Dylan Andersen

Work has been *wild* lately

@rauchg geardex.app Mainly Opus 4.6

Show me the thing you’ve built with AI you’re most proud of. Reply with a working product URL and what model / agent you primarily used.

Comparison demo without and with the Transitions skill Demo page with more details, usage and commands transitions.dev/skill npx skills add jakubantalik/transitions.dev

Welcome Agentforce Coworker. 🤝 Your new AI teammate is now inside every Salesforce search bar. It doesn’t just find things — it works with you. Agentforce now instantly taps into your CRM data, workflows, customer history, opportunities, and cases… then takes action in real-time. ❌ No copy/paste ❌ No tab hunting ❌ No context switching Just ask. Act. Close faster. 🔥 Plus, build custom agents that run natively in Slack, Teams, and mobile. Available today for every Agentforce customer. We went from internal dog fooding to your hands in record time. The pace at Salesforce is absolutely WILD right now ⚡️Be a Trailblazer — turn yours on today! 👇

@thsottiaux Day 99 of asking for a split screen option

For those of you living inside the codex app, what should we prioritize among features, reliability or performance?

@thsottiaux Icons for projects? Please? Split screen chats?

What are we obviously not getting right with Codex?

@clarklab Woaaahhh

@dylandersen seriously, look at this spritesheet!

Enjoying catching what names Codex gives the sub-agents. Confucious and Bacon? Feeling seen right now.

@clarklab I haven't played with it yet but I am already sadly sold haha

@dylandersen I'm playing with their new "Pets" thing right now, and: a) it's so stupid b) I'm really impressed with it's pixel art generation skills (completely matching characters across mutliple sprites)

@thsottiaux Who do I have to beg to get split screen agents in a project?? 🥲

We will ship again this week. Codex has achieved escape velocity and will keep improving rapidly.

No browser required. Our API is the UI. 🔓 Salesforce Headless 360 just exposed our entire platform — apps, workflows, metadata, Agentforce & Slack — as unified APIs, MCP tools & CLI. Build on any surface. Give Agentforce deep, trusted context. Stop just using Salesforce. Start building with it. 🚀 cio.com/article/415953…

Had meetings and a dinner with 20+ enterprise AI and IT leaders today. Lots of interesting conversations around the state of AI in large enterprises, especially regulated businesses. Here are some of general trends: * Agents are clearly the big thing. Enterprises moving from talking about chatbots to agents, though we’re still very early. Coding is still the dominant agentic use-case being adopted thus far, with other categories of across knowledge work starting to emerge. Lots of agentic work moving from pilots and PoCs into production, and some enterprises had lots of active live use-cases. * Agentic use-cases span every part of a business, from back office operations to client facing experiences from sales to customer onboarding workflows. General feeling is that agentic workflows will hit every part of an organization, often with biggest focus on delivering better for customers, getting better insights and intelligence from data and documents, speeding up high ROI workflows with agents, and so on. Very limited discussion on pure cost cutting. * Data and AI governance still remain core challenges. Getting data and content into a spot that agents can securely and easily operate on remains a huge task for more organizations. Years of data management fragmentation that wasn’t a problem now is an issue for enterprises looking to adopt agents. And governing what agents can do with data in a workflow still a major topic. * Identity emerging as a big topic. Can the agent have access to everything you have? In a world of dozens of agents working on behalf, potentially too much data exposure and scope for the agents. How do we manage agents with partitioned level of access to your information? * Lots of emerging questions on how we will budget for tokens across use-cases and teams. Companies don’t want to constrain use-cases, but equally need to be mindful of ultimate token budgets. This is going to become a bigger part of OpEx over time, and probably won’t make sense to be considered an IT budget anymore. Likely needs to be factored into the rest of operating expenses. * Interoperability is key. Every enterprise is deploying multiple AI systems right now, and it’s unlikely that there’s going to be a single platform to rule them all. Customers are getting savvier on how to handle agent interoperability, and this will be one of the biggest drivers of an AI stack going forward. Lots more takeaways than just this, but needless to say the momentum is building but equally enterprises are acutely aware of the change management and work ahead. Lots of opportunity right now.

@clarklab ahhaha true true

@dylandersen I just tell myself it's cheaper than a human dev team so yolooooo

gosh this is a fun one: 📸 snap a photo of statue 🤖 agent grabs history, generates voice(s) 🗣️ chat with art in real time

@HappyGezim @clarklab def hear that. wonder, though, are those things that I want to be doing instead? for the cron, overnight jobs, I noticed the new codex app is great at that. the personal life stuff, I find gemini personal intelligence to be good enough

@clarklab now that everything moves 1000mph every 5 minutes, would love your take on the 'fastest' way to get an openclaw (or fork) set up on a vps - I remember you had shared something previously... any updates? (not for me, for a newb friend who won't stop asking haha)

@clarklab you mean like the million emails I get daily from "real" people? 🥲

@dylandersen In short: if I send you a human email and get an agent response or automation- I'm not likely to contact you again, haha

@clarklab damn, mic drop. yes. exactly -- google already has gemini in gmail now, works very well to summarize, find things, help fill in the gaps, etc. i don't need to do that in a telegram chat. the personal intelligence - if you use gapps - is solved imo

@dylandersen People seem to want to automate the easy stuff (that probably *should* be done by a human) but I'm looking to use it for stuff I could never do myself

@clarklab i've been blasting through the claude max 5x sub every month and have been very happy. playing with the new codex app and love some things about it, hate others. nice to switch between the two as i build @geardexapp used opus 4.6 to add a 'working' mock on the hero today

I'm nerdy enough that I haven't quiiiite seen the need for OpenClaw yet, I'm just using Claude Code locally and on VPS and on the app, all at the same time, like madman. But my use case (making sites and writing prod code) seems to be fairly different than most using OpenClaw (messages and email and scheduling and research). Maybe I'm wrong. But my Claude Code setup is shared at vibeserverops.com