Speeding chat answers with pre-structured SQL
floor_per_area shares a technical brainstorm: using Jev with pre-structured SQL to make chat responses about ten times faster, and asks whether it would work.
CA clean typed decision with low volume or low value, or too vague to act on.2.11
Key facts
- Vertical
- Software & tech
- Function
- Agents & dev
- Status
- Seen in the wild
- Volume
- occasional
- Value
- meaningful
- Risk
- low
- Evidence
- question asked
- Flags
- check-fit
Source: https://madewithjev.com/builds/jev-pre-structured-sql
Build this with a classifier
Define a typed decision with a bounded answer, then evaluate it on examples.
{
"decision_type": "choice",
"question": "Does this input match the decision in “Speeding chat answers with pre-structured SQL”?",
"input": "<input to classify>",
"output": "one label from a fixed list"
}Related use cases
Cite this
Copy a link in your preferred format.