BREAKING NEWS: SF and LA Tech Week calendars are LIVE!
You can now register for events: https://t.co/IElfyON9rg
2,300+ event submissions across San Francisco and Los Angeles
📍SF: October 5-11
📍LA: October 12-18
People always ask about the data, so a few stats:
-SF once again takes the crown for “biggest tech week ever” with 1,500+ events
-1 in 7 SF events is about agentic AI: 213 events in SF and 53 in LA are explicitly about agents (in the title or description). In 2024 there were only about a dozen!
-There are 124 hackathons across the two weeks, and the variety is huge: everything from hardware to defense, media/creative, fintech, civic/social good, etc. Everyone is a builder now.
- LA, the OG Tech Week (now in its fifth year!), has seriously doubled down on deep tech with 100+ events and lots of El Segundo activity.
Last year, Tech Week saw attendees from over 100 countries. It’s going to be a party.
See you there! 🥳
I saw this post and had to give it a try. I finally deployed my personal website using @convex@bot@Cloudflare after putting it off. https://t.co/VtSEwuvGJk
Ok sold on @cursor_ai@bot . I got access, installed @convex & @Cloudflare plugins, built a demo site with convex as the backend & frontend, purchased domain name and setup redirect rules with cloudflare. All in just 2 prompts on my phone.
Demo app https://t.co/sqaXIraVer
In this first episode, I share my desire for Decora, my interior design agent, to be more agentic in practice rather than theory. The first step was setting up her MCP server that will lead to everything else.
I'm excited about what comes next, so stay tuned!
https://t.co/vUdlpX4CBg
NEW VIDEO DROPPING TOMORROW!
Decora, my interior design agent, has agent in the name and nothing agentic about her. So I'm agentifying my homegirl one decision at a time, starting with the foundation every later decision depends on.
https://t.co/Bcp53pYCn2
Road to Agentic, episode one.
Anthropic senior engineer just released a 1-hour course on building a team of agents with loops & graphs:
• 00:27 - introduction to CLAUDE.md & Plan mode
• 11:24 - building "skills" & "hooks" for Claude agents
• 37:02 - building agents & subagents with Claude
• 52:47 - self-improving loops & graphs for Claude agents
this 1-hour watch will replace a $500 agentic engineering course
watch today, then read how to build a team of self-improving agents that work together
Anthropic hired this engineer at $250K-$750K a year because he knows how to build harnesses for multi-agent systems
In this 15-minute workshop, he shows exactly how to build one from scratch
AI → Agents → Harness → Loops → Graphs
step 1 → start with the Claude Agent SDK - the harness handles loops, context, and sandboxing
step 2 → separate the brain from the hands - reasoning in one place, tools in a sandbox, 60% faster to first token
step 3 → run it server-side and log every step - close your laptop and it keeps running, crashes resume from the log
step 4 → make failure cheap - retry dead sandboxes and replay lost context instead of starting over
step 5 → turn yesterday's logs into new memory and skills - the harness wakes up smarter
Anthropic calls this "dreaming"
Most people spend weeks building this by hand
You don't have to
Bookmark and watch it
Then read the full harness engineering guide below ↓
SpaceXAI engineer, Lauren Tan:
"GrokBot is the most powerful agentic tool we have ever shipped, but only 1% of users use it correctly|
at SpaceXAI, I'm running a team of 15+ GrokBot agents. I have a Chief of Staff agent, 3 managers and 11 workers - that's the new engineering setup in 2026"
In a 1-hour talk, a SpaceXAI engineer reveals how to get 100% of every agentic tool you are using
worth more than a $500 agentic course on the internet
skip Netflix and watch today, it will change the way you use GrokBot forever, then read the article below
@APIWorld 2026 Day One! Of course we’re talking about the impact of long running requests, costs, latency, using web crawled data to feed LLMs. Looking on to what’s next.
Here's a blog by @addyosmani I had a chance to read that validated a project I'm working on around the idea of not losing recipes (domain knowledge) as we build agentically. That is, specifically for junior devs to treat AI tools like pair programmers or cointelligence to build fast while gaining the fundamental knowledge required for system design, code review, etc.
Good read.
https://t.co/SkhV4YUXpL
We’re giving you full permission to be nosy.
August 26, we’re opening up our laptops to show you what we’ve shipped recently.
Peek behind the scenes → https://t.co/GieqSlegOu
If @Braums_IceCream ever goes out of business, I might riot. It's my favorite place to go after a long session of talking to claude and her cousin codex.