Who it is forA developer on a support or operations team who wants tickets sorted before a person reads them, triggered by a growing backlog of plain-text messages.
The problemKeyword rules miss meaning, and sending every ticket to an LLM means parsing free-form text back into fields.
The outcomeA script that returns one intent label and one urgency score per ticket, ready to branch on in code.
What you need first
- Access to Jev through the TypeSafe waitlist, Vercel AI Gateway, or Cloudflare Workers AI
- A TypeSafe API key from the TypeSafe console, stored as TYPESAFE_API_KEY
- Python with pip for the Python SDK, or Node.js with npm for the JavaScript SDK
Steps
- Run
pip install typesafe-sdk. - Create an API key at https://console.typesafe.ai/settings/keys and set it as the TYPESAFE_API_KEY environment variable.
- Copy the Python quick start from the README, replace the sample state with your ticket text, and keep the Choice, Noul, and Score questions.
- Run the script on a few sample tickets and check the intent, is_urgent, and frustration values.
- Add your own thresholds in code to decide which tickets go to a priority queue.
Prompt for your agent
Using the repo kraayenjon/awesome-jev and the typesafe-sdk Python package, write a script that reads each ticket in <tickets folder> and sends it to Jev with a Choice question for intent, a Noul question for urgency, and a Score question for frustration. Output one line per ticket with the intent, the urgency value, and the frustration score. Verify that every urgency value is between 0.0 and 1.0 and that every intent is one of the option keys you defined.
Caveat. Jev accepts text only, so tickets with screenshots or attachments need their text extracted first, and the list is unofficial and Jev launched in early access on September 15, 2026.
Get 5 new use cases every morning. Free, one short email, unsubscribe anytime.
Get them freeShare: X LinkedIn Hacker News Email Copy link
Disclaimer
Deduped lists open-source repositories that belong to other people. We do not own, maintain, audit, or vouch for any of them, and a repo appearing here is not an endorsement or a safety check. The use cases, steps, and prompts are written by AI and may be incomplete, outdated, or just wrong. Where a use case is marked "Seen in the wild", we link to public posts where someone described something similar, but we have not verified those posts and the use case itself is still our AI's own write-up. Use all of this at your own risk. Only run code, commands, or agents on systems and accounts you are authorized to use, and read the code and every command before you run it, especially anything that touches credentials, files, or the network. Nothing here is professional, security, legal, or financial advice. All trademarks and project names belong to their respective owners, and their use here does not imply affiliation. Content is provided as is, without warranties of any kind. Found a mistake, a safety problem, or something you want removed? Email [email protected] and we will look at it promptly. Full disclaimer page