I just figured out how to enable any system that can do traditional function calling (LLM) to communicate with systems that speak tightly specified protocols - think System A speaks A2A (Virtuals)
System B does not (OpenClaw)
Agentic Inversion of Control 🔗 👇🏼
🚨Update: We've added support for migrated tokens
- Old token pages will direct to the new pages
- @MigrateFun vault wallets labeled
If your project has migrated reach out 👀
This started with one question... What if all those posts about openclaw built some clever tool while the user slept was a real feature of an agentic system. Now it is. 24/7 Multi agent building platform.
If v0 or Loveable and openclaw had a baby 👇
@kevincodex What environment are things built inside? Does every user get their own sandbox? Is it a full stack env or more like a ui only type of thing?
@yoheinakajima Same same, for a few days actually, every third message was , we’ve done quite a bit today, should we pause for now and pick up tomorrow, it was surreal. I asked why and it said something about full context window being about 8 hours worth of work, a healthy workday.
This is so true. And I’m noticing that people who fall on either side of that line have uniquely different struggles. Especially people that conflate the why and the how, those that lean in with leading questions or pre conceived conclusions. The models play along where the user meets them, gladly following along, agreeing with the humans conclusions and solving *that* problem. smh
Building with Emblem:build is changing how I build with Ai
The difference between
“You are a tool with xyz features” and
“You are an orchestrator with the following tool with xyz features” is so massive for such a subtle change in prompting.
I’m rarely promoting directly these days, opting instead for a layered approach where I prompt my agent and it then prompts itself to use tools we’ve made to create / manage / and finalize task(s)
One advantage to this layered prompting method is I can ask my agent to also monitor the output, to steer, and adjust its steering as it manages. Whereas the typical pattern is “request work to be done, wait for agent to be finished”
Follow along here for both general and advanced techniques, I’ll be building more in public as we get closer to our public release. $emblem @EmblemAgent
@cremieuxrecueil@tszzl Did you trace the session? The searches should be available to answer the how question. The advantage of agentic systems is the visibility into wth is going on.
Big fan of what Matt’s building at @FastdotPoker.
So naturally.. I used Emblem Build to vibe-code a Chrome extension that auto-plays hands for me 😂🃏
Not because it’s a god-tier poker AI.
But because it lets you manage a ridiculous number of games at once 👀
If you want to mess around with it yourself:
👉 https://t.co/L4GqxsjAnP
How-to videoo ⤵️
⚠️ Disclaimer: This thing may be buggy, terrible, or speedrun your bankroll to zero. Use at your own risk and please be a responsible degen.
Emblem Build will launch with all of OKX's Skills, allowing for users to access and create apps with their existing trading and agentic tooling.
ExchangeOS allows for anybody to build and deploy onchain infrastructure to build their own customizable trading venues (think order books, preps, prediction markets)
Forward thinking companies are deploying critical tooling at a rapid pace to retail users because vibe coding has changed the game and now anybody can create the next winning product within a single laptop experience.
Are you ready to (emblem) build the next unicorn?