iiinova — where your digital self keeps evolving

CodeRabbit @coderabbitai.bsky.social · 24/09/2026

Know what your PR does. CodeRabbit Change Stack - your explainability layer: > Overview + Layers: map the PR's logical changes > Findings: issues, proposed fixes and agent prompts > Code Peek + AI Chat: definitions, context, answers > Blast radius: understand the impact

111

CodeRabbit @coderabbitai.bsky.social · 23/09/2026

Agents can create PRs in minutes, but understanding them still takes work. CodeRabbit Change Stack connects a PR's purpose, behavior, dependencies, and code so reviewers can really verify it before approving. Do you understand what you're about to merge?

141

CodeRabbit @coderabbitai.bsky.social · 17/09/2026

PRs piling up. Which one needs you next? Hop over to see how CodeRabbit Triage can sort the queue for you. Quick walkthrough 👇

100

CodeRabbit @coderabbitai.bsky.social · 01/09/2026

Before: 20 repos, 20 standards files. Update one and the other 19 go stale. After: one central repo. Point 𝚏𝚒𝚕𝚎𝙿𝚊𝚝𝚝𝚎𝚛𝚗𝚜 at it with 𝚛𝚎𝚙𝚘:𝚙𝚊𝚝𝚑, and CodeRabbit pulls the right standards into every review, in every repo.

100

CodeRabbit @coderabbitai.bsky.social · 27/08/2026

If you already love our Pre-Merge Checks, this is for you. One click and AI fixes the failed ones. We got you.

110

CodeRabbit @coderabbitai.bsky.social · 25/08/2026

CodeRabbit is now available as a plugin for Cursor! Ask Cursor Agent to review your changes, delegate review to the included CodeRabbit subagent, choose the diff scope, and work through findings without leaving your Agent workflow. Heres a quick overview!

100

CodeRabbit @coderabbitai.bsky.social · 21/08/2026

Full code security visibility. Steer it all from the CodeRabbit Security panel. Detect, understand, secure.

100

CodeRabbit @coderabbitai.bsky.social · 21/08/2026

A diff shows the lines that changed, not what they reach. Blast Radius maps each change against: > Dependencies it uses > Consumers it may affect > Tests that cover it > Supporting repository context It’s included with CodeRabbit Security and available through Change Stack.

151

CodeRabbit @coderabbitai.bsky.social · 20/08/2026

Where to find them in CodeRabbit web interface: Security > Pull Requests > PR Findings

100

CodeRabbit @coderabbitai.bsky.social · 20/08/2026

Security issues raised in review land in PR Findings. Change Stack provides the explainability layer. You or your agent takes it from there. Detect, understand, fix.

100

CodeRabbit @coderabbitai.bsky.social · 19/08/2026

Agents can write code faster than ever. Review can’t be the bottleneck. CodeRabbit CLI 0.7 makes typical reviews 19% faster, longer reviews up to 23% faster, and cuts client disconnects by 31%. More review-fix-review cycles completed before the code ever reaches a pull request.

131

CodeRabbit @coderabbitai.bsky.social · 17/08/2026

CodeRabbit Security's AI Deep Scan finds exploitable vulnerabilities across your source code and infra config. Every finding: category, severity, CWE, file, line range and reachability. Understand the exploit and fix it yourself or with AI.

100

CodeRabbit @coderabbitai.bsky.social · 31/07/2026

+ PII leaking into logs. + An auth server error. + A concurrency bug in an idempotency path. CodeRabbit surfaced all three in the systems that protect 1.6M+ customers, before a human even opened the PR. Find out how we managed that (and more use cases) below 👇

111

CodeRabbit @coderabbitai.bsky.social · 30/07/2026

VS Code CodeRabbit extension v0.21.2 is live 🚨 > In-IDE reviews now stay connected and reconnect more reliably during longer sessions. > Sign-in flow improved to help you reach the right workspace. Install or update to take advantage of the latest version ✌️

121

CodeRabbit @coderabbitai.bsky.social · 20/07/2026

CodeRabbit can now investigate and fix CI failures on GitHub! Once you trigger the action using '@coderabbitai fix-ci', CodeRabbit will investigate, fix, and deliver a stacked PR ✌️ Check out the docs below to get started.

151

CodeRabbit @coderabbitai.bsky.social · 16/07/2026

Pattern-based scanners can parse your syntax but they have no idea what your app actually does. That's why the logic flaw ships clean while you burn a sprint triaging a "critical" in dead code. Reasoning and trust across the codebase is the whole game now.

