Let agents read and update your @Jira tickets with Atlassian Rovo MCP on Superconductor.
Look up issues, comment, summarize work, create follow-ups, update fields, and move issues through workflows.
We ran the new Grok Build harness + model on our "Personal SWE-Bench" for our Ruby on Rails codebase.
The results are better than expected! Fast and pretty good.
We're now throwing Grok Build into the mix when we launch multiple implementations for tricky features.
Meeting bots should SHIP CODE, not take notes.
We just added a Meeting Assistant that listens for features and bug reports and automatically launches coding agents to implement them.
By the end of the meeting, you have live previews of multiple new features!
@paularambles This is available as a feature in superconductor. It will find and link to existing tickets, or create new ones. Most team and customer meetings now come with mergeable PRs.
AI coding agents produce a lot of code quickly.
Superconductor's QA Review helps you decide what deserves your attention before you dig into the diff.
It checks functionality and code quality, whether tests and lint pass, and what should be fixed next.
Superconductor now automatically sets up the dev environment when you create a project. Any language, any framework. Docker included.
If your dev env doesn't need secrets, we auto-apply it to your project, so coding agents can immediately run tests and show live app previews without you having to lift a finger.
Added breadcrumb navigation across the app.
With so many ticket implementations going at once, it's nice to immediately know where you are as you're jumping around between them.
GPT 5.5 is the π NEW KING π on our "personal SWE-Bench", based on gold standard PRs into our Ruby on Rails codebase.
GLM 5.1 and Kimi K2.6 now beat all Anthropic models (but are slower).
And Opus 4.7 is a real head-scratcher!
Build your own and see: https://t.co/qzr0CMVKYE
Recent Activity sidebar now shows GitHub PR status -- open, merged, or closed -- with color-coded badges that update in real time.
It's nice to see a sea of purple merged PRs π
You can now define your own branch naming pattern using variables like GitHub username, ticket number, and title.
Configure it in your workspace settings to match your team's conventions.
BTW, you can set up a "personal SWE-Bench" on your own codebase:
1. Pick several "gold standard" pull requests
2. Select the coding agents to benchmark
3. Coding agents try to re-implement the PRs, and their results are judged by all three frontier LLMs.
https://t.co/fSMew99sPw
We ran our Rails benchmark on Opus 4.7
GPT-5.4 wrote better code for $1.06 and finished ~2.5X faster
Opus 4.7 wrote worse code for $19.84
We're not sure why 4.7 is so much slower and more expensive than 4.6.
What are you guys seeing on your benchmarks?
Superconductor now shows a 'working indicator' in Slack threads while the agent is working on your ticket.
Small thing, but a helpful validation that the agent is doing its thing.
Mobile push notifications now go to all team members following an AI coding agent implementation, not just the owner.
You'll now know when any of the agents you follow need attention.
Each startup command now has a checkbox to mark it as a background process, so long-running services like dev servers don't block the rest of your setup.
@jordienr Superconductor does exactly what you want. And we have a mobile app too, so you can see the preview environments from your phone or in browser.
New: @posthog MCP integration.
Your coding agents can now query your PostHog analytics data -- funnels, events, usage metrics -- before writing a single line of code.