01 / JEV GUIDE
Jev 1.14 update: model selection, images and Box localization
An October 15, 2026 review of Jev 1.14, preview versus latest, experimental images and Box, long context and SDK migration checks.
Read guide →LEARN & BUILD
Jev guides: API integration and practical applications
19 Jev guide topics covering API integration, agent automation, record linkage, Playwright semantic tests and writing checks, with source-backed cases and limits.
Based on official documentation and project sources. Editorial suggestions and synthetic examples are not live model test results. This is an independent collection.
Model and integration
Understand Jev decisions, API setup, prompts and model selection.
02 / JEV GUIDE
What is Jev? A practical guide to decision models
Understand TypeSafe Jev, its typed outputs and practical use cases, with browser automation, MCP and context-filtering projects.
Read guide →03 / JEV GUIDE
Jev API quickstart: send and validate your first request
Build a Jev API request with state, typed questions and Bearer authentication. Download a JSON fixture and review response checks.
Read guide →04 / JEV GUIDE
Jev prompt examples: Choice, Score and Noul
Write focused Jev questions with original feedback-routing examples, explicit criteria and a practical edge-case checklist.
Read guide →15 / JEV GUIDE
Jev vs generative LLMs: decisions, generation and code
Compare Jev and generative LLM task boundaries through rewriting and script-review cases. Typed output does not establish correctness or performance.
Read guide →Automation and workflows
Connect decisions to browsers, agents, context management and work messages.
05 / JEV GUIDE
Jev MCP setup: connect a decision tool to your coding agent
Understand Jev MCP setup, evaluate tool arguments, credential routing and the difference between a working connection and a live model call.
Read guide →06 / JEV GUIDE
Jev for Claude Code context compaction: choosing a project
Compare Winnow and fast-jev-compaction by integration point, preservation strategy and failure checks for Claude Code context management.
Read guide →09 / JEV GUIDE
Jev browser automation with Playwright and Computer Use
Extract candidates from the DOM or accessibility tree, let Jev select an action, and execute through Playwright or Computer Use. Understand replay and stale-page limits.
Read guide →11 / JEV GUIDE
Jev n8n integration: community nodes and email routing
Understand the TypeSafe AI community node, self-hosting, State and Choice outputs, then design email routing with review and bounded retries.
Read guide →17 / JEV GUIDE
Jev for Feishu message triage: personal tasks and urgency
Understand Work with Jev: role-aware Feishu message classification, four Noul signals, manual review and a cross-chat task queue, with synthetic acceptance cases.
Read guide →Retrieval and record linkage
Separate classification, retrieval, reranking and entity matching.
07 / JEV GUIDE
Jev text classification and task routing: labels to fallbacks
Design Jev Choice classification with distinct labels, unknown inputs and review paths, then explore model-routing and semantic-filtering projects.
Read guide →08 / JEV GUIDE
Jev RAG reranking: semantic search and relevance filtering
Place Jev after retrieval: define relevance, preserve provenance, distinguish snippets from full text and evaluate rankings with labeled queries.
Read guide →18 / JEV GUIDE
Jev + Python record linkage: entity matching with jlink
Use jlink to reason about entity matching: candidate generation, Jev pair judgments, assignment constraints and audits for false links and missed matches.
Read guide →Testing and quality checks
Design reviewable tests, moderation, citation checks and writing rules.
10 / JEV GUIDE
Jev content moderation: Discord spam detection and false positives
Use Jev to assess messages while the application decides whether to allow, review or act. Explore Discord moderation rules, thresholds and failure handling.
Read guide →12 / JEV GUIDE
Jev citation verification: evidence extraction and claim support
Separate finding a paper, locating its evidence and judging claim support. Explore citation-review cases, abstract limits, numeric checks and human verdicts.
Read guide →16 / JEV GUIDE
Jev + Playwright semantic testing: assertions about page state
Use semantic-assert to check the meaning of UI feedback with Jev. Separate exact assertions, state capture, retries, redaction and failure evidence.
Read guide →19 / JEV GUIDE
Jev writing quality checks for Markdown and technical docs
Turn writing requirements into line-level checks and document scores with slop-grader. Design custom rules, review false positives and preserve meaning during edits.
Read guide →Video and games
Explore decisions over text segments and finite actions in creative applications.
13 / JEV GUIDE
Jev video analysis: transcript scoring, timestamps and clip selection
Explore JevMeter and audio beeping: transcribe and align first, evaluate text, then edit media in code. Distinguish rhetoric scores from fact-checking.
Read guide →14 / JEV GUIDE
Jev game NPCs: legal actions, decision loops and fallbacks
Explore NPC decisions through Jev Lab and HEIST//ONE: local state, finite actions, stale responses, rule-based fallbacks and live-model versus replay checks.
Read guide →