Breaking down 724 ads from 37 brands with Jev (X)

Post on X

Views: 1,067,992
Likes: 6,780
Reposts: 454

Read from X on 24 Sep 2026. Counts change daily.

Reported by the author

Speed: 724 ads/40sin 40 seconds it broke down 724 live ads from 37 brandsx.com
Cost: 9 centsused 9 cents of tokensx.com

Matthew Berman ran Jev over 724 live ads from 37 brands, extracting a structured breakdown of each one: the hook, the ad format, the offer, the call to action, the funnel stage it targets, and whether the ad’s promise matches what the linked landing page actually delivers. That is six extraction fields applied to every ad, closer to a classification and extraction pass than to generated ad copy or written analysis.

He reports the full run took 40 seconds and 9 cents of token spend for all 724 ads. He says the pairing will ship inside StealAds and as an MCP tool.

Open on X

View the post on X

Use casesStructured extraction

Introducing System One Models and Jev (Hacker News launch thread)

The 1,978-point, 513-comment launch thread. The top comment calls the speed comparison misleading, since Jev only returns structured output, and disputes the cannot-hallucinate claim because a valid type can still hold a wrong value. Others note ordinary LLMs can already be forced into structured output.

albelfioOpen

DiscussionIntent and model routing+3

DSPy: programming, not prompting, language models

Declares typed input/output Signatures for LLM modules and optimizes the underlying prompts and weights against a metric. Its Signature abstraction is the closest widely-used open equivalent of Jev's typed-question interface. Star count is GitHub's rounded display figure.

stanfordnlp38k starsOpen

AlternativeStructured extraction+3

Outlines: structured outputs for LLMs

Guarantees valid structured output during generation by constraining decoding to a grammar or schema. The mechanism HN commenters repeatedly cited as already covering Jev's cannot-produce-a-type-error guarantee on ordinary LLMs. Star count is GitHub's rounded display figure.

dottxt-ai16k starsOpen

AlternativeStructured extraction+2

Instructor: reliable JSON from any LLM

Pydantic-based library that extracts typed, validated structured data from LLMs across providers with automatic retries. The established way teams get Jev-style typed answers today, at LLM latency and cost. Star count is GitHub's rounded display figure.

567-labs14k starsOpen

AlternativeStructured extraction+1

GLiNER: generalist lightweight NER

Compact encoder model that takes the label set as input at inference time and extracts arbitrary entity types zero-shot on CPU. Same classifier-that-takes-its-categories-as-input shape, for extraction rather than decisions. Star count is GitHub's rounded display figure.

urchade3.9k starsOpen

AlternativeStructured extraction+2

vercel-labs/ai-cli

Vercel Labs CLI for generating from the terminal. Its evaluate command takes a state plus typed questions and defaults its evaluation model to typesafe-ai/jev on the AI Gateway, with -m jev as the shorthand and an --input flag for text or JSON state.

vercel-labs813 starsOpen

ToolStructured extraction

Menu