signalLenny's Newsletter2026-10-06
🎙️ How I AI: 8 real Jev use cases + How OpenAI uses ChatGPT Sites (live at DevDay!) + Claire’s DevDay recap
John Lindquist demonstrates eight real Jev use cases, including real-time voice assistants, data deduplication, and chess analysis. Jev is a fast, cheap decision engine that turns unstructured input into structured decisions, costing 73 cents across 23 development runs. The chess benchmark ran 10 times faster and 4 times cheaper than a low-reasoning LLM, making brute-force analysis viable.
- for who
- Developers building AI agents or applications that need fast, cost-effective decision-making.
- why now
- Jev's DevDay debut and sub-cent costs signal a new decision-model market window.
- what changes
- Developers can replace many traditional if/else and routing logic with natural-language decision calls, making previously impractical brute-force approaches simple and affordable.
- to do
- Identify branching decisions in your app and route them through Jev, while keeping open-ended reasoning on LLMs.
key points
- Jev outputs structured decisions, not text, enabling routing, classification, and function calls.
- Cost: 73 cents for 23 runs, 5GB JSON processed for 40 cents.
- Chess analysis: under a second, 10x faster and 4x cheaper than low-reasoning LLM.
#Jev#ai decision model#cost optimization#workflow#agent
score
score 8 out of 10. 0-10: how dense the facts are, multiplied by how much you can do with them after reading. 8+ means the topic's evidence bar is met: benchmarks and availability for a new model, amount and investors for a funding round, revenue figures for a solo-money story. Below 5 an item does not enter the digest. A press release scores 3 or less, a reprint loses 2, anything older than 14 days loses 1, a headline that misleads loses 3.
read the source