An AI Researcher building products that ship. Co-Founder @ Interact AI
San Francisco
Joined March 2024
- Tweets326
- Following324
- Followers150
- Likes203
This gold rush has turned into a shovel rush. Everyone wants to sell shovels, but too few are actually digging for gold.
The irony is that when everyone starts selling shovels, digging for gold might become the real deal again.
Utsav Singhal retweeted
Reliable agents are built in layers: trustworthy data, caller verification, scoped tool permissions, and human handoff when the model gets it wrong.
At VapiCon, the people building those layers and the people running agents on them break it down.
Production vs Demo: How to Keep Agents Reliable
Michael Grinich, Founder & CEO @workos
Sourish Biswas, Sr. Product Manager @HOAi
Vidas Bacevičius, Lead Solutions Engineer @oxylabs_io
Utsav Singhal, Co-Founder & CTO @Interact_AI
Sidhant Kabra, Co-Founder @cekura
Fort Mason, San Francisco
November 11–12, 2026
Agenda and tickets: vapi.ai/vapicon-2026
My grok @bot is single handedly replacing real humans and real tools I would hv bought otherwise.
Will be speaking at @Vapi_AI's VapiCon this year. I'll be on a panel on How to Keep Agents Reliable, where we'll cover what keeps agents reliable in production and the importance of data in driving reliable agentic experiences. Lot of interesting ideas and learnings to be shared from @interact_ai .
If you’re also at VapiCon, hit me up. Would love to chat! Here's a speaker discount code "SINGHAL20".
See you at the event.
Finally a way to use the bought band and ditch the @WHOOP subscription.
🚀🚀
Visitors on Sprinto's website spend an average of 7 minutes conversing with an AI agent.
Pranay Gondane, Head of Demand Gen at Sprinto, shares how Interact AI turned those conversations into conversions.
He walked in a sceptic & ran a two-month A/B test. The results changed how people at Sprinto thinks about their website, and how their sales team starts every call.
Sprinto is a compliance platform, so what it really sells is trust. For years, building that trust took a call with a rep. Now it starts the moment a buyer lands on the homepage.
Pranay tells the rest in his own words.
Props to @harshjndigital for setting this up and Nitin Gupta for producing the video.
I'll be speaking at @aiDotEngineer Shanghai talking about what it takes to build a truly multimodal, agentic system which can talk to millions of customers while personalizing the experience to their individual problems.
At @interact_ai, we’ve built an agent builder that can integrate with your knowledge bases, products, and media to create an expert that can not only talk, but also show and interact with the right information.
Whether it’s powering your website to help visitors understand and navigate your product, helping customers explore complex workflows, or training your internal teams, the goal is the same: build an agent that can understand the context, reason about the problem, and dynamically create the right experience for each person.
This is going to be the step 1 for the dream of Internet of Agents.
This is going insane now!! Congratulations @OpenAI
We’re sharing a solution to the Navier-Stokes Millennium Prize Problem, one of the deepest problems at the frontier of mathematics.
The proof was produced by a group of agents, using an OpenAI next-generation model significantly more capable than GPT-6 Astra.
The problem concerns whether the description of smooth three-dimensional fluid motion modeled by the Navier-Stokes equations can break down. It has remained unresolved for roughly 90 years.
That's very sick. I wonder how much you can steer with continuity between scenes.
What if movies were not viewed but experienced?
What if you could star in your own movie?
What if you could change the ending?
xp.koyal.ai
- Choose your genre
- Cast yourself and your friends
- Change the storyline
Create your own adventure. All in 15 minutes.
Introducing Koyal Experiences.
Generate for free now at xp.koyal.ai
Utsav Singhal retweeted
Releasing the model weights and technical report of Kimi K3.
Kimi K3 is our most capable model: a 2.8T MoE model with native visual understanding and a 1M-token context window.
New model architecture: 2.5x the intelligence per unit of compute, not just more params.
Alongside Kimi K3, we're opening up more of the stack behind it — high-performance attention kernels, MoE communication library, and infrastructure for running agent environments at scale.
Model weights: huggingface.co/moonshotai/Ki…
Tech report: github.com/MoonshotAI/Kimi-K…
Tech blog: kimi.com/blog/kimi-k3
Utsav Singhal retweeted
At its peak, Sun Microsystems was valued at 205B (394B if inflation adjusted). Sold software in enterprise servers. Got disrupted by Linux, x86, and commodity hardware. Ended up selling to Oracle for 7.4B, losing 96% of its value.
Open source models running on local hardware can have a similar impact given what’s going on.
Utsav Singhal retweeted
Keeping up with AI news is becoming a full-time job.
So my friend @ivan_bezdomny built HuggingNews, an AI-curated feed that surfaces the news actually worth reading. Soon, it will even personalize the feed using your Hugging Face profile. Been using it for weeks!
Bookmark it, or ask your agent to send you the top 10 stories every morning or night. Less noise. More signal. More building!
huggingnews.com
This is crazy. Can we have @GMHikaru for SF one?
I’m judging a @GrowthX_Club Hermes agent buildathon this weekend!
Excited to meet & interact with the builders and tech folks of Mumbai.
It will be interesting to see & evaluate products people will ship that day!
This is pretty cool.
We made an RFE Scanner to review O-1 visa and EB-1 petitions and check for 97+ reasons for Requests for Evidence.
Lots of folks hit us up when they are stuck with other law firms or questioning the strength of their case.
This tool is a pretty good sanity check on what the gov't could respond with.
Who wants to give it a try?
The most weird experience is buying Chai in SF for 50 times the typical price and people calling it "chaaaeyy lattey"
What is with few folks in SF using "like" a 1000 times in every sentence. Like I don't think like this many "like" are liked in like natural like english. Like there is not much to like about like.
