NewLLPhant
A PHP AI framework with a typed Jev classifier integration.
Added to Jevfast
NewHow it uses Jev
LLPhant’s JevClassifier sends caller-provided text state and named typed questions to Jev, then maps Noul, Choice and Score responses into PHP answer objects. Its guide shows a three-question support-message triage example.
What Jev decides
Support-message triage exampleExample answers · not a recorded Jev response · Source ↗
Question 1 · is urgent
YOUR APP
INSTRUCTION
Does this convey urgency?
STATE
The documented text state is “Help! My payouts have been failing for 3 days.”
JEV · NOUL
YesNo
Question 2 · department
YOUR APP
INSTRUCTION
Which team should handle this?
STATE
The documented text state is “Help! My payouts have been failing for 3 days.”
JEV · CHOICE
- billing
- technical
- sales
Question 3 · frustration
YOUR APP
INSTRUCTION
How frustrated is the customer?
STATE
The documented text state is “Help! My payouts have been failing for 3 days.”
JEV · SCORE
0
App workflow
- Define classification
A PHP caller supplies message text plus Noul, Choice and Score question objects.
- Call JevClassifier
The library sends the state and question map to the Jev API.
- Use typed answers
The caller receives typed PHP answers with probabilities, score levels and usage data for its support routing.
Why it is interesting
A PHP application can use Jev’s bounded decision primitives through the same library ecosystem as its other AI tools, while retaining typed answers and token usage metadata.