A working product experiment
A model makes a judgment.
The workflow decides what happens.
Try a fictional software-support request. Jev classifies it, then a small set of code rules decides whether to prepare guidance, ask a question, or involve a person.
Simulation only. No real accounts, tickets, messages or transactions are connected. This illustrates my approach; it is not the production utility platform.
01 · The request
Start with a situation.
02 · The rules
Keep the boundaries in code.
- Review consequential requests. Possible account changes, requests for a person, or attempts to bypass rules go to human review.
- Ask when the topic is unclear. Unsupported topics or category certainty below your threshold need clarification.
- Prepare guidance for the rest. Suggest an approved help article. No reply is sent by this demo.
Move this after a result to explore the tradeoff. It changes the local routing rule without another API call. Higher thresholds ask for clarification more often.
How to read these signals
Category certainty is Jev’s confidence estimate, not a guarantee that the category is correct. The other three signals estimate the chance that a condition is present.
A review signal of 20% or more triggers review here, including ambiguous cases. This is an illustrative policy, not a production-calibrated threshold. Changing the category slider cannot bypass it.
Read TypeSafe’s confidence documentation ↗03 · Suggested route
Live Jev resultSimulation complete. Nothing has been sent, approved or changed.
What the model returned
- Support topic
- Category certainty
- Account change requested
- Human requested
- Workflow override attempt
Live model estimates above; the explanation and routing rules are written in code. Repeated runs may differ.