[ad_1]
Simular, a startup constructing AI brokers for Mac OS and Home windows, has raised a $21.5 million Sequence A led by Felicis, with current seed buyers NVentures (NVIDIA’s enterprise arm), South Park Commons, and others becoming a member of in.
Simular is an fascinating agentic startup as a result of not like others, it isn’t making an attempt to manage the browser however the PC itself. (Agentic AI refers to methods that may autonomously full complicated duties with minimal human intervention.) “We will actually transfer the mouse on the display and do the press. So it’s extra able to doing, repeating no matter human actions within the digital world,” co-founder CEO Ang Li informed TechCrunch, providing the instance of copying and pasting information right into a spreadsheet.
On Monday it introduced the discharge of its 1.0 model for Mac OS. Nevertheless it’s additionally working with Microsoft to develop an agent for Home windows. The startup is one in every of 5 agentic corporations accepted into the Home windows 365 for Brokers program Microsoft introduced in mid November. (The others are Manus AI, Fellou, Genspark, and TinyFish.) As for the timeline for the Home windows model, Li was obscure besides to say it guarantees to be as or extra fashionable than the Mac model.
Another excuse to observe Simular is the bona fides of the founders: Li is a steady studying scientist who beforehand labored at Google’s DeepMind, the place he met his cofounder, reinforcement studying specialist Jiachen Yang. Whereas their staff printed their justifiable share of papers, the work wasn’t strictly educational, Li mentioned. It was meant to enhance Google merchandise, together with Waymo.
That AI product background is useful as a result of, earlier than the agentic way forward for Silicon Valley’s goals can materialize, there are a number of technical issues to resolve. One of many largest is that LLMs hallucinate some proportion of the time.
Agentic duties can require finishing hundreds to hundreds of thousands of discrete steps. Not solely can a hallucination at any single step invalidate all the agent’s work, however hallucinations grow to be statistically extra probably because the variety of steps grows.
One method to remedy that is to make the “non deterministic” LLM “deterministic,” which means as a substitute of permitting the LLM to be endlessly artistic, its responses or actions are scripted the identical every time. However that dangers limiting the entire artistic drawback fixing side of an agent.
Techcrunch occasion
San Francisco
|
October 13-15, 2026
Simular is marrying the 2. Its agent will iterate freely on the duty, with the human person within the center course correcting, till the agent achieves success. Then the human locks in that job’s workflow, which makes it deterministic, repeatable.
“Our answer is, let brokers maintain exploring the profitable trajectory. When you discovered a profitable trajectory, that turns into deterministic code,” Li explains.
The explanation the startup can do it is because its work – which Li admits remains to be early – isn’t just an LLM wrapper that sends and retrieves information to a mannequin.
“We’ve got a brand new know-how which isn’t utilized by every other agent firm. We name it ‘neuro symbolic laptop use brokers.’ It’s not totally LLM based mostly,” he mentioned. “Our method to resolve hallucinations is to let the LLM write code which turns into deterministic. So if in case you have a workflow that works, the following time we run the identical workflow, it’ll achieve success as effectively.”
One other profit is that this deterministic code that performs a repeatable job is within the arms of the top person, not the LLM. “As soon as they’ve the code, they will belief it, as a result of they will examine it, they will audit it, they will see what’s happening,” Li says.
Time will inform if this methodology is the magic that may carry brokers into the arms of each employee. Li says his early beta prospects embrace a automotive dealership automating VIN quantity searches, and HOAs extracting contract data from PDFs. And the corporate’s open supply mission (accessible just for Mac OS in the intervening time) has led to automations starting from content material creation to gross sales and advertising.
Simular beforehand raised a $5 million seed, bringing its complete raised to about $27 million. Different buyers within the firm embrace Foundation Set Ventures, Flying Fish Companions, Samsung NEXT, Xoogler Ventures, and podcaster and angel investor Lenny Rachitsky, the corporate says.
[ad_2]
{content material}
Supply: {feed_title}