Curistrials
Clinical research
An AI-powered platform for clinical-trial recruitment, participant screening, communications, qualification, and follow-up.
Live product · curistrials.com (opens in a new tab)
Building intelligence people can use.
Arhat Labs is an applied AI lab conducting fundamental research and building intelligent products for businesses and individuals. We create AI agents, AI-native operating systems, and consumer applications designed to make advanced intelligence accessible to everyone.
ResearchAgent infrastructureProductsReal-world impact
Research and deployment belong together.
We believe the most important advances in AI will emerge from a continuous loop between research and real-world use. Our research helps us understand and govern increasingly capable systems. Our products reveal the practical problems that research must solve.
Research
Understanding how AI systems reason, represent information, and act.
Business agents
Building agents that can understand workflows, use tools, coordinate information, and complete meaningful work.
Consumer applications
Giving individuals access to capabilities that previously required assistants, specialists, or extensive preparation.
A portfolio built by shipping.
Each product below came out of a specific workflow we set out to understand. We say plainly where each one stands today.
VistaraOS
Healthcare operations
An AI-native operating system for psychedelic medicine and specialized healthcare organizations, connecting patient care, clinical research, operations, and compliance.
Live product · vistaraos.com (opens in a new tab)
PaniniOS
Business operating systems
An AI-native operating system for small and midsized businesses. PaniniOS learns how a company operates, connects its existing tools, and helps create agents that perform operational work.
Live product · paninios.com (opens in a new tab)
AutoScreen
Talent intelligence
An AI interviewing and talent-evaluation platform that helps organizations conduct structured interviews, evaluate candidates, and make better hiring decisions.
Live product · autoscreen.ai (opens in a new tab)
MakeMyCall
Consumer agents
An application that lets people delegate phone calls to AI agents, reducing the time and friction involved in everyday tasks.
Live product · makemycall.ai (opens in a new tab)
Rehearse
Consumer communication
A private AI practice environment for difficult conversations, including interviews, negotiations, workplace situations, dating, and conflict resolution.
Live product · getrehearseapp.com (opens in a new tab)
Matilda
Conversational commerce
An AI-powered storefront and operations platform for Matilda's Bloombox. Customers design flower arrangements through a conversation with an AI florist, while supplier orders are drafted automatically for human approval.
Pilot
CRE Insights
Commercial real estate intelligence
An agent-operated research and sales platform for businesses serving commercial buildings. It combines property data, ownership intelligence, decision-maker discovery, CRM workflows, and human-approved outreach.
Pilot
Enterprise AI Systems
Custom enterprise agents
Governed AI platforms that automate complex workflows involving documents, email, institutional knowledge, evaluation, reporting, and human decision-making.
Client engagements · More
From complex workflow to intelligent system.
We build production systems, not demonstrations. That difference shows up in what happens after the first working version.
Understand
We study the real workflow, including exceptions, incentives, existing tools, and human judgment.
Build
We create the data, integration, retrieval, agent, and interface layers required to operate reliably.
Evaluate
We measure outputs against real examples and capture structured human feedback.
Deploy
We introduce the system gradually, with clear permissions, auditability, and human review.
Improve
The system becomes more useful as it accumulates feedback, operational context, and institutional knowledge.
A demonstration only has to work once, for an audience that wants it to. A production system has to work on the exception, on the malformed document, on the Friday afternoon nobody is watching — and it has to be reviewable when it does not.
Researching the foundations of trustworthy agency.
Two threads run through our research: what a system is actually doing internally, and what it should be permitted to do in the world.
arXiv preprint, June 2026
Behavioral Governance for Autonomous AI Agents: The AgentBound Framework
Research into runtime governance for autonomous agents. AgentBound evaluates proposed agent actions against delegated authority, behavioural policies, and environmental constraints before execution.
Active direction
Mechanistic interpretability
Research into how neural networks represent concepts, process information, and produce behaviour. The goal is to make advanced AI systems more understandable and easier to evaluate.
This is ongoing work. Nothing in this direction has been published or peer-reviewed — we will link results here when there are results to link.
AI that works inside the business, not beside it.
Most organizations do not need another chatbot. They need systems that can understand their information, coordinate existing software, preserve institutional memory, and perform work under appropriate human supervision.
Capabilities
Information
- Document intake and structured extraction
- Research and knowledge retrieval
- Integration with existing tools and data systems
Action
- Workflow orchestration
- Email and communication agents
- Voice agents
- CRM and pipeline automation
Governance
- Evaluation and quality monitoring
- Human approval workflows
- Audit logs and cost visibility
- Secure deployment within enterprise environments
Where this work tends to matter most
Healthcare and clinical research. Financial services. Commercial real estate. Recruiting. Professional services. Operationally complex small businesses. These are industries where the workflows are genuinely complex, the information is unstructured, and the consequences of getting something wrong are real.
Built by experienced engineers and entrepreneurs.
Arhat Labs was started by two people who have spent their careers building systems that had to work — at scale, for real users, with real consequences.
Pranay Gupta
Co-founder
Pranay is a former Staff Engineer and engineering leader at Google with more than 15 years of experience building internet-scale systems across Google Ads, Search, and Cloud AI. He led the development of enterprise conversational and voice AI systems used by major global organizations and helped build automation deployed by brands including McDonald's, Wendy's, and Burger King.
Prakhar Gupta
Co-founder
Prakhar is a serial entrepreneur and former AI product leader with experience building and scaling technology businesses. He co-founded LetsMD, grew the organization from an early-stage company into a team of approximately 50, and helped pioneer healthcare financing and pricing-transparency products in India.
Let's build something genuinely useful.
We work with organizations that have valuable workflows, complex information, and a serious reason to apply AI.