Constraint Awareness

Coverage

Theory-of-Constraints (Goldratt) applied to the cost-structure inversion of AI-assisted software development. Identifies the constraint as the human activity that cannot be delegated to an agent — review, validation, decision-making, learning. Walks the Five Focusing Steps (Identify, Exploit, Subordinate, Elevate, Repeat) and shows how each step maps to a team operating multiple coding agents. Names the four constraint-aware process-design rules: front-load agent work and back-load human judgment; batch constraint touches; present options + recommendation rather than open questions; eliminate false dependencies on the constraint by promoting recurring questions into rules or skills. Catalogs five anti-patterns (unnecessary questions, spawning without consent, summaries nobody reads, over-engineering with maintenance debt, circular discussions). Specifies attention-audit ratios for measuring constraint health. Explains the constraint-shift model — that the bottleneck moves over time as agent autonomy improves, from review bandwidth → strategic decisions → user research → market timing — and that the focusing steps must restart when it does.

Philosophy

Most AI-coding systems fail not because the agents are incapable, but because they waste the one resource that cannot be scaled: the human operator's attention. Without explicit constraint-awareness, agents treat all tasks as equal-priority, interrupt the operator with questions they could have answered themselves, and produce verbose output nobody reads. Theory of Constraints turns this into a tractable engineering problem rather than a vague productivity complaint: identify the constraint, route work around it, invest only in changes that genuinely move it.

The single sharpest insight TOC offers an AI-coding team is the cost-structure inversion. Pre-AI, code production was the dominant cost — every feature took hours of typing, every test took hours of writing. Post-AI, code production is nearly free; an agent can produce ten thousand lines in minutes. The bottleneck has moved entirely to the activities that cannot be delegated: reviewing whether the agent's output is correct, deciding what to build next, validating that the system matches user reality, and learning from outcomes. Every team optimization should now be evaluated through one question: does this reduce demand on the constraint?

1. Goldratt's Theory of Constraints

Eliyahu Goldratt's TOC states that every system has exactly one constraint that limits its throughput. Improving anything other than the constraint does not improve the system. Overloading the constraint degrades the entire system.

The Five Focusing Steps