Here’s an update on what our engineering team has been shipping in sem-ai and what’s coming up next.
Glitches have been fixed. A few issues were blocking some users from getting started with sem-ai. Those are resolved. If you tried it before and ran into friction, now’s a good time to try again.
Task creation is faster and more reliable. We dropped some unnecessary API calls that were causing hiccups. You can now create and manage tasks on your projects entirely through the CLI. No context-switching, no workarounds.
Plugin submitted to the Claude marketplace. We’ve submitted the sem-ai plugin and are waiting on review. More on that once it clears.
Also shipped on Semaphore Cloud. You can now toggle the visibility of skipped blocks in the workflow editor. One click to see everything, one click to filter down to what actually ran. If you work with complex workflows, you’ll notice the difference right away.
On the horizon:
Full platform management through the CLI. Members, organizations, and every management action currently in the Semaphore UI will be accessible directly through sem-ai. Agents will be able to manage the entire platform, not just the pipelines.
We are also working on exposing flaky test data through the API. Flaky tests are one of the biggest sources of developer toil in CI. Once this ships, agents will have direct access to diagnostics and project insights so they can actually act on flakiness, not just surface it.
And we’re building AI-driven onboarding. Your coding assistant sets up your entire CI pipeline from scratch. You define the intent. The agent handles the setup. You wait for green.
As always, we’re moving fast and there’s more coming. Stay tuned.
👉 Try sem-ai
👉 sem-ai docs
👉 Try Semaphore Cloud
👉 All product news
Till the next time,
Pete Miloravac
https://semaphore.io
