JevMade Sign in
← Back to experiments

Apps & data pipelines

jev-ql

Query messy text with SQL-style filters and plain-language questions that Jev can answer.

Bookmark: jev-ql Keep this in your collection.
Leave a noteWhat would you try with this? : jev-ql

Only you can see your notes.

Source screenshot of jev-ql
SOURCE SCREENSHOTFull screenshot ↗

What it does

Ordinary filters run first, sparing model calls. Without a key, or if the API fails, it falls back to keyword heuristics.

How you can use it

A developer can adapt this code for a customer support app. They write a simple command that filters for open tickets first. The app sends the remaining messages to an outside AI service called TypeSafe. This service reads the text to choose a category like billing or security.

The app can sort tickets by how sure the AI is about the problem. It can wait for a person when the answer is uncertain. The software requires an access key to connect to TypeSafe. Without this connection, the tool guesses answers using basic keywords.

Keep this for later

Sign in to bookmark experiments, guides and videos, and keep notes only you can see.

Continue to sign in

We’ll bring you back to this listing.