
Can A Chatbot Be Your Therapist? Casper's Neil Parikh Launches A New $93 Million Startup To Try
N eil Parikh's first startup Casper made sleep easy—and even cool. The med school dropout used tech to help people buy mattresses with just a few clicks. Now he wants to make getting therapy just as simple.
After turning the sleep brand into a billion-dollar business, the Forbes Under 30 alum is back with a new venture: Slingshot AI, a startup building a chatbot designed to replicate the experience of talking to a therapist.
'I never really thought about therapy,' Parikh told Forbes . 'Then I found a therapist who changed my life.' That's how it clicked for the entrepreneur. While millions struggle with mental health issues, access to care is staggeringly limited. 'We realized there's over 10,000 people who want care for every therapist that's out there,' he said. 'There was an opportunity for AI to actually help people in a new way.'
On Tuesday, Slingshot officially launched its AI-powered therapy bot, called Ash, and announced a follow-on Series A round co-led by Radical Ventures and Forerunner Ventures, with participation from existing investors Andreessen Horowitz, Menlo Ventures and others. The round brings Slingshot's total funding to $93 million as it emerges from beta after being tested with more than 50,000 users.
Parikh founded the startup with Daniel Cahn, a machine learning engineer who previously worked on AI tools for mental health in the UK. Unlike general purpose models like ChatGPT—which pull data from the internet—Ash was developed in collaboration with clinicians and trained specifically on behavioral health data. It doesn't offer advice or try to diagnose, but is instead designed to guide users more through self-reflection, similar to how a therapist might prompt deeper thinking.
Andreessen Horowitz's a16z was quick to back the entrepreneur. Daisy Wolf, partner at the firm, said they'd been actively looking for a startup bringing AI into the mental health space, handing Slingshot a term sheet as soon as the team was ready to raise. 'They have the experience and know how to pull this off. They've been absolute magnets for talent, and the caliber of people they've been able to recruit has continued to blow us away,' Wolf said.
Parikh was 22 when he dropped out of medical school to build Casper. The company wasn't the first to sell mattresses online, but it was the first to become a household name with mattress-in-a-box convenience and a wellness-focused message that turned sleep into a lifestyle. Celebrity endorsements and subway ads helped build the brand amongst a younger audience. Parikh went all in and even co-authored a book on sleep.
Casper went public in 2020 at $12 a share—below its target range—and returned to private ownership two years later. He stepped down in 2021 and fully exited the board after the sale. Since then, he's invested in more than 150 startups, many tied to mental health.
Now back in the founder seat, he says building from the ground up is both daunting and exciting. 'Every part of this business is really challenging when you think about it. You have to build a large scale data set through partnerships. You have to build a team that knows how to train AI models. You actually have to learn how to train the models,' he said.
The burning question: Can a chatbot really compare to a human therapist?
Though the concept of AI therapy might seem experimental, early evidence suggests it could have real potential. At Dartmouth College, researchers developed and tested their own chatbot therapist called Therabot. In a trial of more than 100 people with mental health conditions, all improved. Those with depression saw a 51% symptom drop on average.
Nicholas Jacobson, one of the clinicians behind Therabot, said chatbots can offer several advantages over traditional care, including cost, convenience and 24/7 availability. Even individuals who had not previously responded to therapy saw significant improvement with Therabot. "A full caseload is about 26-and-a-half patients a week for a practicing therapist,' he said. 'They will see their patients generally once a week in outpatient settings for about 45 minutes.'
In that case, why not use the widely popular generative AI models like ChatGPT or Google's Gemini? While these models are incredibly advanced, they aren't designed specifically for mental health care, Jacobson said, and can be potentially harmful. At Dartmouth, this meant researchers had to build their own data from scratch. At Slingshot, it means partnering directly with clinicians—and using that $93 million to build a better data pipeline.
And, Parikh adds, general models can be somewhat of yes-men. 'You want them to appropriately push back on you. That's a core part of self growth.'
Courtesy of Slingshot
Still, not everyone is convinced chatbots can handle mental health responsibly. Critics have raised concerns about safety and privacy. Slingshot says it's proactively addressing these issues by working with a clinical advisory board. Ash, for example, redirects users experiencing a serious crisis to human professionals.
This time around, the serial entrepreneur (who's gone to plenty of therapy since) wants to keep the company lean and mission-driven. For its initial launch, Ash will be available for free to users, and Parikh imagines rolling out a subscription model priced similarly to Netflix. In the future, there may be avenues for Ash to be available via employers or insurance.
In the meantime, Parikh says he isn't trying to reinvent therapy, but hoping Ash might just help more people start it.
'Doing anything that nobody's done before means that you have to figure out a lot of new things,' he said. 'It's a lot of unknown nodes, but it's also cool because every day we get to wake up and get feedback from people who say this is incredible and their lives changed.'

