User repository on GitHub
Jev Engineering: Typed Decision Systems for Reliable Agent Workflows. Paper, diagrams, and companion examples by Av1dlive.
- Forks
- 5
- Last pushed
- Updated Sep 2026
Repo stats from the GitHub API, cached Oct 2026.
Jev directory
CommunityJev Practices & Patterns
Jev Engineering: Typed Decision Systems for Reliable Agent Workflows
A 34-page technical review and implementation framework by Av1dlive for using Jev's typed decisions inside agent workflows, separating observation, model judgment, deterministic policy, authorized action, and outcome verification.
- Stars
- 13
- Language
- JavaScript
- Reading time
- 2 min
- Published by
- Community
- Author
- Av1dlive
- Last verified
- Oct 2026
- Languages
- JavaScript
- Platforms
- CLI
- Capabilities
- Open source
Highlights
- The illustrated paper ships with an editable manuscript, eight original diagrams, a workflow demo, and a reusable integration prompt.
- Separates observation, model judgment, deterministic policy, authorized action, and outcome verification across agent workflows.
- Offline example: node jev-workflow-demo.mjs --self-test runs 30 checks of validation and policy behavior using synthetic responses.
- An optional --live mode reads TYPESAFE_API_KEY, prints an advisory result, and does not execute a business action; it incurs provider usage.
- Practice cases are fictional, and demonstration thresholds are described as uncalibrated rather than production settings.
Quickstart
bash
node jev-workflow-demo.mjs --self-testWatch out
Copy reviewed against the repository README on 2026-10-15. It is an independent review, not an official TypeSafe publication, a peer-reviewed paper, or a model benchmark; API details and pricing reflect a 19 September 2026 snapshot, and the 30 self-test checks measure validation and policy behavior, not Jev's semantic accuracy.
Questions about this entry
Short answers drawn from the linked project or page.
A 34-page illustrated paper and implementation framework by Av1dlive for typed decision systems in agent workflows, published 19 September 2026 with diagrams, an editable manuscript, and companion examples.
It separates five stages: observation, model judgment, deterministic policy, authorized action, and outcome verification, so model output stays distinct from the policy that authorizes an action.
With Node.js 20 or newer and no package installation, run node jev-workflow-demo.mjs --self-test. The 30 offline checks test validation and policy behavior using synthetic responses.
It reads TYPESAFE_API_KEY from your environment, makes a provider request that incurs usage, and prints an advisory result without executing a business action.
No. The README describes it as an independent technical review and proposed implementation framework, not an official TypeSafe publication, a peer-reviewed paper, or a new model benchmark.
The paper PDF, an editable manuscript with numbered references, eight diagrams, a dependency-free workflow demo, an example native TypeSafe request, fictional practice cases, and an integration prompt for coding assistants.
No live provider request was made for the paper, demonstration thresholds are uncalibrated and not production settings, performance figures carry their evaluation boundaries, and API details and pricing reflect the 19 September 2026 research snapshot.
Reactions & coverage
Posts, threads, and videos about this entry from around the web.
X: How the agent stack moved in Jev's first three days
YouTube: Diogo Almeida tells swyx what System One is, why RLHF failed his automation goal, and why AI should eventually disappear.
X: The 10-step roadmap, summarised
X: Giving your agents a decision brain
More Jev resources like this
A zero-dependency Node tool that finds where a folder of Markdown notes contradicts itself: crosscheck judges every note pair from both sides, and ask puts one plain-English question to every note and ranks the folder by probability.
Jev Tools & CLIs#community#catalog-import#logicrw
Community
nothans/sieveJavaScript
nothans/sieveJavaScriptAn open lab for using Jev correctly next to Claude Code: a patched jev-router with per-turn model routing, a health-gated fallback with alerts, and write-ups of two silent bugs and of where tokens actually go.
Jev Practices & Patterns#community#catalog-import#logicrw
Community
pasblinn/jev-labTypeScript
pasblinn/jev-labTypeScriptA local guard layer for AI coding agents: it evaluates delivered tool hooks against deterministic rules, blocks dangerous ones in milliseconds with no model in the decision path, and keeps a grep-able local activity log for auditing.
Jev Tools & CLIs#community#catalog-import#logicrw
A MoonBit and TypeScript playground for Jev: an API client for noul, choice, and score questions, a single-question CLI, Jev-vs-Jev gomoku with real-time GIF replay, and experiments like an ESLint plugin whose verdicts come from Jev.
Jev Repos & SDKs#community#catalog-import#logicrw
Community
mizchi/jev-playgroundTypeScript
mizchi/jev-playgroundTypeScriptA guard for coding agents that puts Jev in front of every step: it judges tool calls for intent and risk, scans tool outputs for instructions aimed at AI agents, and checks replies, mapping probabilities to allow, ask or warn.
Jev Agents & MCP#community#catalog-import#logicrw
Community
harshwasan/pi-jev-sentinelTypeScript
harshwasan/pi-jev-sentinelTypeScriptOpen-source Codex plugin that consults TypeSafe Jev about tools, models, tasks, skills, context, and strategies, diagnoses failed commands, and checks completion claims against evidence. The current package is version 0.4.0.
Jev Agents & MCP#community#catalog-import#logicrw
From the Jev guides
Original write-ups on what this entry is for.
From the Jev AI model community
Posts from builders shipping with Jev right now.