Lesson 03 · Jev 101
Use cases: decision slots Jev is built for
These patterns echo TypeSafe’s public use-case map and cookbooks. We don’t invent customer logos or unpublished wins. If you came from chat UIs, the “instead of prompting” lines are a translation — not the product definition.
Official category buckets come from TypeSafe’s use-case map. Rows tagged Educational are teaching hypotheses, not TypeSafe customer stories. Launch-week platforms and community builds — labeled, with URLs — live on Ecosystem. Chat-native habit pairs sit at the bottom and in the What’s the difference?.
Background automation / smart if-statements
Classify, route, score, and gate inside product paths where a human should not sit in every loop.
Support ticket triage
Instead of prompting ChatGPT to decide which queue owns a ticket, how urgent it is, and whether the customer is furious… Send ticket state plus Choice(queue), Score(urgency), and Noul(frustration or needs_human). Route in code.
Refund eligibility gate
Instead of prompting ChatGPT to decide whether we can auto-refund from a policy plus the message… Ask a Noul on eligibility (and optionally Score abuse risk). Auto-act only above your thresholds.
Spam / phishing quarantine
Instead of prompting ChatGPT to decide if this message is a phish in one chat reply… Compose several Nouls — credentials asked, sender mismatch, reward bait — then combine in code.
Content moderation
Instead of prompting ChatGPT to moderate a community post by chatting with a policy… Choice and Score on toxicity / spam / fraud with severity plus confidence. Escalate the middle band.
Insurance FNOL triage
Instead of prompting ChatGPT to read a first-notice-of-loss narrative and assign a desk… Choice on complexity, Score on missing information and fraud indicators, then route investigators.
KYC / AML alert prioritization
Instead of prompting ChatGPT to rank alerts with a long chat summary… Score suspicious characteristics against your rubric; send high scores to investigators.
Contract clause detection
Instead of prompting ChatGPT to ask ChatGPT whether a contract is “fine”… Noul or Choice per missing clause or prohibited claim. Keep the legal memo for an LLM or a lawyer.
Marketplace listing QA
Instead of prompting ChatGPT to decide if a listing is prohibited or counterfeit in prose… Choice on category issues plus Nouls for counterfeit signals; normalize attributes in code.
Brand safety for ads
Instead of prompting ChatGPT to ask a chat model if this creative is “on brand”… Choice / Score on suitability and prohibited claims. Threshold before the ad serves.
Invoice pay / hold / return
Instead of prompting ChatGPT to have a chat model narrate what to do with an invoice… Workflow-eval scenario: typed action over invoice state. Code executes pay, hold, or return.
Security incident contain / close
Instead of prompting ChatGPT to ask ChatGPT whether to page the on-call… Workflow-eval scenario: decide contain versus close from incident state, then let runbooks fire.
Expense claim approval
Instead of prompting ChatGPT to approve meals, travel, and equipment from a chat essay… Choice against policy criteria; keep numeric checks in code. TypeSafe evals use this as a toy example.
Opt-out / DNC detection
Instead of prompting ChatGPT to have SDR chat decide whether a prospect said stop… Noul on the message. Honor opt-out in code — do not generate a follow-up when P(yes) is high.
Churn risk from ticket text
Instead of prompting ChatGPT to guess churn from a support thread in chat… Score risk from the message plus account state; alert CSMs above a threshold. Educational mapping.
Verify other AI
Judge prompts, drafts, citations, traces, and tool calls — the company highlights verify / guardrail patterns.
LLM output guardrails
Instead of prompting ChatGPT to ask ChatGPT whether its own answer is fine… Take the draft or agent trace as state. Score policy, jailbreak risk, or “needs human.”
Citation support check
Instead of prompting ChatGPT to ask GPT to re-read the source and bless the claim… Choice: does this passage support the claim? Cookbook pattern.
Agent trace review urgency
Instead of prompting ChatGPT to skim a long agent log in a chat window… Workflow-eval observability: score whether a trace needs a human now.
Podcast or report claim check
Instead of prompting ChatGPT to paste a transcript and ask “any problems?”… Noul per atomic claim against the transcript. Educational mapping, not a customer story.
Semantic code lint in CI
Instead of prompting ChatGPT to ask ChatGPT to comment on every PR… Nouls against conventions and guidelines. Fail the check on high-confidence violations.
Shell command safety class
Instead of prompting ChatGPT to let an agent decide if a command is dangerous in prose… Choice: read_only / reversible / irreversible. Educational mapping for agent harnesses.
