←
Juan Cruz Martinez7,604 posts
Juan Cruz Martinez avatar

Juan Cruz Martinez

@jcmartinezdev

Auth & identity nerd | 20+ yrs in software engineering DevRel Manager @auth0 Writing about dev careers + AI at thelongcommit.com DM open for collabs

◷ Joined November 2007▧ 653 Photos and videos
Juan Cruz Martinez avatar
Juan Cruz Martinez@jcmartinezdev·7h

I just shipped OpenKumi 0.0.1, a very early alpha of this new open-source project to run bots on dedicated devices. You can run a server and connect it to Claude code or Codex, using your already existing subscriptions or use them with local models. Bots get their own workspace, and dedicated browser sessions and superpowers, so each bot can be independent of the others, with their own identities and memory. I’d love to hear your thoughts, there’s much more work to be done here, and if anyone wants to jump in and collaborate, I think we can build something amazing! The first version gives you the server, desktop app, the mobile app will be coming in the next few weeks, but you can already try it out on iOS if you want to build it. github.com/jcmartinezdev/ope…

Juan Cruz Martinez avatar
⟳ Juan Cruz Martinez retweeted
Juan Cruz Martinez@jcmartinezdev·Nov 16

I made a game where you run an AI lab and race CloseAI, Gemmini Labs and Macrohard AI to AGI. Ship too fast and dooms day gets closer, do it right and you'll achieve AGI. Out now on iPhone and iPad: apps.apple.com/app/ai-lab-ra… I'm having too much fun!

0:44
Juan Cruz Martinez avatar
Juan Cruz Martinez@jcmartinezdev·Nov 10

Anthropic just needs a YT clone now

Starting to roll out today: Claude Whiteboards, Claude Sheets and Claude Data. Think a plan through on a board, build a tracker in a sheet, and tell a story with your data.

0:58
Juan Cruz Martinez avatar
Juan Cruz Martinez@jcmartinezdev·Nov 10

Using @theo’s council skill with t3 has fundamentally changed the way I’m building. Currently I have opus 5.5 leading the charge, with Opus himself, gpt6 and grok as council members. I’m getting amazing results running goals, I’m very happy with it. It’s not cheap though, but it’s very efficient.

Carla Urrea Stabile avatar
⟳ Juan Cruz Martinez retweeted
Carla Urrea Stabile@CarlaStabile·Nov 10

this month's in the last episode for this season of the Making Software podcast. i have an idea of what topic i'd like to discuss but i'd love to hear from folks here: who should be the last guest of the year? what should we talk about?

Post attachment
Auth0 avatar
⟳ Juan Cruz Martinez retweeted
Auth0@auth0·Oct 30

An attacker chains a few small flaws and mints an admin token out of thin air. No password. Five minutes later: one plugin, one backdoor, gone. The team patches fast. Does everything right. It doesn't matter. 🎃

4:01
Auth0 avatar
⟳ Juan Cruz Martinez retweeted
Auth0@auth0·Oct 13

Tools give your AI hands. MCP connects them. Skills give it a playbook. @jesstemporal breaks down how these layers fit together, where security can go wrong, and where OAuth 2.1 comes in. 👀

11:51
ora avatar
⟳ Juan Cruz Martinez retweeted
ora@oradotai·Oct 21

Introducing AgentReady.org, the first open standard for agent experience. Agents are a new class of user, but there's still no shared definition of what it takes to be ready for them. So we partnered with the leading companies in the agentic web such as Vercel, Stripe, Auth0, Mintlify, Tavily and Elementor. Our research lab ran agents on real tasks more than 250,000 times to measure what actually decides whether an agent succeeds, and every requirement traces back to that data. The result is a short set of essentials in the order agents meet a product: find, read, act. We've been overwhelmed by requests to join. If you build or study the surfaces agents touch, come help shape it. The spec: agentready.org The story behind it: ora.ai/blog/agentready-launc…

0:28
Andrea Chiarelli avatar
⟳ Juan Cruz Martinez retweeted
Andrea Chiarelli@andychiare·Oct 19

"On-Behalf-Of" (OBO) names a pattern. OAuth Token Exchange (RFC 8693) is the standard that formalizes it. Microsoft's OBO flow predates it and isn't RFC 8693-compliant. Why that distinction matters for AI agents: auth0.com/blog/on-behalf-of-…

Juan Cruz Martinez avatar
Juan Cruz Martinez@jcmartinezdev·Oct 15

Tech interviews are having an identity crisis. For long tech companies relied on leet code interviews, and even though they were controversial, they worked, at least somewhat. But AI ruined it, AI can solve any leet code challenge with ease, which had two side effects, first, it lead to cheating and a fight for companies to caught it, but most importantly, with AI, being able to solve a challenge like that is meaningless. So where are we now with interviews in tech? I see increasingly companies testing a developer’s ability to understand code bases, basically instead of a leet code challenge, you’re given a medium size code base and you need to understand it, or make a small change live during the interview. They expect you to use AI to make progress fast, otherwise you won’t be able to complete it in time. I like this, because it reflects more the reality of devs in their daily jobs, using AI not only to build, but to understand, and stay in control. AI as an amplifier, not a replacement.

Juan Cruz Martinez avatar
Juan Cruz Martinez@jcmartinezdev·Oct 12

There are no surprises here, this is the Bending Spoons way. Leaning on smaller teams to run products and they have been quite successful doing so. Not because of AI, but because they seem very efficient at finding the right focus and working with smaller teams. It's really unfortunate to everyone who was let go, that part really sucks and I hope they were fairly compensated and can get back on their feet quickly. I know great people who worked there.

Today we’re laying off a large part of the Airtable team. This is not a reflection of their work but a reflection of our deep belief that small teams ship more and better. For Airtable, better is about to look like: - A new Core team shipping your top requests monthly (already 30+ shipped in 3 weeks) - Upgraded Omni, Airtable Canvas, a stronger MCP, and BYO agents, coming soon - New Performance and Infra teams focusing on speeding up bases and increasing limits on records, fields, and syncs To everyone leaving: thank you. If you’re hiring, these are excellent people and worth a call.