
Shubham Saboo
@Saboo_Shubham_ • 122,752 subscribers
Senior AI Product Manager @google | Open Source Awesome LLM Apps Repo (#1 GitHub with 140,000+ stars) | Author of books on GPT-3 & Neural Search | My views
Shorts
Videos

My mind is f*** blown. I built this live insurance claim agent that can see, talk, think and draw in real-time using the new Gemini 3.8 LIVE. Even switched my language to Hindi mid-call and it still worked. VOICE AI can't be more real. Made it 100% open-source.
Shubham Saboo121,539 Aufrufe • vor 1 Monat

INSANE. This is 100% Open Source version of Grok Bot. Works with any Agent harness. Let that sink in.
Shubham Saboo203,374 Aufrufe • vor 1 Monat

INSANE. Voice AI Agents getting better every other week. I'm now talking to a live avatar of my insurance claim voice agent. It can see, talk, think and draw in real-time now with a face. Switched to Hindi mid-call and it still worked. Made it 100% open-source.
Shubham Saboo32,518 Aufrufe • vor 21 Tagen

Codex /goal With Hermes Agent is life-changing. I updated my Hermes agent skill to give Codex a goal on the fly using Telegram and track each one of those codex goals in a Kanban board. It has been really insane to see and track Codex execute goals in the wild.
Shubham Saboo202,128 Aufrufe • vor 5 Monaten

SPEC IS BECOMING THE PRODUCT An Anthropic engineer gave Claude a spec, pointed it to an Asana board and left for the weekend. Claude broke it into tickets and spun up a team of agents. The agents started picking up tasks on their own. No one told them to. They just did.
Shubham Saboo285,749 Aufrufe • vor 7 Monaten

How I built an AI Agent team that runs 24/7 explained in 19 minutes. OpenClaw is where the squad started. Hermes is where it's evolving. YES, I use both of THEM just via Telegram. 4 things that makes my agent team work like humans: - Automated Cron: Agents run pro-actively on schedules and heartbeats - Memory: They keep context about my preferences, audience, past performance, and decisions. - Self-improving review loops: Each agent reviews its own work monthly. Monica reviews the entire squad bi-weekly and grades them. - Escalation: They do the work, but I still make the final decision. These agents manage the open-source Awesome LLM Apps repo with 115k+ GitHub stars and help me stay up-to-date with pro-active daily signals. I operate like a CEO reviewing a squad from my phone. The agents keep the work moving until I have to step in.
Shubham Saboo141,325 Aufrufe • vor 3 Monaten