# How to use Jev to automate your business (Step-by-step w/ Treg)

## Executive summary

This talk introduces Jev, a specialized model designed for reliable, high-accuracy business automation rather than creative text generation. Unlike general-purpose LLMs, Jev is optimized for structured decision-making, providing probability distributions for a limited set of options. This makes it ideal for mission-critical workflows requiring near-100% accuracy, such as fraud detection, internal link mapping, and classifying user intent, while being significantly faster and cheaper than large general models.

## Key takeaways

- Jev's Core Advantage: Jev is designed for reliable, high-quality decision-making, outputting the probability of a list of given answers rather than predicting text token by token. This makes it extremely fast and cost-effective for high-volume business workflows.
- Confidence Scoring: Every answer Jev provides comes with a probability distribution (confidence score). This allows developers to build sophisticated business logic (e.g., if confidence > 70%, auto-block; if 35% < confidence < 70%, request human review).
- Use Case: Browser Automation: Jev can predict the next action (click, type) and the target UI element based on the DOM and interaction history, enabling fast and accurate browser and computer use for agent systems.
- Workflow Example: Fraud Detection: By combining Jev with data services like Track, users can build automated pipelines to classify signups (e.g., fraud, upsell value, affiliate) using thousands of data points, making previously uneconomical automation possible.

## Technical details

- Model Architecture: Jev predicts the probability of a list of given answers, outputting a probability distribution rather than generating text tokens. This approach is faster and cheaper than general LLMs.
- Input/Output Structure: Jev requires a prompt (or 'state') and a set of predefined questions/options. It can handle multi-choice, True/False, and scoring questions, outputting a probability score for each option.
- Context Window Limitation: Jev has a context window of 32K. For larger inputs, workarounds like map-reduce may be necessary.
- Integration Stack: Effective automation pipelines often combine Jev (for decision logic) with specialized data services (like Track) and smaller LLMs (for final text generation, e.g., typing).

## Practical implications

- Build highly reliable, autonomous business logic by leveraging Jev's confidence scores to create decision trees (e.g., blocking messages based on fraud probability).
- Design scalable data pipelines by integrating specialized models like Jev with external data enrichment services (e.g., LinkedIn, company data) to qualify leads and detect fraud.
- Implement automated browser interactions by feeding Jev the DOM and history to predict the next necessary UI action (click/type) and the target element.
- Use Jev for content analysis, such as classifying whether a social media post is organic or paid, providing quantifiable insights for marketing and intelligence feeds.

## Topics

AI Automation, LLMs, Structured Output, Build Engineering, Fraud Detection, Decision Logic, Jev Automation Workflow, Treg GitHub Repo, AI Builder Club Workshop, Track.to/jff

Source: https://www.youtube.com/watch?v=o4Vi5uBZYH0