We built a qbash Task to match company names from call transcripts to our database. Compared Jev and OpenAI's Decisions API. Full catalog first. Then phonetic encoding to narrow the options. Estimated model cost down ~84%. Small accuracy tradeoff.

Write the process in Python and call a model where a step needs judgment. Qbash runs the rest. Start free at qbash.com

Jev from @typesafeai is now available on qbash. Full release notes: qbash.com/blog/release-notes…

More mail-merge magic, this time with fillable PDFs. Starting with a list of 20 customers, we fill out the same pdf for each, then zip them for download.

Well... Yesterday was a big afternoon for model releases. Opus 5.5 and GPT-6 Sol & Luna are now available on qbash. Try them in playgrounds, and with your existing tasks today.

How do you know AI-written code actually works? Make it write the tests first. Alex builds a Task using AI with test-driven development (that's TDD for the SDLC folks).

Triaging our busiest Slack channel into Asana tickets we could act on was a Monday morning job for whoever had the time. So Jack built a Task to do it for us, reading Slack, Asana and GitHub together so status updates come from what actually shipped instead of who remembered to post about it.

GPT-6 Astra is now available on qbash. Enable it in Org settings, and it's available in all of your Tasks, Prompts, Chats, and Projects. Test it with your existing Prompts, and compare the output with Playgrounds. qbash.com/models

Long-bond yields are at 19-year highs. Let's use Tasks to track every Fed official's remarks and see who's hawkish.

Upload your docs and start asking questions. Instant RAG with vector search. qbash.com/blog/instant-rag-v…

aisle is now qbash. Program AI automations at qbash.com