How Much Does AI Cut Development Effort? Agentic-Era Data
"How much does AI cut software development effort?" With agentic coding arriving in 2025–2026, the very unit we measure by changed. It used to be "how many percent faster is one task"; now it is an order-of-magnitude story: "a dev cycle that took weeks compresses into hours or days" (TechTarget). Claude Fable 5 finished Stripe's 50-million-line migration in a day; TELUS saved 500,000 developer-hours; cycle time went 9.6 → 2.4 days. The autocomplete-era numbers — Copilot RCT 55.8% faster, McKinsey 20–50% by task — are now the floor. But it is not a uniform 10×: per Anthropic's 2026 Agentic Coding Trends Report, developers use AI on ~60% of their work, yet only 0–20% of tasks can be fully delegated (the delegation gap), so human review is required, and about 27% of AI work is new work that did not exist before (cutting effort = producing more). With good context design, 40% fewer errors and 55% faster. Even METR's 2025 "experts are 19% slower" result is reversing in 2026, with the authors admitting the measurement undercounts reality. This article separates that polarization with named sources (GitHub, McKinsey, Anthropic, METR, DORA) and lays out how to actually capture the effort savings.
