Walkthroughs, demos, and deep dives. Our notes first, the original next.
Real-time research powered by
The full collection
263 videos · showing 1–24
Start here
Codevolution takes a customer message from the TypeSafe playground into TypeScript, explaining Noul, Choice, and Score responses before combining them in one request. The closing examples make the boundary clear: use Jev for bounded judgments, a text model for writing, and ordinary code for exact calculations.
Duration: 22 minutes 12 seconds. View notes : What is Jev and How to Use it?More walkthroughs, examples, and different perspectives.
Anass Kartit compares sixteen hosted decision models and four local setups on his own 82-question test. Perplexity’s Decider leads his results; Jev scores 79 out of 82 and Microsoft Decision-1 scores 75. He also examines malicious instructions, reordered choices and differences between local runtimes.
Duration: 5 minutes 51 seconds.Instantly shows how Jev can check whether companies fit a sales team’s criteria, recognize buying signals and sort contact data. The presenter reports scoring 1,000 businesses in 6.8 seconds for about $0.045; that demonstration is not an independent performance test.
Duration: 21 minutes 22 seconds.Cole Medin shows how Jev screens incoming email, decides which messages deserve a draft, filters news and checks duplicates. He keeps a richer model for judgments needing more personal context.
Duration: 13 minutes 16 seconds.Derek Cheung demonstrates how to build an automated speed-to-lead system in n8n using Jev and OpenRouter. The workflow qualifies leads by analyzing text derived from user-submitted photos and voice notes, routing qualified prospects to receive generated media while pausing uncertain cases for human review in Slack.
Duration: 12 minutes 56 seconds.Tech With Tim evaluates the Jev decision model against traditional LLMs across four tests, including support ticket routing and shell command guardrails, highlighting its speed, cost-efficiency, and structured outputs.
Duration: 22 minutes 4 seconds.John Lindquist demonstrates using Jev to turn messy inputs into typed decisions for agent workflows, highlighting its speed, cost-efficiency, and limitations like menu size constraints.
Duration: 94 minutes 21 seconds.Simon Scrapes demonstrates how to combine Jev's rapid classification capabilities with Claude's reasoning to build efficient browser agents, highlighting both the architectural benefits and common failure points like iframes and false positives.
Duration: 12 minutes 2 seconds.Kai Pervölz and Trutz Fries discuss the mechanics and benefits of decision models like Jev. They explain how providing predefined options yields fast, structured probability outputs without generating text, using support ticket routing as a practical example.
Duration: 46 minutes 25 seconds.Reşit Abdullah Yavuzkol demonstrates how to set up the Jev model in Python using the TypeSafe SDK and Vercel AI Gateway. The tutorial covers basic configuration and runs a support ticket triage script using Choice, Score, and Noul questions to categorize requests.
Duration: 4 minutes 57 seconds.DSwithBappy builds a Python customer-support triage demo using FastAPI. Jev selects a department, scores urgency, and checks refund and human-review conditions, while optional LangChain and Groq generate a suggested reply.
Duration: 50 minutes 32 seconds.Mark Kashef compares OpenAI’s Decisions API with Jev through an image inspection, an outage investigation and a business report check. The image example uses OpenAI alone; the text examples show both systems.
Duration: 9 minutes 38 seconds.NextGenQA builds an n8n workflow that reads Outlook emails, uses Jev to choose a route and asks OpenAI to write a reply. It prepares Outlook drafts and records the results in Google Sheets.
Duration: 26 minutes 5 seconds.Parker Prompts builds four small apps with Claude Code and Jev: a support inbox sorter, a prompt checker, a podcast clip finder and a Y Combinator company matcher. Each gives Jev a defined decision rather than asking it to write a long answer.
Duration: 12 minutes 3 seconds.Code to the Moon introduces Jev through planet and atmosphere questions in its playground. He shows how context changes a decision and explains that the Mario example receives game state rather than screen images.
Duration: 7 minutes 25 seconds.Tyler Slaton's CopilotKit demonstration uses Jev to select existing interface components, then lets Claude fill the chosen layout with content.
Duration: 76 minutes 28 seconds.James Briggs compares hosted Jev with local GLiNER models. His examples separate confidence calibration from task accuracy and show why local response time can matter when a model controls a game.
Duration: 34 minutes 30 seconds.Sydney Runkle explains how LangChain chooses a model tier for each Open SWE task, using past task records, routing criteria and measured outcomes.
Duration: 13 minutes 39 seconds.TypeSafe co-founder Diogo Almeida explains why Jev returns bounded judgments instead of writing replies, and argues for combining those decisions with software rules.
Duration: 13 minutes 10 seconds.Rhesis AI demonstrates using Jev to check a travel agent's airline recommendations. The evaluator returns a category and probability, while the language-model judge also writes an explanation.
Duration: 5 minutes 0 seconds.Diogo Almeida explains why TypeSafe built Jev for machine-to-machine decisions rather than prose, and describes its probability outputs and training approach.
Duration: 89 minutes 40 seconds.The AI Automators trains Laya to choose among 30 support tools, compares matching basic and richer inputs with Jev, then examines how calibration changes automatic mistakes and human-review workload.
Duration: 14 minutes 48 seconds.Better Stack compares Jev and Clef on 200 channel comments using Claude as referee, then tests whether Clef's judgments of 225 thumbnails predict video performance.
Duration: 7 minutes 59 seconds.Harness briefly introduces Jev as an alternative to long generated replies, using a reported Doom demonstration to explain its focus on decisions.
Duration: 0 minutes 51 seconds.
