How A Prototype Built During A Missed Flight Became A New Gusto Product
Eddie Kim, Gusto co-founder and head of technology, discusses Gusto Co-founder, an AI product that automates business processes for small business owners. Built in 10 weeks by a 5-person team during a missed flight layover, the product lets customers automate tasks like payroll and scheduling through SMS and Slack, while proactively suggesting optimizations and uncovering hidden opportunities like tax credits.
Summary
Eddie Kim, Gusto co-founder and head of technology, discusses Gusto Co-founder, an AI product that automates business processes for small business owners. Built in 10 weeks by a 5-person team during a missed flight layover, the product lets customers automate tasks like payroll and scheduling through SMS and Slack, while proactively suggesting optimizations and uncovering hidden opportunities like tax credits.
Eddie Kim describes how Gusto Co-founder emerged from his personal experimentation with open-source AI tools like Claude and OpenClaw. After setting up his own instance and experiencing the power of AI-driven automation through chat interfaces, Kim had the idea while stranded at London's Heathrow Airport during a missed flight connection. Using five hours at the airport lounge, he built a prototype using Claude Code that allowed users to request custom web applications through natural language prompts.
The prototype evolved through team feedback from a web app builder into the current vision: an AI co-founder that automates recurring business processes that Gusto customers already perform. The product uses data Gusto already has about customers' businesses—including industry, employee count, and historical workflows—to suggest and execute automations. For example, a spa business that manually exports data from MindBody to Google Sheets to calculate commissions can now have this entire process automated, receiving only an SMS requesting final approval.
The development process was unconventional and revealed insights about modern AI-powered software development. A small team of four engineers and one designer worked from a single persistent Zoom call for 10 weeks with no formal specifications, Figma designs, or documentation. Instead, they threw away approximately 50% of written code by prototyping ideas directly and discussing tangible implementations rather than abstract requirements. This approach collapsed traditional role boundaries, with designers writing production-grade code and engineers contributing design decisions.
Gusto Co-founder launched with 500 customers and operates through multiple channels (currently SMS and Slack) with plans to add Telegram and WhatsApp. Beyond automation, it proactively identifies opportunities like R&D tax credits and compliance requirements. Kim mentioned a concrete example where Gusto Co-founder identified $50,000 in R&D tax credits for a pool company that was unaware of the opportunity.
Future roadmap includes expanding connectors to vertical-specific systems (like Curve Dental for dental practices), adding communication channels, and crucially, opening the product to people without existing Gusto accounts or an EIN, enabling aspiring entrepreneurs to use AI automation before formally starting their business.
Key Insights
- Most AI users (99.9% of people) treat AI as a glorified search engine rather than an autonomous agent capable of taking actions, even though the technology promises agentic capabilities.
- Personal hands-on experimentation with tools like OpenClaw revealed insights that reading about the same tools could not provide—the gap between theoretical understanding and direct experience is significant.
- A 5-person team built a production-ready product in 10 weeks using only a persistent Zoom call, no specs, no Figmas, and no formal documentation—succeeding by having a 50% code throwaway rate and prototyping implementations rather than discussing requirements.
- Small business owners immediately understand and embrace automation when shown specific recurring tasks they perform weekly (like manual payroll data manipulation) that take significant time, requiring minimal sales effort.
- Building with AI is now so inexpensive and fast that the challenge shifts from building capabilities to disciplined product decisions about what to exclude, requiring a reversal of previous constraints.
Topics
Transcript
[0:05] I'm here with Eddie Kim, Gusto's co-founder and head of technology. Gusto was in YC's winter 2012 batch and recently crossed a billion dollars in annual revenue and now serves over 500,000 small businesses in the US. In fact, one in five new businesses started today are Gusto customers. Today we're going to talk about a new product they're releasing which Eddie actually built himself called Gusto Co-founder which uses AI to automate running a small business. Welcome Eddie. >> Thanks for having me. >> Cool. So why don't we start? I mean [0:35] actually tell us a little bit about what exactly is Gusto Co-founder? What does it do and who is it for? >> Yeah. So simply…
Full transcript available for MurmurCast members
Sign Up to AccessMore from Y Combinator
A camera that can see through walls
Bill Abster from Applied Electromagnetics discusses his company's breakthrough technology that uses radio waves and high-frequency antennas to create 3D images of objects behind opaque materials. The system processes echoes in real-time using GPUs to generate detailed depth maps, and the company has achieved significant progress in just 4 months by maintaining rapid iteration cycles.
What If We Stopped Using GPUs? | YC Paper Club
A YC Paper Club discussion exploring alternatives to GPU-based computing, featuring presentations on optical computing, neuromorphic chips, and biological computing approaches. Speakers argue that GPU efficiency (FLOPS per joule) has plateaued, necessitating fundamentally different computational substrates inspired by the brain's 20-watt energy efficiency.
Robotic factories that build robots
Tensor is building a 12,000 sq ft robotic factory that manufactures robots, including humanoids and specialized grippers. The company, founded by Berkeley researchers with autonomous vehicle and manufacturing backgrounds, treats the entire factory as a learning system that improves manufacturing processes with each customer order.
New LLMs Are Unlocking Robot-Use Agents
This discussion explores how large language models like Claude (Astra) are enabling robot control through code generation and tool use, building on foundational work like RT2 and visual language-action models. The speakers from Waddle Labs and RoboCurve explain how models trained on diverse data modalities—including web text, computer usage, and coding—are converging toward general-purpose robot agents that can perform complex physical tasks within the next 2 years.
Rocket cargo delivery anywhere on Earth in minutes
Matthew, CEO of Hover Arrow, discusses the company's mission to deliver cargo anywhere on Earth within minutes using rocket technology. The startup has secured $1.37 billion in commercial letters of intent, with primary focus on military applications and emerging interest from industries requiring rapid, temperature-controlled delivery of perishable goods.