# Andrea Griffiths - Agent Pull Requests Are Everywhere. Here’s How to Review Them. (Highlights)  ## Metadata **Review**:: [readwise.io](https://readwise.io/bookreview/61401208) **Source**:: #from/readwise #from/reader **Zettel**:: #zettel/fleeting **Status**:: #x **Authors**:: [[Andrea Griffiths]] **Full Title**:: Agent Pull Requests Are Everywhere. Here’s How to Review Them. **Category**:: #articles #readwise/articles **Category Icon**:: 📰 **Document Tags**:: #favorite **URL**:: [github.blog](https://github.blog/ai-and-ml/generative-ai/agent-pull-requests-are-everywhere-heres-how-to-review-them/) **Host**:: [[github.blog]] **Highlighted**:: [[2026-06-17]] **Created**:: [[2026-06-20]] ## Highlights - The part of review that doesn’t get automated is judgment, and judgment requires context only you have. ([View Highlight](https://read.readwise.io/read/01kvabtpm049635881rhyxapma)) ^1026100369 - Annotate the diff where context is helpful. And review it yourself before tagging others, not just to check correctness, but to signal that you’ve validated the agent captured your intent. ([View Highlight](https://read.readwise.io/read/01kvabw50bjwcnahcfxwnvx2tj)) ^1026100511 - Reviewing your own pull request isn’t optional when agents are involved. It’s basic respect for your reviewer’s time. ([View Highlight](https://read.readwise.io/read/01kvabwefcz6xeke4ykwe807v7)) ^1026100583 - For every new helper or utility in an agent pull request, do a quick search. If you find an equivalent, don’t leave a comment. Require consolidation before merge. ([View Highlight](https://read.readwise.io/read/01kvac2jprv4kbhma839mmja5h)) ^1026100798 *Don't leave a comment*: do not just leave a comment, consider it as a blocking. - Pick the most critical path in the diff. Follow it from input through every transform to output. Check boundary conditions (zero, max, empty), missing validation on external values, permission checks on every branch, and surprising conditional logic. ([View Highlight](https://read.readwise.io/read/01kvac6frxqwj628v76pgnyeas)) ^1026100866 - Require a new test that fails on the pre-change behavior. If the agent can’t write a test that would have caught the bug it claims to fix, the fix is incomplete or the understanding is wrong. ([View Highlight](https://read.readwise.io/read/01kvac6xr083tdz2fbqvnj2r58)) ^1026100872 - *This* pull request *is too large for me to review without a clearer implementation plan. Can you break it into smaller scoped units, or add a summary of what each part does and why it’s structured this way? Happy to review after that.* ([View Highlight](https://read.readwise.io/read/01kvad9c9gh60z5fzj2m51bx08)) ^1026102035 - separate the “analysis” step from the “execution” step with a human approval gate for anything touching production, never eval model output ([View Highlight](https://read.readwise.io/read/01kvaddmkz2recdcntwz0a60x9)) ^1026102109 - Search for new functions, helpers, or modules. For each one, do a quick repo search to check for duplicates. Flag anything that reinvents existing functionality. ([View Highlight](https://read.readwise.io/read/01kvadea9zsg0x8vgx1xa3xr15)) ^1026102146 - Pick the most important logic change. Trace it end-to-end: input → transforms → output. ([View Highlight](https://read.readwise.io/read/01kvadefwxqv2x14my82xefqb9)) ^1026102152 - The diff touches more than five unrelated files ([View Highlight](https://read.readwise.io/read/01kvadevxk8sp3csrd4y65tp6n)) ^1026102165 - You can’t describe the purpose of the pull request in one sentence ([View Highlight](https://read.readwise.io/read/01kvadf08w9mfxhakdvvegffnw)) ^1026102171 - The agent has no implementation plan or the pull request body is empty ([View Highlight](https://read.readwise.io/read/01kvadf2hrdew1hj4fwcds1bdm)) ^1026102173 - Treat it as a prerequisite, not a replacement. Let Copilot run first. If it catches something obvious, let the author address it before you invest your review time. ([View Highlight](https://read.readwise.io/read/01kvadfw6hvta5dbwtb6m4qamy)) ^1026102201