Pinned Tweet
Excited to announce a new venture for me -- yet another video podcast!!!
First episode is with @engineerrprompt
- CLI > IDE even for vibe coders?
- Learning Syntax is in the past
- and much more
Using @RiversidedotFM for full production.
youtu.be/9ucS8vRAT1E
Abraham Gomez retweeted
Officially a month out from Google Cloud Next!
Yesterday was rehearsals for the Developer Keynote. A dream team line up of folks and a really fun theme this year. 👀
Excited to see everyone in Vegas soon.
#GoogleCloud
Abraham Gomez retweeted
Introducing the all new vibe coding experience in @GoogleAIStudio, feating:
- One click database support
- Sign in with Google support
- A new coding agent powered by Antigravity
- Multiplayer + backend app support
and so much more coming soon!
xitter.cf/GoogleAIStudio/status/…
Abraham Gomez retweeted
if you are a startup, building on top of any of our platforms - come to our office hours in SF!
🌉 San Francisco: LangSmith for Startups Office Hours
📣Calling founders, engineers, and founding teams to join us on a Friday morning for office hours.
Come ask our Head of Product, PMs and Deployed Engineers your burning agent development questions + get updates + give us your feedback.
Or, come chat and learn how to better ship great agents!
🗓️ March 27 | ☕️ 8:30 AM | 📍San Francisco (SOMA)
RSVP: luma.com/rb85h5l5
Abraham Gomez retweeted
All good things start with a plan 📝
Plan mode is now live in @geminicli 🚀
Read-only mode with access to MCP tools, Agent Skills and built to be fully extensible to your needs!
Use Shift+Tab or ask "Create a plan for..."
Announcement blog below 👇
I'm finding that the best vibe coders really are disciplined and patient with sharing their axes vs going full yolo more.
Each development in a harness and models makes running enticing until you hit a wall.
Sharpening an ax is really underrated
Abraham Gomez retweeted
Gemini 3.1 Flash-Lite is the model to build always on multimodal AI Agents.
I just built a memory agent with Google ADK that runs 24/7. Feed it text, images, audio, video or PDFs. It reads, connects and consolidates everything while you sleep.
100% Opensource code.
Abraham Gomez retweeted
Work on whatever you want. With people you like. Wherever you happen to be. That used to be a fantasy reserved for the already-wealthy. AI is making it the default path for anyone willing to learn the tools and do the work. This isn't hype. I'm living it. And so are thousands of solopreneurs you've never heard of.
I used to say that for an early stage startup, Everyone is a seller and a builder. I feel this is the case for any lean organization really.
PMs at Notion are shipping pull requests. Product managers writing and merging code into production. A year ago that sentence would’ve gotten you laughed out of a product leadership Slack.
Figma’s PM org reportedly cut their average feature cycle from 6 weeks to 3 after standardizing Claude Code workflows internally. Linear’s team has talked publicly about PMs prototyping directly in their codebase.
This tells you everything about where PM hiring is headed. The gap between “PM who can go from insight to working prototype” and “PM who writes a spec and waits 2 sprints” is becoming the new senior vs junior divide. Except it has nothing to do with years of experience.
The last time a tool shift redrew PM job descriptions this fast was when Figma made every PM a passable wireframer around 2019-2020. That took 2 years to become table stakes. Claude Code is moving faster because the output is code, not mockups, and code ships.
Abraham Gomez retweeted
PMs at Notion are shipping pull requests. Product managers writing and merging code into production. A year ago that sentence would’ve gotten you laughed out of a product leadership Slack.
Figma’s PM org reportedly cut their average feature cycle from 6 weeks to 3 after standardizing Claude Code workflows internally. Linear’s team has talked publicly about PMs prototyping directly in their codebase.
This tells you everything about where PM hiring is headed. The gap between “PM who can go from insight to working prototype” and “PM who writes a spec and waits 2 sprints” is becoming the new senior vs junior divide. Except it has nothing to do with years of experience.
The last time a tool shift redrew PM job descriptions this fast was when Figma made every PM a passable wireframer around 2019-2020. That took 2 years to become table stakes. Claude Code is moving faster because the output is code, not mockups, and code ships.
I've been building in Claude Code non-stop for 6 months.
Today I'm releasing everything I've learned as a copy-paste PM Operating System:
41 skills
7 AI sub-agents
My Claude md file
I made all the mistakes so you don't have to:
news.aakashg.com/p/pm-os
For any early founders considering accelerators, this is my shortlist:
• @HF0Residency (SF)
• @ycombinator (SF)
• @spc (SF/NYC/BLR)
• @sequoia Arc (US/EU)
• @pearvc PearX (SF)
• @Neo (SF)
• @conviction Embed (SF)
• @a16z Speedrun (SF)
• @fdotinc (SF)
Abraham Gomez retweeted
there are 250 million+ public repos on GitHub
open-source Awesome LLM Apps is just weeks away from being in the top 100 Github repos of all time (91k+ stars already!)
building in public and open-source is the way to go.
thank you amazing community :)
Abraham Gomez retweeted
interrupt year 2!
Will be more people, more speakers, more days, more events
tickets dropping soon 👀
🎉📅 Interrupt 2026 — the AI Agent Conference by LangChain — is back May 13-14 in SF
1,000+ practitioners. Production agents. Real world lessons.
Why you should come:
→ Hear from teams scaling agents in production
→ Get hands-on in workshops with the LangChain team
→ See new product drops first
→ Connect with builders solving the same challenges you are
🎟️ Tickets drop Feb 12 — seats are limited
Sign up to get notified: interrupt.langchain.com/?utm…
Abraham Gomez retweeted
Introducing Agentic Vision with Gemini 3! 👀🔥
Gemini can now write and execute code to zoom, annotate, inspect, and plot directly with vision input, all while leveraging it's advanced reasoning capabilities
Highly recommend this read if you want to better conceptualize MCP vs Skills (you should be using both btw) kvg.dev/posts/20260125-skill…
First actual test with @openclaw gave it my youtube video podcast to see how good can it scan a 51 minute episode and grab sound bites...
These are the 4 out of the 5 sound bite I manually selected myself.
Next step is automating this process for marketing my shorts. :,)
