Try Our AI Features
Explore what Daily8 AI can do for you:
Comments
No comments yet...
Related Articles
Yahoo
19 minutes ago
- Yahoo
Walmart bets on AI 'super agents' to boost e-commerce growth
STORY: Walmart is deepening its push into AI, unveiling four new "super agents" on Thursday, aiming to improve the shopping experience and better compete with rival retailers. Powered by agentic AI - which needs minimal human intervention - the super agents will serve as primary entry points for every AI interaction with Walmart shoppers, store employees, suppliers and sellers, and software developers. The new agents will replace several existing AI tools, and the retailer hopes they'll attract more shoppers away from Amazon, which has its own range of AI-powered tools. One of Walmart's agents, Sparky, is already available on its app as a Gen-AI powered tool, where it currently assists customers with product suggestions, such as athletic wear or the right ink for a printer. In its "super agent" form, Walmart says Sparky will be able to plan themed parties and offer product recipes by looking at the contents of a shopper's fridge through its computer vision. Another super agent, Marty, is being developed for sellers, suppliers, and advertisers in an effort to streamline the onboarding process, manage orders and create ad campaigns. Walmart declined to say whether the super agents would replace human jobs.
Yahoo
19 minutes ago
- Yahoo
New data from Global Water Intelligence reveals impact of hyperscale data center boom on onsite water consumption and unprecedented growth in water technology and infrastructure spending
OXFORD, United Kingdom, July 24, 2025 (GLOBE NEWSWIRE) -- New research from GWI has found that onsite water consumption for data center cooling is forecast to increase by just over 50% by 2030, despite data center capacity doubling over the same findings reflect significant efficiency gains in water use, with a shift to water-efficient cooling technologies. These technologies require higher quality water, and GWI therefore predicts that these strides in responsible water use will be supported by unprecedented double digit annual growth in water-related technology and infrastructure spending for data centers. Hybrid air-water cooling, as well systems designed for AI workloads, where chips are in direct contact with a water-based coolant, are increasingly the norm for data centers. Additionally there is a shift to lower-quality recycled water as the sector cuts its freshwater use. However, the extent of these efficiency gains is not globally balanced, nor are they always related to concerns of water stress. In India, for example, data center water use is set to more than double by 2030, posing major risks in a country already facing extreme water stress. Data centers can reduce their onsite water footprint by switching to dry cooling, but this drives up energy use, leading to greater indirect water consumption from power generation. As power demand continues to surge through 2030 and beyond, water-efficient cooling will be essential to the sustainable growth of data centers. Access the full dataset via our rich forecast data dashboard. Book a demo directly at For general inquiries contact: sales@ About Global Water Intelligence Global Water Intelligence (GWI) is the leading market intelligence and events company serving the international water industry. Over the last 25 years we have built our business around being a trusted interface between our clients and their markets, providing our customers with high-level intelligence that enables them to make the most informed strategic decisions for their business. We cover municipal markets and every industrial vertical as well as technology, finance and economics. GWI runs an advanced manufacturing conference focusing on semiconductors and data centers: CONTACT: Victor SmithCOMPANY: Global Water IntelligencePHONE: 01865 204208 EMAIL: sales@ A photo accompanying this announcement is available at
Yahoo
19 minutes ago
- Yahoo
ServiceNow (NOW) Stock Soars After Smashing Q2 Targets Amid AI Boom
July 24 - ServiceNow (NYSE:NOW) shares surged more than 5% in Thursday morning trading after the enterprise?software firm posted a strong second quarter driven by AI?related growth. Warning! GuruFocus has detected 3 Warning Sign with NOW. Subscription revenue climbed to $3.113 billion, up 21.5% year?over?year in constant currency and exceeding guidance by roughly two percentage points. Operating margin widened to 29.5%, more than 2.5 points above projections, while free cash flow margin rose to 16.5%, up three points from last year. Remaining performance obligations reached $23.9 billion, a 25.5% jump, with current RPO at $10.92 billion, up 21.5%. ServiceNow closed 89 deals over $1 million in net new annual contract value, including 11 above $5 million, as renewal rates held at 98%. The company ended the quarter with $10.8 billion in cash and investments and repurchased about 381,000 shares under its $2.6 billion buyback authorization. Management raised full?year subscription revenue guidance by $125 million to a $12.775 billion$12.795 billion range, signalling roughly 20% growth. Third?quarter subscription revenue is expected between $3.260 billion and $3.265 billion, with operating margin forecast at 30.5%. CEO Bill McDermott noted rapid adoption of its AI Pro Plus platform, which may drive larger deals and deeper customer engagement going forward. This article first appeared on GuruFocus.