100

CodeRabbit @coderabbitai.bsky.social · 13/07/2026

CodeRabbit can now take action AFTER a PR has merged, not just before ✌️ You can configure up to 5 post-merge actions across your org and set them up via Settings > Post-merge actions! (Full docs below)

110

CodeRabbit @coderabbitai.bsky.social · 13/07/2026

Maintainers lose whole days answering the same setup question, triaging half-formed bug reports, nudging stalled PRs. CodeRabbit Agent now does that inside your Discord server. Answers from your docs, triages bug reports, drafts fixes as PRs. All inside the thread! Free for open source projects.

131

CodeRabbit @coderabbitai.bsky.social · 08/07/2026

One codebase, three identical PRs, three different CodeRabbit review profiles. > Quiet - only the most important feedback > Chill - balanced (the default) > Assertive - most comprehensive Dial in the review depth that fits your team ✌️

111

CodeRabbit @coderabbitai.bsky.social · 08/07/2026

"quiet" reviews now join the roster alongside "chill" and "assertive". "quiet" will surface only the most important findings inline while keeping everything else inside collapsable sections. You can adjust your review profile in repository settings!

100

CodeRabbit @coderabbitai.bsky.social · 06/07/2026

CodeRabbit's review comments now cite their sources! Bad guideline? delete it. Irrelevant linked repo? disable it. The review starts matching how your team actually works.

110

CodeRabbit @coderabbitai.bsky.social · 02/07/2026

Your PR history shouldn't be a mystery. Timeline View is live in CodeRabbit Review UI. Filter by context, see what happened and why it happened. Full explainability, so you can ship with confidence!

100

CodeRabbit @coderabbitai.bsky.social · 30/06/2026

CodeRabbit Agent now runs in Discord. PR fixes, automations and code work, in the channels your community already uses. Scoped so your server can't be misused. Free for open source.

260

CodeRabbit @coderabbitai.bsky.social · 29/06/2026

Two years ago everyone assumed AI would just make code review faster. Same job, less time...right? That assumption is the whole problem. ~1.7x more issues Logic bugs up 75% Security holes up around 2x. The bottleneck has shifted right, from writing code to reviewing it.

021

CodeRabbit @coderabbitai.bsky.social · 26/06/2026

A little teaser of what we’re cooking for you. CodeRabbit Agent inside Discord. The same one that reviews your PRs now lives in your community.

131

CodeRabbit @coderabbitai.bsky.social · 24/06/2026

Enterprise users can now programmatically access their organization’s Learnings via the new 𝙶𝙴𝚃 /𝚟𝟷/𝚕𝚎𝚊𝚛𝚗𝚒𝚗𝚐𝚜 API endpoint. Use it to export, audit, or integrate learnings into your own workflows! See the Learnings API reference below for the full parameter and response schema ✌️

110

CodeRabbit @coderabbitai.bsky.social · 24/06/2026

Tokens are an input. Merges are the outcome. You won't win by burning more compute, you'll win by shipping good code faster without rationing which PRs get reviewed. Out with tokenmaxxing, in with mergemaxxing!

110

CodeRabbit @coderabbitai.bsky.social · 20/06/2026

CodeRabbit now includes React Doctor v0.5.6 to make sure your React code is secure and performant! Enabled by default, but easy to switch off. 👨‍⚕️

061

CodeRabbit @coderabbitai.bsky.social · 19/06/2026

You shouldn't have to read the diff to understand the PR. Our new Overview page gets you oriented before you touch a line. PR summary, walkthrough, actionable-blockers, comments all in one place. Live now in the Change Stack 👇

110

CodeRabbit @coderabbitai.bsky.social · 18/06/2026

Don't let code reviews be an expensive bottleneck during your agent loops. CodeRabbit CLI can now run 1.5x faster with light mode. Update & run 𝚌𝚘𝚍𝚎𝚛𝚊𝚋𝚋𝚒𝚝 --𝚕𝚒𝚐𝚑𝚝 today.

000

CodeRabbit @coderabbitai.bsky.social · 16/06/2026

CodeRabbit now lets admins review newly created Learnings before they are added to the knowledge base! Set 𝚔𝚗𝚘𝚠𝚕𝚎𝚍𝚐𝚎_𝚋𝚊𝚜𝚎.𝚕𝚎𝚊𝚛𝚗𝚒𝚗𝚐𝚜.𝚊𝚙𝚙𝚛𝚘𝚟𝚊𝚕_𝚍𝚎𝚕𝚊𝚢 to 𝟷 through 𝟹𝟶 days at the organization or repository level to hold new chat-sourced learnings for review!

