AI-native SDLC for a food-tech company's India engineering pod: AI-assisted development and automated code review

Thistle, a $100M+ revenue food-tech business, needed more engineering throughput to keep pace with growth, without adding to its engineering headcount. The answer was a new engineering pod in India, run as a fractional engagement through Studio Management. That brought its own risks: a new, small team had to ramp up on an existing production codebase, work across time zones from the core team, and ship at the pace the business needed while keeping review quality high. With only two engineers, adding people or review rounds was not an option, so the process itself had to get faster.

I set up and led the India pod as fractional engineering lead, and built its delivery process around AI from day one instead of adding it later. AI-assisted development: engineers ran Claude Code and Codex sessions in parallel through Conductor, each in its own isolated workspace, going from ticket to PR. Custom skills encoded the team's conventions and repeatable tasks so the agents worked the way the codebase expected. Designs came from Figma, so agents and engineers built from the same source. Automated code review: every PR got a first-pass AI review in GitHub CI before a human looked at it, catching routine issues such as bugs, missed edge cases and inconsistencies early. Human review could then focus on design and business logic, and time-zone round trips were not spent on nits. The workflow became the pod's standard way of working, and delivery was measured by ticket-to-PR lead time.

Ticket-to-PR lead time fell from about three days to about one, roughly 3x faster from ticket to reviewable code. The pod contributed to 30% revenue growth at Thistle without additional engineering hires.