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
How To Build The Future: Max Hodak
Max Hodak argues that BCIs represent a fundamental shift from incremental biotech to a precise engineering paradigm capable of restoring senses and potentially extending human lifespan to centuries, with current technology already restoring vision to the blind and paving the way for cognitive enhancement.
Common Mistakes With Vibe Coded Websites
AI coding tools have made professional web design accessible to everyone, but they've also accelerated the spread of visual clichés—like purple gradients and distracting hover effects—that prioritize technical impressiveness over brand distinctiveness and user experience.
Boris Cherny: How We Built Claude Code
Boris Cherny reveals how Claude Code emerged accidentally from a terminal prototype built to test Anthropic's API, emphasizing the philosophy of building for AI capabilities six months in the future rather than today's limitations, and evolving the product through observing latent user demand rather than rigid roadmaps.
More in Business & Entrepreneurship
View all
Do THIS When You Feel Disconnected In Your Relationship | Tony Robbins FULL Intervention
Tony Robbins intervenes with a couple facing a decade of disconnection, revealing how the man's 'tunnel' of professional failure and self-loathing creates withdrawal that triggers the woman's timeline fears, and demonstrates that unconditional love—not biological deadlines or past trauma—breaks the cycle.