# Prototyping as Leadership: How a CTO Ships with AI Agents — Hursh Agrawal, The Browser Company

## Executive summary

The speaker argues that autonomous AI agents have fundamentally changed the role of a leader, transforming 'building' from an extracurricular activity into a core job function. By leveraging overnight development loops, leaders can now prototype features, optimize LLM calls, and train custom models with minimal hands-on time. Success hinges on establishing robust organizational scaffolding, including trustworthy CI, feature flags, and rigorous code hygiene.

## Key takeaways

- Building is Now Part of the Job: Due to autonomous coding agents, the manager's schedule can now be used for building. This shift allows leaders to stay current with rapidly changing frontier models and demonstrate capabilities via working prototypes rather than just theoretical discussions.
- The Overnight Development Loop: A core workflow involves a 'co-worker agent' gathering context (from Slack, Jira, Notion) into a comprehensive prompt. This prompt is then handed to a coding agent overnight (4–8 hours), resulting in a report and a functional package ready for review the next morning.
- Judgment Remains Human: While modern models excel at execution, they are not yet reliable at judgment. Leaders must provide high-level context and strategic direction to guide the agents effectively.

## Technical details

- Overnight Feature Development: The process requires setting up a run at 5:00 PM (the 'most important block'). The agent must be instructed to write tests first, test the end-to-end flow with computer use, and ensure the resulting code is split into reviewer-friendly PRs that pass CI checks.
- AI Feature Optimization (Hill Climbing): To optimize LLM calls or agents, collect small JSON dumps of feedback. These are used to create an eval set, which the coding agent then uses to run a hill climbing process overnight until the desired scoring rubric is achieved.
- Custom Model Training: Training custom ML models (e.g., BERT PII classifiers) can be automated by providing training data, business context, and access to an ensemble of frontier models. The agent is instructed to manage the entire lifecycle: provisioning a sandbox EC2 cluster, training two separate models, testing against eval examples, and deprovisioning.

## Practical implications

- Prioritize building artifacts that showcase the vision (the 'vision piece') over critical path work to minimize dependency risk.
- Implement organizational scaffolding: trustworthy CI, feature flags, and a dedicated prototype branch are mandatory for safe prototyping.
- Maintain high code hygiene by submitting small, readable PRs and performing thorough local reviews before involving other team members.

## Topics

AI Agents, LLM Prototyping, DevOps Automation, Leadership Strategy, Code Hygiene, Arc and Dia browsers, Claude Code / DIA, Slack, Jira, Confluence, Notion

Source: https://www.youtube.com/watch?v=bdHaOXZOhcM