Structured extraction
Pull typed fields out of messy text by choosing among candidates rather than generating them.
18 rows are filed under this pattern, 18 of them with code. Rows are listed as the catalogue orders them: official first, then rows with code, then by stars.
Filter and search them in the catalogue →
Rows marked “not Jev itself” or “shadow mode” stay listed, but they are not examples of deciding with Jev.
-
Cookbook: Date extraction
Extracts absolute and relative dates by asking for the parts a document names, then resolving and validating them in code with confidence-based review.
-
Cookbook: Pre-parsed value extraction
Regexes find candidate emails, phone numbers and amounts; the model selects the requested span so code can normalise a verbatim value.
-
Cookbook: Structure recovery
Reconstructs Markdown from plain text that lost its formatting, in two requests: one restitches hard-wrapped lines, one classifies every block.
-
Cookbook: Structured data extraction cascade
A two-stage mini-then-verify-then-reasoning cascade that reaches most of a big reasoning model's quality at a fraction of the cost.
-
jev4pg
Natural-language SQL and 41 semantic operators for PostgreSQL. Filtering, extraction, ranking, matching and verification go to Jev in bounded batches with validated answers; a choice option needs 0.55 and a noul 0.8 to count. The authors report 98% accuracy against 92% for pg-jev's request path.written by a model
-
jev-reviewer
Data extraction for systematic reviews, quoted from the papers. Ask a trial report and its supplements your extraction form or a RoB 2, ROBINS-I, QUADAS-2 or TIDieR template; Jev points at the lines, every answer is a verbatim quote with its page, you check it and export the table. Files stay i
-
smart-paste
Fills form fields from pasted text: the form's heading, labels and your text go to TypeSafe, and it inserts the values it matches for you to review before submitting.
-
jev-macos-loop
Computer-use agent for native macOS apps on Apple silicon: OmniParser CoreML, Apple Vision OCR and accessibility labels find a window's controls locally, and Jev picks the next action with a choice from the observed text, never pixels. Input is guarded, and benchmarks check results, not Jev's DONE.written by a model
-
jevfill
A Chrome extension that fills web forms from unstructured notes with Jev: paste your details once as plain text, with no structured profile, then fill forms on demand.
-
JevSpan
Zero-shot named entity recognition for Chinese and English: code enumerates candidate spans at punctuation, and Jev choice questions nominate a window per entity type, verify each nominee (type, none, mixed or partial) and pick its exact boundary, keeping each entity's probability.
-
jeveryword
Text extraction with Jev: field extraction, PII detection and exact quotes, built on TypeSafe's Jev.upstream description
-
jev-mcp-dispatcher
Natural-language MCP tool dispatcher powered entirely by TypeSafe's Jev — no general-purpose LLM. Discovers a simple MCP server's tool signatures at runtime and uses Jev's typed primitives (Choice/Noul) to pick the right tool and extract its arguments straight out of the sentence.upstream description
-
jev-information-extraction
Parsing the PDF and extracting the relevant informationupstream description
-
jevsume
ATS-friendly resume review powered by Jev (TypeSafe System One). The frontend extracts resume text the way a parser would, then a Cloudflare Worker runs typed JEV questions and composes a JevScore.upstream description
-
ask-jev
Standard-library CLI that hands an agent's small judgments to Jev within a 280 ms advisory budget: choose (a choice), check (a noul on whether evidence shows a claim), score, a batch of at most 32, and purify, a noul per passage keeping only relevant original lines. Fails open; the agent decides.written by a model
-
typesafe-ai-jev-example
Hands-on demos for TypeSafe's Jev (System One) model: six runnable examples and four field notes. Runs offline with no API key; samples/ holds real measured output from jev-1.13.0.upstream description
-
jev-data-questions
Bring a dataset and see the right chart: the UI inspects the CSV's shape and proposes insights, and Jev fills in the values.
-
smoking-extraction-benchmark
Synthetic smoking-history extraction benchmark comparing TypeSafe Jev and OpenAI structured outputs, with reproducible accuracy, cost, and latency results.upstream description