AI coding workflows
Workflows that matter.
Agent choice gets easier when you start from the job. These are the recurring workflows worth testing before a team settles on a tool.
Building new software where there are no legacy users, contracts, or behaviours to preserve.
Writing quick throwaway code to test feasibility, compare options, or expose unknowns.
Creating a minimal version of a solution to test a product, technical, or workflow hypothesis.
Keeping existing systems running through small updates, dependency work, operational fixes, and routine changes.
Restructuring code without changing behaviour, while preserving tests, contracts, and user expectations.
Improving speed, memory usage, latency, cost, or throughput with evidence from measurement.
Replacing old code with new code while managing feature parity, migration risk, and rollout.
Moving code to new platforms, runtimes, frameworks, or programming languages.
Tracing issues through existing code, logs, tests, reproduction steps, and runtime behaviour.
Diagnosing defects, making targeted changes, and proving the fix with a focused verification path.
Writing unit tests, integration tests, regression tests, or repairing failing test suites.
Evaluating code for correctness, quality, maintainability, security, standards, and missing tests.
Writing or updating technical docs, comments, READMEs, runbooks, API notes, and migration guides.
Managing deployment, configuration, environments, pipelines, and infrastructure as code.
Understanding unfamiliar, old, under-documented, or high-risk codebases before making changes.
Learning a new programming language, technology, tool, framework, or technique through guided practice.