Make harnesses smarter
Routing, retrieval, tool picking, and feature extraction around LLMs and classical ML.
Model router
Instead of prompting ChatGPT to send every request to a frontier chat model… Score difficulty or risk, then Choice the model. Cheap path versus frontier path lives in code.
Tool / skill picker
Instead of prompting ChatGPT to let an LLM narrate which tool to call… Choice over tool or skill names plus a Noul for “use a tool at all.”
RAG passage filter
Instead of prompting ChatGPT to stuff every retrieved chunk into the prompt… Noul or Score relevance and injection risk before the LLM sees the passage.
Semantic rerank
Instead of prompting ChatGPT to ask a chat model to reorder 200 results as a list… Score query–candidate relevance after BM25; sort in code.
Resume screening
Instead of prompting ChatGPT to write a ChatGPT essay about each candidate… Score fit against job criteria; escalate uncertain cases to a human.
Lead / ICP scoring
Instead of prompting ChatGPT to ask ChatGPT if this account is worth a call… Score industry fit and intent; Noul buyer relevance. Queue the SDR list in code.
Hiring competency evidence
Instead of prompting ChatGPT to grade a work sample with a chat rubric in prose… Score against a predefined competency rubric. Keep the written feedback for an LLM.
Function-calling without LLM prose
Instead of prompting ChatGPT to hope tool-call JSON from a chat model parses… Map natural language onto typed function arguments with Choice over allowed values.
Feature engineering for classical ML
Instead of prompting ChatGPT to hand-label text features for CatBoost overnight… Autoresearch cookbook: Score and Noul features from text, then train a classical model.
Forecast enrichment signals
Instead of prompting ChatGPT to summarize tickets and hope a forecast model understands the essay… Extract intent and urgency features as Score / Noul, then feed numbers to the forecast.
PR risk matrix
Instead of prompting ChatGPT to ask ChatGPT how scary this diff is… Score security and complexity per file. Educational mapping for review routing.
Inbox sponsor inquiry sort
Instead of prompting ChatGPT to triage a form inbox with one mega-prompt… Noul + Choice + Score on the form fields. Educational mapping.
Map-reduce over large corpora
Many independent questions over chunks, then aggregate in code — instead of one giant summary judgment.
Map-reduce judgments over lots of text
Instead of prompting ChatGPT to prompt ChatGPT for one giant summary judgment… Decompose into many independent questions over chunks; aggregate in code (company theme).
Hierarchical patent / product class
Instead of prompting ChatGPT to ask a chat model to invent a taxonomy path… Beam search over Choice probabilities down a predefined tree.
Date-part extraction
Instead of prompting ChatGPT to ask which date is earlier in natural language… Choice over months and days, then assemble and compare in code. Jaggedness: do not do the math in the model.
Structure recovery / autoformat
Instead of prompting ChatGPT to ask an LLM to rewrite a messy blob as JSON… Stitch candidates, then Choice block types and Noul “is this a heading?” Official extraction theme.
Entity alignment / merge decide
Instead of prompting ChatGPT to ask ChatGPT if two records are the same person… Score merge / leave / send-to-curator. Humans take the uncertain band.
Knowledge-graph relation classify
Instead of prompting ChatGPT to extract free-form relationships as sentences… Typed relation Choice over a closed relation set.
Real-time UX / games
System One–shaped calls where the UX needs roughly 100 ms-class decisions. Company demos and claims; do not overclaim game results.
Game / real-time control
Instead of prompting ChatGPT to prompt ChatGPT on every frame (too slow, too pricey)… Action Choice on structured game state. Company demos exist; do not invent win rates.
Wikiracing / high-cardinality links
Instead of prompting ChatGPT to ask a chat model to invent the next article title… Choice among many existing links without inventing new ones. Company demo theme; cardinality up to 255 (launch blog).
Smart-home intent → device action
Instead of prompting ChatGPT to chat with the house until something happens… Evaluate the user request as a Choice over allowed device actions (official demo theme).
