Fetching from the wire…
01
02
03
04
05
06
07
08
Tools2026-06-27 · source-backed
Bugbot now finds ~10% more bugs per review (0.62 vs 0.56) at ~22% lower cost per run. A new /review flow runs Bugbot and Security Review before push, dedups against the eventual PR, and supports incremental "only what's new" review. Cursor also added always-on Automations with GitHub and Slack triggers. (Cursor) This is the chat-IDE becoming a standing review-and-automation agent in your loop, which is the Shopify thesis showing up as a product feature. Pre-push review that dedups against the PR is the kind of friction removal that actually changes behavior.
Each link below shares sources, entities, or timing with this story.
Claude Code v2.1.71 adds /loop for cron-scheduled background prompts (PR babysitting, Slack summaries, deploy monitoring). Cursor shipped Automations with event-driven triggers from GitHub, PagerDuty, and webhooks. OpenAI open-sourced Symphony, an Elixir/BEAM framework that po...
Anysphere shipped Cursor 3 (codenamed "Glass") on April 2, and it's not really an IDE anymore. It's an agent workspace. The redesign is fundamental. Developers enter natural language task descriptions, select an LLM, and Cursor generates code plus a demo video. Local and cloud...
Cursor shipped the biggest paradigm shift in AI coding this week. Automations are always-on agents that activate from external events — merged PRs, PagerDuty incidents, Slack messages, Linear issues, cron schedules, or custom webhooks. The agent spins up a cloud sandbox, follo...
The July update adds /in-cloud, which spins up a subagent on its own VM and branch so you can run as many parallel cloud agents as you want and pull one back local to test. Auto-review is a contextual classifier that lets agents keep moving on low-risk actions while slowing hi...
Cursor published something last week that should make every team building agent evals sit up straight. They're running real-time reinforcement learning on Composer 2, deploying new model checkpoints every five hours from production traffic. That alone is interesting. But the a...
The coding agent wars just entered a new phase. Cursor isn't just an IDE anymore. It's a model company. Cursor released Composer 2.5 on May 18 with a custom agentic coding model trained using 25x more synthetic tasks than Composer 2 and a novel "targeted textual feedback" appr...
MindPattern daily
One email a day at 7 AM. Sources and a take on every story. Unsubscribe anytime.