Guides
Jev workflow guides
Small, typed questions composed in code. These notes follow official primitive names and sourced repositories. They are not a substitute for TypeSafe docs.
Route a support ticket with Choice, Score, and Noul
Build one Jev request that picks a team, rates urgency, and checks for an explicit refund ask.
Read guide →2026-09-20Why LLM Summaries Break Coding Agents: The Case for Verbatim Context Pruning
A plain-English deep dive into context compaction. Why traditional LLM summaries erase crucial stack traces and paths, and how fast-jev-compaction uses binary Jev decisions to keep context lean and lossless.
Read guide →2026-09-23When not to use Jev
Keep Jev on System One judgments. Do not send it work that needs generation, tools with arguments, or slow reasoning.
Read guide →2026-09-20The Dual-Speed Agent: Coupling Codex with Jev for Fast Harness Decisions
Decouple deep reasoning from instant decisions. Use Codex as the engineer for architecture and code, and Jev as the fast evaluator, router, and risk gatekeeper.
Read guide →2026-09-23Confidence Cascades: Escalating Low-Certainty Decisions from Jev to Deep LLMs
Do not choose between speed and accuracy. Use Jev as the high-throughput frontline filter, and automatically escalate decisions with sub-95% confidence to deep reasoning models for verification.
Read guide →2026-09-23Decision-Native Computing: Why Tomorrow's Software Separates Judging from Generating
Why the future of software has two distinct AI calls: Generation Calls (to produce text) and Decision Calls (to choose which code branch to run). How HA-Jev, Kev (0.5B on-device), and the Decision Runtime pattern turn sensor states into real-world automated actions.
Read guide →2026-09-23Jev for Beginners: What It Does, Hands-On Tests, and Its Limits
A summary of programmer Yupi's hands-on Jev review: the three question types, why Jev is fast, a 1,000-email test against DeepSeek V4.1 Flash, where a match-pairs game fell short, and the limits he lists. With a runnable request.
Read guide →2026-09-25What 5,314 Jev Cases Show: A Summary of Jinqiu Research's Study
Jinqiu Research sorted 5,314 public Jev case records into 1,912 applications. Gates, action control, and routing make up over half, and only about 11% have reached product or framework integration. The numbers, examples, and caveats, summarized.
Read guide →2026-09-25Screening 80,000 E-Commerce Products with Jev in About an Hour
A worked example of high-volume product selection for Amazon FBA and TikTok Shop: batch margin, size, IP, and MOQ checks into one Jev request per product, and screen 80,000 listings for about $5 in a little over an hour.
Read guide →2026-09-27