Data harness for your agent:
(i) near-100% accuracy,
(ii) deterministic security, and
(iii) easy integration
-- here shipped in prod by Hughes Network Systems:
https://t.co/Dl9fmPG29N
with @Andrew_Brook and Amarender Singh Sardar
Building agents? Need near-100% accuracy...? Come to our session BRK3-003 @ Cloud Next '26:
1/ demo of agentic solution for user support, by Hughes Networks Systems
2/ architecture & design
3/ "how to reach near-100% accuracy" and Q&A
Thurs 4/23 @ 4pm
To take action, your agents need accurate data
(or else, you won't like the results...)
Here your agent harness – a tool for connecting agents to databases: https://t.co/Dfxf0WjdRt
"Golden Handcuffs" – another song from "cyber-country" genre:
https://t.co/PDs6HivM1w
REAL songs about REAL tech folks
Our band is "Exit 404" = myself on lyrics, Suno on music + singing, and Gemini on visuals
@jackdbrody@suno@bradmatthiesen@MikeyShulman
AI agents are getting incredibly smart. But they still don’t really know you.
Having worked on consumer products powered by Open Banking (@meetcleo) and IoT data (Omnia), @MaxAlbarello and I started https://t.co/6cjgGVVWVk at @join_ef because we believe something is missing: portable, user-controlled personal context for truly personal AI.
Our belief has deepened as we use agents that show real intelligence but have gaping holes in their understanding of us e.g. ChatGPT does not know which restaurant I posted from last Saturday and Claude has no idea which book I just ordered.
In real life, your preferences don’t develop in neat little boxes, one box for Google, one for Instagram, and one for ChatGPT.
So why does your personal context stay siloed in Google, Instagram, YouTube, ChatGPT and every other app you use?
You might use ChatGPT multiple times a day.
But you also:
- Post your trips on Instagram
- Watch interesting videos on YouTube
- Use Google to search, discover and navigate the web
Right now, each app sees a slice of you. None of them see the whole person.
Fabric changes that.
With Fabric, you can bring rich personal context from your Instagram stories, Google searches, YouTube watch history and more into AI apps like Claude and ChatGPT. So your AIs stop being clueless agents and start feeling more like friends who actually get you.
Context that evolves with you. And moves with you.
Not trapped in Big Tech or Big AI.
Because you should be able to use many AI products all perfectly tailored to you, instead of being forced into using one or two products that lock you in with your context.
Our vision is simple: just like Visa lets you pay anywhere in the physical world with one card, Fabric lets you sign in with your personal context anywhere in the digital world.
If this resonates, sign up at https://t.co/6cjgGVVWVk.
And comment “Fabric” to get early access to our beta. I’ll reach out and personally onboard you.
@jasonfried 1/ audio slows you down. "speed of thought" > "speed of speech"
2/ higher cognitive load. screen is "all at a glance". with audio, you CACHE things in your head
3/ writing is as natural as grunts. humans drawing since dawn of time
-- if it's audio = it will fail, deservedly so
@lqiao How did you optimize Firefunction-2 for function calling:
1/ positive examples ONLY, or
2/ positive AND negative examples?
-- function calling has "few ways to do it right, many ways to go wrong"
-- negative examples help for such cases: https://t.co/2wQwxW1HMB
"Speed of thought" is faster than "speed of speech".
Chat-based interfaces for LLMs are a crutch.
You will interact with LLMs using buttons, toggles and command-line suggestions