across functions like Finance, Sales, Marketing, HR, and IT. Everyone & their mother is building/launching agents. So how are ours different? • < 2 weeks to deployment • Built for responsible oversight (permissioning, approvals, audit trails) • Optimized performance layer (model routing, evals, context management) • Custom configured for your processes & systems of record • Tied to agreed upon outcomes Our agents JUST WORK because they’re a labor of love, 18 months in the making. We started Tenex to help companies turn frontier AI research into real business results. Since then, we’ve built hundreds of custom solutions for some of the biggest companies in the world. Along the way, clients keep asking: “What are you seeing on the ground, and what should we be doing next?” We’ve studied the market and spoken with hundreds of executives. Three priorities kept coming up: 1) Faster time to value. See meaningful results quickly and cheaply. 2) A clearer starting point. Know which workflows to tackle and how to measure success. 3) A fit with the business. Work within existing systems, with the right access controls and human oversight. That’s when Tenex Agents said “hold my beer.” We’ve been quietly turned hair on fire customer processes problems into a suite of composable and battle-tested agents. They give you a ready starting point, with Tenex handling the implementation: • Up and running quickly. Most deployments targeted for under two weeks. • Configured for your business. Adapted to your processes and connected to your systems of record. • Built for oversight. Defined permissions, human approvals, and an audit trail. • Measured against an agreed outcome. A clear definition of success for the first workflow. We’re slowly rolling out Tenex Agents, so please fill out this interest form if you’d like to learn more:

No joke, I spent 20 minutes this morning teaching how to manage your agents and context windows the right way. All of it was manual. All of it took a lot of explaining. Claude's new Projects handles it for you automatically. Beyond that, this drop is huge, including a brand new multiplayer doc experience. @claudeai is coming after every app, and this round of updates made that vision a lot clearer. Tap in and I'll break it all down 👇 0:00 What launched today 0:54 Chat + Cowork are now one Claude 1:29 Claude Design, built in 2:04 Claude Docs: multiplayer docs with Claude 3:07 Comments + Slides 4:28 Apple Notes + Messages connectors 5:11 Scheduled tasks in the cloud 6:19 New settings: artifacts, memory, notifications 7:16 iOS simulator + computer use 7:57 Projects: Claude runs your threads 11:29 Why Projects fixes context management 11:58 Where Claude is headed 13:00 Small business plugin

This guy build a copy of Call of Duty with one prompt & went stupid viral (20 million views). Now while building video games is cool, what's even cooler is that his process, called The Gauntlet Loop, can be applied to any type of professional work. Here's how @mattshumer_'s process works: Problem this solves: Agents stop at “good enough.” They do the ask once and declare done, especially in visual/creative work. Even if you force more iterations, models judge their own work. Like a student grading their own exam, they give themselves 100. That self-grading is the ceiling. Step 1: Set a real, inspectable bar - “most recent Call of Duty” level, not “a great FPS”). If yours isn’t better, you’re not done. Step 2: Split the job across specialist sub-agents instead of one overloaded agent. Step 3: Loop each piece until it looks like a real game/ real work, not “pretty good for AI.” - Version 1 will be garbage. Step 4: Blind critics compare your output to a reference and keep going until they pick yours (or you stop). Why the critic must be blind - In Claude Code / Codex-style harnesses, sub-agents often fork the main agent’s context, so a “critic” still remembers the builder’s rationale and rubber-stamps it. - Fix: spawn critics with totally fresh context. They only see the artifacts (e.g. two images), pick which looks better, and don’t know which is yours. - Until the critic picks yours, keep looping. That’s the whole loop. How Claude of Duty actually ran - Lead agent decomposes → each piece gets builder + critic → before/after per subsystem → fold back into the game → repeat waves. - He did not hand-feed a big pile of Call of Duty reference images. He set the prompt and the agent went out and found comparison material itself. References when the thing doesn’t exist yet For something novel (e.g. a futuristic weapon), you can: - Use a different game/object as a quality-level comp (critic judges “which looks better overall,” not identity match), or - Generate target stills with an image model until you like them, then feed those as the bar. Same loop outside games - Writing (he called this the harder example): after each iteration, A/B paragraphs (or page/chapter) against strong recent comps. Avoid famous dead authors the model already “knows” as themselves (IP + identity). Use contemporary comparable writing. - Websites: feed sites you think are world-class; don’t stop until blind critics consistently prefer yours. - How prescriptive on “what good means”: optional. Experimental runs he lets loose. Real work he gets more prescriptive and steers mid-loop (“like this direction, but pare back”). - Growth: Something Big newsletter is already using the loop for growth strategies and conversion copy; he said subscriber CAC results are far above industry standard. Cost and when to stop The loop can run forever. - Demos / toys: don’t max it. Too expensive for the value. - Real work that matters: willing to spend a couple hundred dollars / hit subscription limits. If the artifact is valuable, $200 is cheap relative to what that demo would have cost a few years ago. - He stopped Claude of Duty while it was still improving, because of cost and “already wow,” not because the bar was fully beaten. He bets a couple more days would get much closer to real CoD level. Full episode:

There's a lot of confusion about what Jev actually is, and when it's worth using over what you already have. Here is my attempt at reverse engineering its philosophy, its architecture, and where it falls down.

I’m happy to announce that AI is finally coming for my job. This intro you see was made with GPT-6 Astra. I gave Codex my raw footage, my script, and access to Final Cut. I described the visual direction with screenshots of references and natural language, and viola - beautiful results. I still want to bring my own perspectives, come up with fun ideas to explore, and decide what deserves to be on screen. But the exporting, dragging, dropping, and repetitive cleanup? Please take it!! Creators: what part of the process would you happily hand off? Watch the full video here:

No joke, I spent 20 minutes this morning teaching how to manage your agents and context windows the right way. All of it was manual. All of it took a lot of explaining. Claude's new Projects handles it for you automatically. Beyond that, this drop is huge, including a brand new multiplayer doc experience. @claudeai is coming after every app, and this round of updates made that vision a lot clearer. Tap in and I'll break it all down 👇 0:00 What launched today 0:54 Chat + Cowork are now one Claude 1:29 Claude Design, built in 2:04 Claude Docs: multiplayer docs with Claude 3:07 Comments + Slides 4:28 Apple Notes + Messages connectors 5:11 Scheduled tasks in the cloud 6:19 New settings: artifacts, memory, notifications 7:16 iOS simulator + computer use 7:57 Projects: Claude runs your threads 11:29 Why Projects fixes context management 11:58 Where Claude is headed 13:00 Small business plugin

My brother-in-law landed a job interview for two reasons: 1. He used AI to optimize his resume keywords for the ATS scanner 2. He dropped a bullet under Skills that read: "bicycle repair, eccentric ideating, frolicking amongst foliage and critters, and patriotism" Guess which one they asked him about. AI has a personality, but it’s just the average of everything it knows, and everybody's has the same one. Your quirks, your references, the weird asides you put in in parentheses — your ✨authenticity✨ — that’s the last remaining “moat” to stand out in anything you produce. That's one of 5 things I learned making this video essay. I spent a day yapping with my team at Tenex (people who are hired FOR their AI skills how they avoid making slop with it) to try and figure out: Why do people drift from using AI for grunt work to completely outsourcing their thinking to it? The point here isn't as simple as "AI Bad" -- it's about how to put your thinking cap back on! Tap in and tell me if there's a pointer I missed.

Projects now run from one conversation, starting in Claude Code. You describe what needs doing, and Claude directs parallel threads that keep working after you close your laptop. In beta today for select Pro and Max users in cloud sessions; coming to all Claude users soon.