121

CodeRabbit @coderabbitai.bsky.social · 15/06/2026

The hard part of AI code review isn't checking what changed in PR #4306. It's checking everything that changed because of it.

121

CodeRabbit @coderabbitai.bsky.social · 12/06/2026

Give a dev 30 seconds to approve or reject a PR and watch the bugs sail through. We ran exactly that at App.js Conf, then asked devs there, plus JS Nation and React Summit, how you actually review code. Thanks to all three for having us! Here's what we’ve heard 👇

100

CodeRabbit @coderabbitai.bsky.social · 11/06/2026

Best way to test a feature you built? Run it on real repos. So we forked the octokit repos into an org and used our automatic repository linking feature. CodeRabbit now walks the dependency graph on its own and flags cross-repo impact at review time.

110

CodeRabbit @coderabbitai.bsky.social · 10/06/2026

An AI code review company telling you not to talk to humans like machines. yes, really. Humans don't have an API (yet). Read more in our latest blog post.

120

CodeRabbit @coderabbitai.bsky.social · 10/06/2026

Most rework starts the same way. Nobody really mapped the change before the first line got written. CodeRabbit Agent for Slack plan feature turns your task into a codebase-aware plan. Right in your Slack thread.

100

CodeRabbit @coderabbitai.bsky.social · 09/06/2026

We benchmarked Fable 5 on 105 code reviews. It nearly matched on coverage and then trailed on precision while filing 253 comments. Great at building, noisy at reviewing. Full breakdown 👇

120

CodeRabbit @coderabbitai.bsky.social · 08/06/2026

There was a critical issue in Swiggy's codebase and their existing security tooling missed it entirely. CodeRabbit caught it. That single finding turned into a 70% drop in merge time and a rebuilt review workflow across 1,000+ devs.

130

CodeRabbit @coderabbitai.bsky.social · 04/06/2026

CodeRabbit Review UI now available to ALL GitLab users (gitlab.com and self-hosted) > Click "Review Change Stack" in the gitlab MR to see the new UI. > Navigate through layers, cohort summaries, semantic diff view, and more in a guided review flow. 🦊

110

CodeRabbit @coderabbitai.bsky.social · 04/06/2026

That is the useful takeaway: Nemotron 3 Ultra is not the model we would frame as “the new best coding assistant.” It is more interesting as infrastructure for developer workflows where speed, retries, validation, and external checks are part of the system.

110

CodeRabbit @coderabbitai.bsky.social · 04/06/2026

In our CodeRabbit benchmark, Nemotron 3 Ultra landed close to the baseline: > Baseline pass actual: 60/105 > Ultra pass actual: 58/105 > Baseline pass full: 66/105 > Ultra pass full: 65/105 > Baseline mean latency: 8:31 > Ultra mean latency: 7:06 That is a strong signal.

100

CodeRabbit @coderabbitai.bsky.social · 04/06/2026

NVIDIA's Nemotron 3 Ultra is not just another open model release. After testing it in CodeRabbit benchmarks and talking with the NVIDIA team, the interesting part is clear: > This model feels less like a chatbot and more like a fast infrastructure for developer loops.

130

CodeRabbit @coderabbitai.bsky.social · 03/06/2026

CodeRabbit Agent when the humans start arguing in a thread.

010

CodeRabbit @coderabbitai.bsky.social · 02/06/2026

AI-assisted PRs average 10.83 issues each, compared to 6.45 for human-authored code. That gap isn't stopping anyone from shipping. AI coding agents aren't going away, and the code review queue is starting to show it.

130

CodeRabbit @coderabbitai.bsky.social · 02/06/2026

Did you know CodeRabbit Agent for Slack can generate visuals? GitHub traffic, BigQuery data, Datadog metrics and more. Ask for a chart, diagram, or report and get it back in the thread. Ad-hoc or on a schedule. Your call.

100

CodeRabbit @coderabbitai.bsky.social · 29/05/2026

AI can now rewrite an entire codebase in days! ( @bunjavascript 👀 ) Reviewing a million-line diff across 2,000 files is still the hard part though. CodeRabbit Review is built around intent and context, not just line-by-line changes. Read the full post below.

100