Agents For Non-Technical Users
TL;DR
Emergent founders Makund and Madav Jar discuss pivoting from enterprise testing tools to a consumer AI platform that enables non-technical users to build production-ready software, achieving 7 million apps built in 8 months by architecting proprietary infrastructure and hiding technical complexity.
🚀 Platform Evolution & Strategy 3 insights
From Testing to Full Automation
The founders initially applied to YC with software testing automation, discovering that solving verification enables complete software engineering automation.
Enterprise to Consumer Pivot
After finding enterprise sales too slow, they pivoted to non-technical users when internal tools showed viral potential, launching beta in June 2024.
Second-Mover Advantage
Starting later allowed them to learn from competitors' prototyping limitations and capitalize on new model capabilities to focus on production-ready shipping rather than just front-end demos.
⚙️ Technical Architecture 4 insights
Unified Infrastructure
Built proprietary Kubernetes cloud sandboxes instead of outsourcing, ensuring identical build and deployment environments eliminates last-mile deployment failures.
Multi-Agent Orchestration
Deploy specialized sub-agents for testing, API integration, and design searches, managed by a main driving agent to preserve context window efficiency.
Cross-Session Memory
Implemented continual learning where agents generate skills from aggregated trajectories across all user sessions, improving performance on recurring tasks over time.
Full-Stack Tech Stack
Chose Python backend with React frontend to support background jobs and asynchronous processing, anticipating users' growing technical ambitions.
👥 Non-Technical User Experience 3 insights
Global Non-Technical Adoption
80% of users have zero programming knowledge, spanning 190+ countries with 7 million apps built in just 8 months since launch.
Influencer Distribution Strategy
Scaled rapidly through TikTok and Instagram influencer networks rather than traditional sales, targeting users who want to build real businesses.
Interface Simplification
Intentionally hide VS Code editors and code diffs from users after discovering even technical product managers panic at JSON views, prioritizing agent experience metrics.
Bottom Line
Build AI products that hide technical complexity completely while architecting for production-scale infrastructure from day one, as the largest market opportunity lies in empowering domain experts with zero coding skills to ship real businesses.
More from Y Combinator
View all
Personal AI Is the New Personal Computer
Y Combinator CEO Gary Tan details his return to software engineering after a 13-year hiatus, shipping hundreds of thousands of lines of code while running YC full-time by leveraging AI coding tools and developing "token maxing" methodologies that transform exhaustive research and development tasks into solo weekend projects.
How Razorpay Became India’s Largest Payments Company
Harshil Mathur recounts Razorpay's journey from a coding side project to India's largest payments platform, detailing their pivot from education to startups, the year-long regulatory wait that created competitive moats, and how surviving a bank crisis through radical customer transparency cemented their B2B trust foundation.
Beyond Bigger Models: Recursion As The Next Scaling Law In AI
Recursion at inference time—rather than simply scaling model size—may be the next breakthrough in AI reasoning. Recent research on Hierarchical Reasoning Models (HRM) and Tiny Recursive Models (TRM) demonstrates that recursive architectures using shared weights can solve complex reasoning benchmarks like Arc Prize with minimal parameters, outperforming massive traditional LLMs.
How to Build the Future: Demis Hassabis
Demis Hassabis predicts AGI by around 2030 and argues that while current large-scale pre-training and reinforcement learning form the foundation, breakthroughs in continual learning, memory consolidation, and introspective reasoning are still required to achieve true artificial general intelligence.