Anti-patterns (keep ChatGPT)
- Write the customer email
- Refactor this module
- Brainstorm product names
- Explain quantum computing like I’m 5
- Draft a multi-step plan from a blank page
- Generate image, audio, or video understanding
All 36 habit pairs
Pedagogical mappings from the corpus. Not A/B results.Educational = writer hypothesis for Luke-style teaching.
| # | ChatGPT / LLM habit | Jev / System One pattern | |
|---|---|---|---|
| 1 | Prompt: reply yes/no if this ticket is urgent. | Ask a Noul on ticket state, then threshold on the probability. | Theme |
| 2 | Prompt: classify billing / tech / other as JSON. | Ask a Choice with your label criteria, then branch on the choice plus confidence. | Theme |
| 3 | Prompt: rate severity 1–5 and explain. | Ask a Score on your severity levels. If you need an explanation, call an LLM separately. | Edu |
| 4 | Hope JSON.parse works on the reply. | Read typed answers. TypeSafe claims there is no prose-parse step. | Theme |
| 5 | Ask ChatGPT “are you sure?” | Use the returned confidence or probability distribution as the control signal. | Theme |
| 6 | Write one mega-prompt that decides everything. | Ask many atomic questions in one call; compose the policy in code. | Theme |
| 7 | Ask for chain-of-thought, then extract the decision. | Skip generation. Ask the decision directly. | Theme |
| 8 | Fine-tune a classifier whenever labels change. | Change Choice criteria per request. TypeSafe does not offer customer LoRA. | Theme |
| 9 | Route only with embeddings similarity. | Optionally add a semantic Choice or Score rerank on candidates (cookbook theme). | Theme |
| 10 | Let an LLM agent choose the next tool in prose. | Ask a Choice over tool names, then gate on confidence. | Theme |
| 11 | Run a second GPT call to check for prompt injection. | Ask cheaper Noul / Score guardrail questions (company framing). | Theme |
| 12 | Ask the model to count keywords. | Count in code. Use a Noul per item only when the question is semantic. | Theme |
| 13 | Ask which date is earlier. | Extract parts as Choice questions, then compare in code. | Theme |
| 14 | Generate a refund email and decide the amount in one reply. | Let Jev decide eligibility. Let an LLM write the email. | Edu |
| 15 | Moderate community posts in a chat window. | Ask Choice / Score questions with policy criteria and a confidence gate. | Theme |
| 16 | Ask for a JSON confidence field. | Use native probabilities. Do not invent a confidence schema in chat. | Theme |
| 17 | Retry the call when the JSON is invalid. | TypeSafe claims schema-constrained answers cannot type-error. | Theme |
| 18 | Paste the entire CRM history into the prompt. | Filter state. Send only the fields the decision needs. | Theme |
| 19 | One question per API round-trip. | Use speculative fan-out: batch questions in one request. | Theme |
| 20 | Ask an LLM to rank 200 links by writing a list. | Score or choose among candidates; sort in code. | Theme |
| 21 | Ask the model to invent categories. | Predefine the options. Include an “other” label if you need an escape hatch. | Theme |
| 22 | Use chat inside a real-time game loop. | Typed decisions at a ~100 ms company-claimed band for System One–shaped work. | Theme |
| 23 | Verify a citation by asking GPT to re-read the passage. | Ask a citation-support Choice over the passage (cookbook pattern). | Theme |
| 24 | Route models with hand-written rules only. | Ask Jev to Score difficulty or risk, then pick the model in code. | Theme |
| 25 | Screen resumes with a ChatGPT essay. | Score against job criteria; escalate when confidence is low. | Theme |
| 26 | Detect churn risk in a free-text reply. | Score or Noul on the message plus account state. | Edu |
| 27 | Ask “what should we do?” as an open-ended question. | Offer a Choice over the actions your product is allowed to take. | Theme |
| 28 | Parse invoice fields via LLM JSON. | Generate candidates with regex or an LLM, then let Choice select. | Theme |
| 29 | LLM-lint every PR with a comment. | Run semantic lint Nouls or Scores in CI. | Theme |
| 30 | Hide rage-bait with a GPT classify call. | Ask a per-item Noul or Choice in the feed pipeline. | Edu |
| 31 | Summarize first, then label the topic. | Label on the full or filtered state with a Choice. Summaries stay with an LLM. | Edu |
| 32 | Ask whether two hex colors are similar. | Convert colors in code. Ask Jev only semantic naming questions. | Theme |
| 33 | Write a double-negative prompt: “is it not false that…” | Keep wording literal. Rewrite as a positive atomic question. | Theme |
| 34 | Trust a single chat “yes” for a wire transfer. | Set a high-stakes threshold and require a human confirm. | Theme |
| 35 | Let an agent while-loop until it feels done. | Code owns the loop. Jev only answers the judgments. | Theme |
| 36 | Ask Jev to write the customer reply. | Don’t. Use a generative model. Jev is not trained to generate text. | Theme |