WorkerKitJoin the waitlistAI workers for Jev
Ready-made Jev AI workers classify email, calendar events, spreadsheet rows, documents, GitHub work, and web content into typed decisions that your AI assistant can use or route under rules you set.
- Sheets Lead Qualification Decision model Returns lead-fit classifications from spreadsheet rows against your ideal customer profile.
- Internal Request Router Decision model Labels incoming requests for IT, HR or Finance and escalates requests needing private handling.
- Meeting Prep Needed Screen Decision model Reads the week ahead and says, meeting by meeting, whether the owner needs to prepare and what kind of preparation it is.
- Critical Email Finder Decision model Reads a window of inbox mail and returns only the messages where something breaks, money is lost, a person is blocked or a deadline passes if the owner does not see them today.
- Web Research Relevance Filter Decision model Finds and reads web pages on your research topic and returns relevant sources with typed judgments.
- Release Note Classifier Decision model Returns release-note sections and merge judgments for pull requests so an agent can assemble a changelog.
- Meeting Entity Relevance Finder Decision model Finds matching meeting that was actually about a customer, project, vendor, person or topic you name, including the internal ones the target was never invited to.
- Brand Mention Urgency Radar Decision model Finds public brand mentions that merit a company response or investigation.
- Email Jev Classifier Decision model Sorts a window of inbox mail into your own categories and returns one typed row per message, so an agent can read the shape of an inbox in one call.
- Critical Meeting Finder Decision model Reads the week ahead and returns only the meetings where revenue, a decision, a customer or an external commitment suffers if the owner skips them or walks in unprepared.
- Email Reply Needed Screen Decision model Reads a window of mail and says, message by message, whether the owner owes a reply and who owes the next move.
- Sheets Jev Classifier Decision model Classifies spreadsheet rows into your own categories and returns typed results for the calling agent.
- Calendar Jev Classifier Decision model Sorts the week ahead into your own meeting categories and returns one typed row per event, so an agent can read the shape of a calendar in one call.
- GitHub Issue Triage Decision model Reads a repository's open issues and decides what each one is, how badly it hurts, and whether it needs a maintainer.
- Email Entity Relevance Finder Decision model Finds matching message that is actually about a customer, project, vendor, person or topic you name, internal and external, and names the false positives a keyword search returns silently.
- Document Content Relevance Decision model Finds documents whose readable content addresses your chosen topic or business requirement.
- Sheets Feedback Router Decision model Returns a recommended handling category for each customer-feedback row in a spreadsheet.
- Inbox Reply Labeler Decision model Labels requests needing a reply, urgent requests and bulk mail so your inbox is ready to work.
What is a Jev AI worker?
A Jev AI worker is a WorkerKit worker that sends bounded source state and typed Choice, Score, or Noul questions to TypeSafe's Jev decision model. It receives structured answers and confidence rather than generated prose, then applies explicit routing rules. Each worker has its own source access, thresholds, schedule, and run receipt.
What these workers do
Classify inbox messages with your taxonomy
Reads bounded email previews and returns one of the categories you define, with confidence and a message reference for the calling assistant.
Qualify leads from Google Sheets
Judges mapped company and inquiry fields against your ideal customer profile and returns fit, not-fit, or needs-context for each row.
Find critical email and calendar items
Scores messages and meetings against explicit consequence criteria, then surfaces the items that cross the configured threshold.
Filter documents and web research
Checks file contents or scraped page text against a research question and returns relevant items with source references.
Route requests and feedback
Chooses an operational queue from evidence in an inbox message or spreadsheet row, then returns or applies the declared route.
How a Jev AI worker runs
What it judges
How the decision works
What comes back
Jev questions, answered.
What is a Jev AI worker?
A Jev AI worker uses TypeSafe's Jev model to make typed decisions over a bounded set of source items. Instead of asking for a prose response, its kit defines Choice, Score, or Noul questions and routing thresholds. WorkerKit handles the app connection, permissions, execution, action, and receipt around those decisions.
How is a Jev worker different from an LLM worker?
Jev workers are designed for repeated classification, scoring, screening, and routing jobs with fixed answer shapes. A general LLM worker is better suited to writing, synthesis, and multi-step investigation. In WorkerKit, each job can use the model type that fits it, while the calling assistant receives a normal run result from either one.
Can a Jev worker classify Gmail, calendar, and Google Sheets data?
Yes, when the installed kit supports that source and you connect an allowed account or resource. The current kits can judge email previews, calendar events, mapped spreadsheet rows, documents, GitHub items, and public web content. Each source remains bounded by the worker's own permissions and run limits.
Can a Jev worker take actions after a decision?
Yes, when the kit declares an action and you grant the required write permission. A result can drive a label, folder move, or another supported tool call. Other kits deliberately return typed answers and source references so your assistant or a later worker can decide what happens next.
What happens when a Jev decision is uncertain?
WorkerKit compares the decision confidence with the floor defined by the kit or chosen at setup. An uncertain item can be escalated in the result instead of taking the normal route. The receipt keeps its typed answers and source reference so a person or calling assistant can review the evidence.