---
title: "Advisor checklist: what to check before recommending Jev for a decision"
type: community
source_tier: community
tags: [consult, advising, checklist, failure-reports, limitations]
created: 2026-09-25
updated: 2026-09-25
confidence: medium
sources:
  - raw/docs/model-jaggedness__jev-1.13.md
  - raw/docs/models.md
  - raw/x-repos/collapseindex__jev-ultralightspeed.md
  - raw/community/agentjournal-dev-blog-llm-judge-vs-feature-extraction.md
  - raw/x/trycua-2101437979180904640.md
  - raw/x/umezawakanta13-2102062482991001689.md
  - raw/x-repos/allebee__jevgrep.md
  - raw/x-repos/eugeniughelbur__jev-engineering__results-2026-09-20-injection-test.md
  - raw/x-repos/eugeniughelbur__jev-engineering.md
jev_version: "jev-1.13.0"
summary: "Ten checks to run on every decision before recommending Jev (generation, missing evidence, options, latency, price, gates, agents, baselines, security, community tools), each pointing to its evidence."
---

# Advisor checklist: what to check before recommending Jev for a decision

> **TL;DR** Run these ten checks on every decision that survives the fit test in [[ideas/consult]], before it goes on the shortlist. Each item names the evidence behind it; open that page only if the user asks why. Moved from the end of [[ideas/failure-reports]] on 2026-09-25 (every item and link kept) so a consult reads ~1.4k tokens here instead of ~9k there. All community tier; TypeSafe's docs win.

## When to run it

- **Every decision**, after step 3 of [[ideas/consult]] (the fit test) and before the shortlist.
- **A consequential gate** (blocks, pays, deletes or sends) also gets the mandatory failure check in the consult's "Rules for the advisor": read [[ideas/failure-reports-confidence]] and make validating the cut on the user's own labels part of the recommendation.
- Evidence rows cited below sit on [[ideas/failure-reports]] unless another page is named; section names are given so you can jump straight to the row.

## The checklist

| # | Check | Evidence |
|---|---|---|
| 1 | Does the answer need generation, counting, date maths, geometry or lookahead? Put that in code and let Jev pick from the candidates (§2–§4, §9). | [[concepts/jaggedness-jev-1-13]] §2 math, §3 dates, §4 indirection, §9 generation; failure-reports sections "Generation or sampling misuse" and "Arithmetic, numbers, spatial state and time series" |
| 2 | Is the needed evidence actually in `state`? Test against a stub that always answers the same; measure any trim before using it (a short prefix trim collapsed agreement in jev-ultralightspeed). | jev-ultralightspeed row (collapseindex), failure-reports section "Wrong role, or options that don't fit" |
| 3 | Do the options cover reality, with "other/none", one judgment each, and few enough to tell apart (one Choice over a dozen close accounts lost badly: agentjournal)? Shuffle the order in evals; check no option is never chosen. | agentjournal's numbers: bookkeeping row on [[ideas/head-to-head]] ("vs classic methods, engines and people"); pointer row in failure-reports "Wrong role, or options that don't fit"; many-class caveat on P26 ([[ideas/patterns-data]]) |
| 4 | Faster than reported round trips (260–280 ms hosted form-fill; 976.8 ms median in a browser, Mario)? Pause per decision or skip Jev. | @trycua's form-fill row on [[ideas/field-reports]] ("Where it disappointed or broke"); Mario 1-1 row (@umezawakanta13), failure-reports "Speed: too slow for games, or fast but less accurate"; latency vs question count: [[ideas/request-mechanics]] |
| 5 | Price it: calls/hour × input tokens (`state` plus every question's wording) × $0.042/Mtok, with grouped questions. | [[ideas/cost-ledger]]; list price: [[reference/models-and-pricing]] |
| 6 | Gate on confidence only after calibrating on the project's own labels, per question; Noul for gates. | [[ideas/failure-reports-confidence]] |
| 7 | Adding Jev to an agent? A/B the whole agent: in most builder A/Bs success did not rise and time often did. | [[ideas/head-to-head-agents]] |
| 8 | Baseline rules, keywords, a regex, grep, n-grams, BERT, a solver or a small LLM on the same items; use Jev where it wins or ties cheaper. | failure-reports "A simpler tool won"; [[ideas/head-to-head]], [[ideas/head-to-head-security]]; [[syntheses/when-not-to-use-jev]] |
| 9 | Never the sole security gate (self-describing text was scored as its own label; a floor that caught all 5 successful injections escalated 58% of clean traffic); no trading recommendations. | jevgrep (allebee) and jev-engineering (eugeniughelbur) rows, failure-reports "Wrong role, or options that don't fit"; [[ideas/head-to-head-security]]; P03 on [[ideas/patterns-agents]]; trading: P25 (poor) on [[ideas/patterns-data]] |
| 10 | Naming a community tool, route or package? Read its row flag and the Warnings block first. Never offer a Warnings-listed service as the way in, even while direct signup is closed; call anything else "community, unofficial". | [[ideas/warnings]] (receipts: [[ideas/warning-receipts]]); vendor routes: [[ideas/platforms-and-gateways]]; access: [[entities/typesafe-console]] |

## Related

- [[ideas/consult]] — the procedure this checklist belongs to
- [[ideas/failure-reports]] — the failure rows behind items 1-4, 8 and 9; [[ideas/failure-reports-confidence]] — item 6
- [[concepts/jaggedness-jev-1-13]] — the official failure modes; [[guides/testing-and-evaluation]] — the 50-case experiment

## Sources

Files in frontmatter `sources:` (captured by 2026-09-25); original URLs are on the evidence rows linked above. The price is TypeSafe's ([[reference/models-and-pricing]]).