Coding agents & developer workflows
Evaluation, sandboxing, code review, security, and adoption practices for AI coding agents.
Research brief: what agent-authored code studies say teams should measure
A source-backed research brief on AI coding agent adoption studies and the metrics teams should track before scaling developer automation.
A simple evaluation loop for AI coding agents
A builder-focused tutorial for testing coding agents with repository task sets, sandbox constraints, review gates, and regression checks.
AI pull request review checklist for agent-authored code
A checklist for reviewing AI-generated pull requests across correctness, maintainability, tests, dependencies, security, and repository fit.
AI coding agent pricing brief: what usage-based plans change for teams
A brief on how usage-based AI coding plans change pilot design, budgets, review cost, and governance for developer teams.
Coding agent sandboxing guide for local, cloud, and CI workflows
A guide to sandboxing coding agents with filesystem boundaries, command allowlists, network controls, secrets handling, and CI checks.
Research brief: coding agents need security gates before broad repository access
A source-backed brief on practical security controls for AI coding agents, including sandboxing, command review, secrets handling, and dependency risk.
A practical open-source LLM stack for teams starting from zero
A field guide for choosing local model runners, inference servers, model libraries, retrieval layers, and evaluation tools without overbuilding the first stack.
Prompt evaluation playbook for teams that cannot afford silent regressions
A tutorial for building prompt evals, golden tasks, grader rubrics, and release gates for production AI workflows.