AI agents are turning software engineers into process engineers

AI agents are automating much of software development, and engineers are becoming process engineers who design the automated pipelines and human gates of the software factory. By September, more than 40% of pull requests on GitHub started with an agent's first draft, up from 17% in March. Work is moving to machines, but the process around it has not caught up.

Agents automate coding faster than delivery

Agents made generating code cheap and fast, but for the most part they have not had the same impact on shipping it. CircleCI's 2026 delivery data showed average daily workflow runs grew 59% year over year, with the top 5% of teams up 97% and the bottom quartile showing no measurable increase. A study of one company that mandated doubling pull request output found that load per reviewer doubled and automated review overtook human review in coverage within months.

Engineers design the software factory

A software factory runs on many specialized agents, each good at one job, passing work to others across the lifecycle. A research agent turns usage data and customer calls into a brief, a spec agent writes requirements with acceptance criteria, a coding agent writes the change, a review agent reviews the change, a test agent runs the change and sends failures back, and a release agent rolls it out behind feature flags. The engineer's job moves from writing code to designing the system that writes, tests, and ships it. That is more technical, not less, because you are now responsible for how all the code gets made. The work comes down to four jobs, and the first is designing the flow: which agents exist, what each one owns, what runs in parallel, and what each handoff must contain. The fourth is placing the human gates. Humans belong where a mistake is expensive, and the call takes judgment. Line-by-line human review of every agent pull request is a craft-era habit, the factory equivalent of hand-inspecting every bolt. Agents write code and fix tests. A schema migration is costly to get wrong but cheap for a machine to check, so agents run it behind hard checks. User interface (UI) copy tastes but is cheap to change, so a human reviews it after it ships. What to build and where a security boundary sits gets a human gate. When work gets automated in any industry, the people don't disappear. Their job changes. They stop doing the work and start designing the system the work runs through.

Quality is built into every change

Most teams still run the old model of quality assurance: changes pile up, then go through one inspection at the end, a shared staging environment and a human reviewer. That is a single test bench for the whole plant, and once agents multiply the number of changes, it becomes the bottleneck Goldratt described. Toyoda's loom freed the operator because it checked every thread as it ran and stopped the moment one broke. Agent-written code needs the same mechanism: the test agent checks every change as it is made, the coding agent fixes what fails, and nothing moves until it passes.

Process becomes the differentiator

Agents made code cheap, and every team can reach for the same models. What separates the teams pulling ahead is the line they build around those agents, with contracts between stations, human gates where judgment matters, and verification on every change. Designing that line is now the software engineer's job.

Sources: The New Stack