Consult guide: could Jev help this project?
TL;DR Someone shows you a project and asks whether Jev fits. List the project's decisions, keep the ones that are narrow, semantic and frequent, match each to a pattern in Decision patterns from the community (with fit verdicts), and return a ranked shortlist with cost, fit and caveats. Read about 10-15k tokens of this wiki, not the whole corpus. "Jev does not help here" is a valid and useful answer.
Reading budget
Links like [[ideas/patterns]] resolve to https://fakenerd.ai/jev-wiki/raw/wiki/ideas/patterns.md (same rule for every [[dir/slug]]). You do not need llms.txt (~7k tokens) for a consult; come back to it only if you need a page not linked here.
| Step | Page | ~Tokens | When |
|---|---|---|---|
| 1 | this page | 2k | always |
| 2 | Decision patterns from the community (with fit verdicts) | 5k | always |
| 3 | Jev 1.13 jaggedness: known failure modes | 3k | if any candidate touches numbers, dates, long state, or adversarial input |
| 4 | one of Community repos: what people built and how they use Jev or Field reports: independent evaluations, critiques, open replicas | 3-4k | only when a pattern's "Seen in" points there, or the user asks "does this really work?" |
| 5 | one official pattern or cookbook page named in the pattern's Map line | 2-5k | only for the top 1-2 candidates, to sketch the design |
| alt | Choosing between Choice, Score, Noul | 3.4k | only when a surviving decision matches no pattern; it replaces step 5, not adds to it |
Skip llms-full.txt. Skip the SDK and HTTP reference until the user decides to build; then switch to Playbook for LLM agents building with Jev.
Procedure
- Get the project in front of you. Read the repo, spec or description the user gave you. You need: what goes in, what comes out, where an LLM or a pile of
ifstatements currently makes a judgment, volume per day, and latency expectations. - List the decisions, not the features. Walk each flow and write one line per judgment: "is this ticket urgent", "which of 40 tools applies", "does this diff need a human". Include decisions currently made by LLM calls, regexes, keyword lists, hand-tuned heuristics, or a human queue. @Av1dlive's prompt for this (see Decision patterns from the community (with fit verdicts)) is the same idea: ask the coding agent to enumerate every decision point before proposing anything.
- Filter each decision with the fit test below. Drop the ones that fail. Be strict; most value comes from 2-5 decisions, not 20.
- Match survivors to patterns. Find the closest
Pxxin Decision patterns from the community (with fit verdicts). Take its primitive, its fit verdict and its Map links. No match is fine: design it from Choosing between Choice, Score, Noul. - Group, then estimate cost and latency. First group surviving decisions by shared state: every question about the same email, ticket or page goes in ONE call (Speculative fan-out); cost the call, not each decision. Input tokens per call = state + all questions. Cost = tokens x $0.042 per million for
jev-1.13.0/jev-latest; output is free. Worked example: 350-token email + 10 questions (~400 tokens) = ~750 tokens/call; x 40,000 calls/day = 30M tokens/day = $1.26/day, about $38/month. Limits: 64k tokens per request, 32k for state plus the longest question, 1,200 requests/min, 250k tokens/s (Models, aliases, pricing, rate limits, context). TypeSafe states 70-500 ms per call; community reports vary (Field reports: independent evaluations, critiques, open replicas). - Return the shortlist in the format below, best first, and say what you would not use Jev for.
Fit test
| Signal | Verdict |
|---|---|
| Output is one of a known set, a yes/no, or a rating on a rubric | required; otherwise stop |
| Needs semantic understanding that rules or regex handle badly | strong |
| Happens often (per message, per step, per row) or sits on a latency-critical path | strong |
| You can act differently on low confidence (escalate, ask, skip) | strong; see Confidence-gated routing |
| Replaces an LLM call whose answer is parsed into a branch | strong |
| Needs arithmetic, counting, date/time comparison, exact thresholds on numbers | poor; compute in code, ask Jev only the semantic part |
| Needs several hops of inference or implicit intent | workable only if split into literal questions |
| State is large and mostly irrelevant | workable only after filtering state |
| Needs generated text, explanations, code, summaries | not Jev; use an LLM, optionally with Jev as router/judge around it (Jev vs LLM JSON mode / structured outputs) |
| A deterministic rule already works | keep the rule |
| Wrong answers are costly and there is no review path | workable only with confidence gating and an eval set (Testing and evaluating a Jev workflow) |
Shortlist format
Return a table, then two short paragraphs. Fit is strong (do it), workable (only with the stated mitigation) or poor (do not; say what to use instead). When several rows share one call, put the cost on one "shared call" row and write "shared" in the others.
| # | Decision in this project | Pattern | Ask (primitive + criteria sketch) | Code does | Fit | Est. cost / volume | Caveat |
|---|
- Recommended first step: the single cheapest experiment (usually one decision, 50-100 labelled examples, measure agreement and repeatability).
- Not recommended: the parts of the project where Jev is the wrong tool, and why.
Rules for the advisor
- Official pages win. Everything under
ideas/is community-sourced; when a post disagrees withreference/orconcepts/, follow the official page and say so. - Attribute performance numbers ("@handle reports ..."); do not promise the launch multipliers.
- Keep private project details in your own session. Nothing about the user's project belongs in this wiki.
- Trading, betting and other money-moving ideas: describe the engineering only, flag the numeric and time-series weakness, give no financial advice.
- Access is gated by TypeSafe (early access); check console.typesafe.ai (console + playground) and Models, aliases, pricing, rate limits, context before promising availability.
More precedents
The community keeps a larger, unaffiliated demo list at https://jevdemos.netlify.app (curated by @thisiskp_). It is titles, one-liners and videos, useful for browsing once a pattern here has matched; it is not mirrored in this wiki.
Related
- Ideas section overview — what the ideas section contains
- Decision patterns from the community (with fit verdicts) — the pattern bank this procedure matches against
- Field reports: independent evaluations, critiques, open replicas — independent results and critiques
- Community repos: what people built and how they use Jev — working code to borrow from
- Playbook for LLM agents building with Jev — switch to this once the user decides to build
- Use-case map by industry — TypeSafe's own industry map
Sources
- wiki/guides/agent-integration-playbook.md, wiki/concepts/jaggedness-jev-1-13.md, wiki/concepts/system-one.md, wiki/reference/models-and-pricing.md, wiki/guides/choosing-a-primitive.md
- raw/x/INDEX.json (61 curated community posts, captured 2026-09-20)
