Manoel Lemos

Personalize your own suitcase and save the date for @Vercel Ship 26. vercel.com/ship

Wondering about building the future, today? Applications are open for @theresidency! Act now and join amazing founders on a bigger journey.

Thanks a lot @noahzweben !!! This notice just made my day!!! Can't wait to see this in GA! x.com/noahzweben/sta…

Hey @AnthropicAI, what about a secure way to remotely control Claude Code (a session from the dev machine) from the Claude mobile app? You already have everything needed in the user’s hands: the mobile app, notifications for required user actions, etc. I’m sure it would be a killer feature and boost usage even more.

@0xQuasark Hehehehehe!!!!

What would happen if: Super Mario ate a real mushroom? Well, this dude dressed up like Mario. Ate a ton of mushrooms and then Went to Universal Studios 😅

@evilrabbit_ How?

▲

3 days and the scrappy MVP of an always-on assistant powered by @claudeai and inspired by @openclaw is up and running. I'll try to publish the code tomorrow and with some notes on what I learned about OpenClaw during this journey. You can interact with it via CLI or Telegram, can use lots of Claude Code tools, attach tasks to the heartbeat or schedule them with cron. It's cool, but far from ready for production. HeyHo!

It’s alive… and that was one of the first notifications it sent me (testing the heartbeat system). So cool to see all the activity in this space! Kudos to @steipete and @OpenAI for the move!

Getting ready for an exciting long weekend: Volleyball Tournament with the girls and developing my own incarnation of a @openclaw inspired always on assistant (but powered by @AnthropicAI 's Claude Code agent SDK). HeyHo!!!

@pranaygp @WorkflowDevKit Solved! Thanks for that!!!

@mlemos @WorkflowDevKit issue should be resolved on dash again so you can see your runs again. sorry about that

There is something wrong with the Workflow Observability on Vercel platform. When trying to open (view) a workflow, all I see is a huge "red" error message. @pranaygp @WorkflowDevKit

Announcing Built with Opus 4.6: a Claude Code virtual hackathon. Join the Claude Code team for a week of building. Winners will be hand-selected to win $100K in Claude API credits. Apply here: cerebralvalley.ai/e/claude-code-…

That's for you @pranaygp

Software development is undergoing a renaissance in front of our eyes. If you haven't used the tools recently, you likely are underestimating what you're missing. Since December, there's been a step function improvement in what tools like Codex can do. Some great engineers at OpenAI yesterday told me that their job has fundamentally changed since December. Prior to then, they could use Codex for unit tests; now it writes essentially all the code and does a great deal of their operations and debugging. Not everyone has yet made that leap, but it's usually because of factors besides the capability of the model. Every company faces the same opportunity now, and navigating it well — just like with cloud computing or the Internet — requires careful thought. This post shares how OpenAI is currently approaching retooling our teams towards agentic software development. We're still learning and iterating, but here's how we're thinking about it right now: As a first step, by March 31st, we're aiming that: (1) For any technical task, the tool of first resort for humans is interacting with an agent rather than using an editor or terminal. (2) The default way humans utilize agents is explicitly evaluated as safe, but also productive enough that most workflows do not need additional permissions. In order to get there, here's what we recommended to the team a few weeks ago: 1. Take the time to try out the tools. The tools do sell themselves — many people have had amazing experiences with 5.2 in Codex, after having churned from codex web a few months ago. But many people are also so busy they haven't had a chance to try Codex yet or got stuck thinking "is there any way it could do X" rather than just trying. - Designate an "agents captain" for your team — the primary person responsible for thinking about how agents can be brought into the teams' workflow. - Share experiences or questions in a few designated internal channels - Take a day for a company-wide Codex hackathon 2. Create skills and AGENTS[.md]. - Create and maintain an AGENTS[.md] for any project you work on; update the AGENTS[.md] whenever the agent does something wrong or struggles with a task. - Write skills for anything that you get Codex to do, and commit it to the skills directory in a shared repository 3. Inventory and make accessible any internal tools. - Maintain a list of tools that your team relies on, and make sure someone takes point on making it agent-accessible (such as via a CLI or MCP server). 4. Structure codebases to be agent-first. With the models changing so fast, this is still somewhat untrodden ground, and will require some exploration. - Write tests which are quick to run, and create high-quality interfaces between components. 5. Say no to slop. Managing AI generated code at scale is an emerging problem, and will require new processes and conventions to keep code quality high - Ensure that some human is accountable for any code that gets merged. As a code reviewer, maintain at least the same bar as you would for human-written code, and make sure the author understands what they're submitting. 6. Work on basic infra. There's a lot of room for everyone to build basic infrastructure, which can be guided by internal user feedback. The core tools are getting a lot better and more usable, but there's a lot of infrastructure that currently go around the tools, such as observability, tracking not just the committed code but the agent trajectories that led to them, and central management of the tools that agents are able to use. Overall, adopting tools like Codex is not just a technical but also a deep cultural change, with a lot of downstream implications to figure out. We encourage every manager to drive this with their team, and to think through other action items — for example, per item 5 above, what else can prevent a lot of "functionally-correct but poorly-maintainable code" from creeping into codebases.

The Vercel AI Accelerator is so back. Join 40 teams for 6 weeks of learning, building, and shipping with over $6M in credits from Vercel, v0, AWS, and other leading AI platforms. Applications open now until February 16th. vercel.com/blog/the-verce…

.@Diditprotocol is building the fastest way to verify real humans online. One face scan to prove identity, fight fraud by default, and run all identity checks in a single platform with simple pay-per-use pricing. Congrats @albertorosasg and @_arosasg on the launch! ycombinator.com/launches/PLo-d…

@vercel_dev This is awesome. Any plans to add Gemini with Search Grounding via the Gateway?

Parallel's Web Search tool is now available on AI Gateway. 𝚝𝚘𝚘𝚕𝚜: { 𝚙𝚊𝚛𝚊𝚕𝚕𝚎𝚕_𝚜𝚎𝚊𝚛𝚌𝚑: 𝚐𝚊𝚝𝚎𝚠𝚊𝚢 .𝚝𝚘𝚘𝚕𝚜 .𝚙𝚊𝚛𝚊𝚕𝚕𝚎𝚕𝚂𝚎𝚊𝚛𝚌𝚑() } Simply add the tool to your agent to get real-time web search for any model, with any provider. vercel.com/changelog/para…

@Nate_Esparza HeyHo!

If you can reply to this You either got paid or can get paid for posting on X Congrats to those who did and good luck to those in the chase 🫡

@dkrasniy Very nice! Is the code open? I’d love to play with some tweaks on the UX that I think about them everyday I drive my car.

rebuilt the tesla infotainment ui with react and tailwind! try any car config and use keyboard to toggle charging (C), put it in drive (D) and accelerate with arrow keys teslaui.dkrasniy.com