From Skeptic to Superpower: Real‑World AI Coding Workflows That Scale | BRK229

Mario Toffia and Priyanka Sharma share a practical look at AI-assisted coding workflows, comparing Claude Code + Cursor with GitHub Copilot CLI and focusing on what works, what breaks down, and how teams can scale usage without losing control over sensitive infrastructure.

Overview

This Build 2026 breakout session compares two day-to-day AI coding setups used by engineers:

The speakers focus on realistic outcomes rather than hype: initial skepticism, where each tool is strong, where it fails, and what changes when a team scales AI-assisted development to larger delivery expectations.

Key themes covered

Background and context

Autonomous/agentic coding workflow with Copilot CLI

Where AI helps (and what it changes)

Reliability and operational risk: “AI collaborators can quit anytime”

Maintaining manual control for sensitive infrastructure

Scaling to a team setting

Session metadata