Definition
The discipline of designing software work, environments, and controls so goal-directed AI agents can perform substantial engineering. The agent may plan, implement, test, investigate, or operate software. Humans remain responsible for deciding what should exist, which risks are acceptable, what evidence earns promotion, and who owns the result.
This is engineering around the agent as a production participant. It includes task and interface design, repository legibility, tool access, isolated execution, evaluation, observability, cost control, escalation, and recovery. Model capability matters, but it is only one input. The same model can be useful or hazardous depending on the harness, environment, authority, and verification around it.
Why the distinction matters
Agentic systems shift labor without eliminating expertise. Large-scale evidence on coding-agent use finds persistent returns to domain knowledge, while practitioner critiques of software factories point to product judgment, review capacity, and context as remaining constraints. The discipline therefore asks where human judgment has the highest value and how to encode routine constraints without pretending that judgment has disappeared.
Distinguish it from nearby terms
Agentic coding is a working method. Agentic software engineering is the broader discipline that makes that method dependable across a team or system. A dark software factory is one possible operating model at the high-autonomy end, not the definition of the discipline.
Check your understanding
An agent writes a correct patch, but only because an experienced engineer supplied a reproducible environment, a precise behavioral contract, and a test that exposed the first wrong attempt. Which part counts as agentic software engineering? The answer includes the environment, contract, feedback loop, and promotion decision, not only the generated patch.