Ai-generated pull requests now wait 17.6 hours for a first review, 5 times longer than the 3.4…
ai-generated pull requests now wait 17.6 hours for a first review, 5 times longer than the 3.4 hours human-written prs get, and only 33 percent merge within 30 days against 84 percent for manual work, per linearb. the code is getting faster, the review queue is not.
the bottleneck moved from writing to deciding.
Context
LinearB's 2026 Software Engineering Benchmarks Report is built from 8.1M+ pull requests from 4,800+ organizations. Its page says agentic pull requests, opened by agents such as Devin, Copilot Coding Agent and Codex, wait 17.6 hours at the 75th percentile against 3.4 hours for unassisted work, a 5.25x gap, and gives 32.7% versus 84.4% of pull requests merging within 30 days. The report landing page says AI PRs wait 4.6x longer before review.
This is vendor-reported from LinearB's own customer base, not independent. The 17.6 hours is a 75th-percentile figure for agentic pull requests, not a mean for all AI-generated ones, and the note drops that. The report page's 4.6x differs from the 5.25x, and the text did not show whether they use different statistics, so the note's 5 times only matches 5.25x. Whether the merge figures cover agentic PRs only or also AI-assisted ones was unclear, and the reporting period was not stated. Causes such as low-priority backlog items and unclear ownership are LinearB's interpretation, not measured. The code is getting faster, the review queue is not is the author's opinion.
Related work
- LinearB engineering glossary ↗Defines agentic PRs, snippet only.
Watch next
- The full report for the percentile definition and the scope of the merge rate.
Sources
Provenance
The note above is reproduced unedited from the original post, first published on Threads on 18 September 2026 at 18:17 IST. Sources are the papers and datasets the note draws on.
View the original post ↗Embed this note
More notes
The air is now being asked to keep its own ledger
the air is now being asked to keep its own ledger: ecmwf’s aifs compo becomes the first ai model to forecast atmospheric composition globally every three hours, cleanair simulates 365 days of pm2.5 over china in ten seconds, and a unified framework maps six pollutants at one kilometer across the whole country. the air now files its own composition report.
read the note →The current is now being asked to draw its own map
the current is now being asked to draw its own map: china’s langya 2.0 predicts six ocean phenomena including internal waves and mesoscale eddies, a deep net called wenhai resolves eddies globally with air sea flux formulas built in, and scripps infers surface currents from the way temperature patterns deform in satellite images. the ocean now files its own circulation report.
read the note →The soil is now being asked to report its own carbon
the soil is now being asked to report its own carbon: a nix color sensor paired with generative data augmentation predicts soil organic carbon without a lab, random forest drives 74 percent of soil health mapping studies, and sentinel 2 tracks five year carbon change across france and italy from 922 samples. the dirt now files its own carbon account.
read the note →