AI-native development for engineering teams, done safely. I roll out Cursor and Claude Code, train developers, and rebuild review and CI/CD around AI-generated code so output stays fast and trustworthy in production.
Six focused engagements, from curious about AI tooling to shipping AI-assisted code safely.
Cursor and Claude Code set up across your teams with shared rules, prompts, and project context, so every developer starts from the same baseline.
AI ships far more code, far faster : the speed can't cost you reliability. Every engagement leaves behind the review, CI, and evaluation systems that keep AI output safe in production.
A review process for larger, faster diffs : human checklists plus automated review, so AI-authored changes still get real scrutiny.
Pipelines tuned for the volume AI tooling produces : tests, types, and checks catch regressions before anything reaches main.
Merge gates on linting, types, and tests, plus dependency and security checks : faster output never lowers the bar.
Evaluation and classification systems for AI-driven features, drawn from evaluating millions of chatbot events at Dashly.
Two-sided recruitment marketplace with a retrieve-and-rerank pipeline: pre-filtered ANN vector search plus multi-factor re-ranking. Built on an Effect.ts hexagonal architecture with compile-time dependency guarantees.
3,949
Contributions
606
PRs
53
Week Streak
5
Day Streak
Does not include automated bots, issue resolvers, or software factories.
Flexible options to meet your project needs and budget
Tell me about your codebase and where your team is with AI tooling. I will map out how to roll it out and keep the output production-safe.
Book a free call