qbash retweeted
Quick tutorial connecting qbash MCP servers to Grokbot. Use these to share memories across users/sessions, distribute otherwise unavailable connectors or share deterministic AI tasks with a team spread across Grokbot, Muse, Codex, Claude, etc: youtu.be/i4emsHOFraQ
qbash retweeted
Nobody owns which agents keep running or who answers when they break.
Some call that role AI ops. Most of the job is moving agent work into fixed tasks.
qbash.com/blog/who-owns-the-…
qbash retweeted
This week on qbash : Muse + Grokbot Support, a heavily improved Task Builder AI and build custom MCP servers with any Connector/Task/Memory qbash.com/blog/release-notes…
qbash retweeted
Quick demo using Jev inside of a @qbashdev Task. This is an easy way to use Jev for classification and other models (ie Astra, Fable, Sol) for other parts of the flow - without having to build your own bindings on infra. qbash.com/blog/use-jev-with-…
qbash retweeted
I’m testing small @typesafeai Jev × @qbashdev Task ideas.
Which one should I try first?
61%AI slop copy loop
13%Policy + CRM decision
13%Decision fractal
12%Entity resolution
75 votes • Final results qbash retweeted
Jev from @typesafeai feels very much in the spirit of what we’re building at @qbashdev. Small pieces of AI judgment inside processes we can understand.
Seems like the right idea, given the doom and all.
qbash retweeted
My @qbashdev tasks work in Codex, too.
In this demo, Codex uses MCP to run my changelog and news tasks, read past newsletters, and put together a draft.
The tasks still run on qbash. Codex calls them.
Apologies for the sound. My neighbour thought it was a great idea to drill into concrete all day :)
qbash retweeted
We see deterministic tasks as enabling a new type or third rail of the application that is being developed. Thought it would be fun to share one of our internal strategy decks on the pivot and what we've learned having been iterated on what is now called @qbashdev for the last 2.5 years.
qbash.com/blog/the-strategy-…
qbash retweeted
On the AI Frontier Slowdown: The best systems we built are years old and don't really need better models: qbash.com/blog/our-most-usef…
qbash retweeted
In my previous video, we used the @qbashdev Task builder to create a complex model testing suite.
I wanted to zoom in on the mechanics of what a Task is by creating a simplified single model version of that.
qbash retweeted
Fable 5.1 and GPT-6 Astra in two days begs the question: When should you upgrade models?
I built a @qbashdev task that runs 15 business tests across 8 models every Monday, scores them, and diffs the results against last week.
qbash retweeted
Super happy to announce a refreshed rebrand for our AI work as we become more focused on programmatic, deterministic AI processes. Read more about the journey and switch over here: qbash.com/blog/aisle-is-now-…
qbash retweeted
In the Microsoft earnings call Satya was talking about how ip needs to be abstract from models - and that models are fast becoming commodities. Enter the whole reason we made Tasks: aisle.sh/blog/the-model-is-a…
qbash retweeted
New in Aisle Projects this month:
- GPT Support for Projects / Orchestrator Agent
- Chat and logs search across a project or your whole account
- Nested memories folders / KBs
Plus, a whole bunch of UX love, and some fun experiments. Quick tour:
qbash retweeted
We've made some changes to the @aisle_sh Task editor. Quick tour ↓