Jev-style
A way to structure AI prompts and responses for clearer, more predictable interactions.
Jev-style is a method for interacting with AI models. It involves giving the AI specific instructions and expecting structured answers back.
Think of it like filling out a form. Instead of just asking a question, you provide the AI with a template or a set of rules for how to answer. This helps make the AI's output more organized and easier for other programs or people to use.
Jev-style refers to an API design pattern emphasizing structured input and output for Large Language Model (LLM) interactions. It aims to improve the predictability and parsability of LLM responses by defining explicit formats for prompts and expected outputs, often using JSON or similar schemas. This contrasts with freeform text generation, enabling more robust integration into software workflows.
The primary benefit is increased reliability in AI-driven processes. By enforcing structure, developers can reduce errors caused by ambiguous or unexpected LLM outputs, making it easier to build applications that depend on AI decision-making.
OpenAI's recent API update highlights a move towards more predictable AI interactions. This focus on structured answers aligns with the concept of Jev-style, which emphasizes clear input and output formats for large language models. As developers seek more control and consistency, API designs that facilitate this structured approach are gaining attention.
- llm-openai-decisions 0.1a0OpenAI · Simon Willison ·
- OpenAI ChatGPT
- OpenAI's new API provides structured answers, aligning with the Jev-style concept of predictable AI interactions.
- JSON mode
- JSON mode specifically enforces that the AI's output is valid JSON, w
- Function calling
- Function calling allows an LLM to output a JSON object describ
The term 'Jev-style' appears to originate from community discussions and specific implementations within AI development, likely named after an individual or a project that popularized this structured interaction method.
Ask an AI chatbot to act as a travel agent. Instead of just asking for flight options, instruct it to provide the answer in a specific format, like a JSON object with keys for 'airline', 'flight_number', 'departure_time', and 'arrival_time'. See how it handles the structured request.
The Playbook: reusable how-tos, prompts, configs and tips pulled out of the news.
- PromptRole-play a student struggling with math for AI tutor simulationSimulate a student's math struggles and uncertainty for AI tutor evaluation. · 5 min
- TemplateReusable workflow templates for healthcare teamsTeams can create and share templates for common workflows like documentation or prior authorizations. · 15 min
- TemplateTemplate for building an AI tool tailored to your workA structured approach to defining and building a custom AI tool for specific business needs. · 15 min
- TemplateEvals CSV prompt list for agent skillsA CSV file template for listing prompts used in evaluating agent skills. · 20 min
- HeuristicDouble coding agent task completion with docs linksProviding coding agents with a documentation link significantly increases their task completion rate. · 2 min
Questions people ask
- What is the main goal of Jev-style?
- The main goal is to make AI responses more predictable and easier to use in software by structuring both the input and the output.
- Is Jev-style only about JSON?
- While JSON is a common format for Jev-style outputs, the concept is broader and refers to any structured format that makes AI interactions more reliable.
First seen on Subvolts Oct 6, 2026. Updated Oct 13, 2026. Written by an AI model from the items above and reviewed against them weekly; report an error.