Call Scope
Choose a prepared conversation flash card as a call unfolds.
What Jev decides
Which conversation state or prepared card best fits the latest transcript.
CallScope transcribes a call locally and uses Jev to judge paraphrased questions, answers, and topic changes before updating a prepared prompt card.
- Jev role
- Match the evolving conversation to prepared goals and prompt cards.
- Input
- Recent transcript text, speaker context, and the user's prepared call brief.
- Output
- Validated typed Choice results used to update the card.
- Decision frequency
- As finalized speech or topic changes arrive during a live call.
- Fallback
- The opening card and local transcription remain available without a Jev key.
How it works
Overview
CallScope is a Windows conversation companion. The user prepares goals and approved talking points. Local speech transcription follows the call, while Jev evaluates whether a question has been asked in other words, how a remote answer relates to the goal, and whether the topic has moved. The app then shows one short relevant card.
Practice mode uses scripted fictional replies and needs no key. Live automatic card updates need a TypeSafe key; the transcript text and brief are sent to Jev even when audio transcription runs locally. The project does not claim to detect lies or hidden emotions.
- Language
- TypeScript
- Author
- EricKwong
Sources
Related projects
typesafe-computer-use
A native macOS computer-use loop built from local OCR, accessibility data, and bounded Jev actions.
What Jev decides
Which computer action, visible item, site, or off-screen accessibility control to use next.
Jev Chat Assistant
An Android conversation copilot that uses Jev to interpret chats and rank reply candidates without sending for the user.
What Jev decides
The likely intent, conversation risk, reply need, best next action, unresolved tension, and which of three candidate replies fits best.
Kill My Idea
Turn a startup pitch into a compact set of scores and a blunt Kill, Fix, or Ship verdict.
What Jev decides
Dimension scores, idea category, whether the pitch is understandable, and supporting diagnostic signals.