Walkthroughs, demos, and deep dives. Our notes first, the original next.
Real-time research powered by
The full collection
263 videos · showing 25–48
IndyDevDan discusses model usage on OpenRouter and describes adding Jev to his Pi coding agent. His rough 20% token-spend saving is a personal estimate, not a controlled comparison of cost, speed or work quality.
Duration: 26 minutes 8 seconds.AVB explains BEV, an independent decision model inspired by Jev. It adapts pretrained Qwen layers and adds a small head that compares choices, answers yes/no questions and scores ordered levels.
Duration: 108 minutes 59 seconds.Cmpnd explores DSPy’s Jev integration and the ReAnchor optimizer. Typed signatures describe small decisions, and agent examples apply them to shell-command checks, tool selection and filtering history.
Duration: 62 minutes 13 seconds.TypeSafe's Allie Laabs discusses bounded decisions, combining Jev with language models, and asking several questions about the same input in one request.
Duration: 31 minutes 27 seconds.A short science segment in eR33t's mixed stream reports a Conway's Game of Life test over all 512 local patterns. It contrasts asking for the next state directly with reading cells separately and letting exact code apply the rule.
Duration: 61 minutes 28 seconds.bhupen and Grokkers introduce Jev through VoltCart, an electronics support assistant. The lesson separates routing, urgency and fault checks from writing a reply, then explains why a valid output can still be the wrong decision.
Duration: 11 minutes 45 seconds.Martin Keen explains Jev’s typed decisions through a support email: whether it asks for a refund, which team should handle it, and how urgent it is. He connects probability outputs and calibration to software thresholds, human review, and workflows where an LLM still writes the customer reply.
Duration: 15 minutes 3 seconds.Hosts Hannes Rudolph and Patrick Erichsen discuss Jev with Allie Laabs and Josh Lehman, then OpenClaw Enterprise with Kevin Lin. They explore small decisions in agent software, experimental harness and plugin integrations, and the separate security boundaries needed to manage agents at work.
Duration: 59 minutes 23 seconds.Pico AI Lab demonstrates choosing a skill in two steps and ranking retrieved passages, with fallbacks and limits for each decision.
Duration: 10 minutes 20 seconds.Programando en JAVA walks through using Jev to judge an answer generated through Ollama. The Spring AI example combines relevance, quality and category decisions with a separate check that the answer is not empty.
Duration: 14 minutes 17 seconds.This Hindi/Hinglish walkthrough builds a Python movie assistant: Jev chooses a route, LangGraph connects the steps, and a Groq-hosted language model supplies prose and extracts movie details.
Duration: 102 minutes 46 seconds.Agora’s short demo uses a voice agent called Ruby to explain context-aware turn-taking. Jev reads the transcript rather than the audio: the conversation illustrates waiting while someone asks for more time, staying quiet during side-talk, and continuing through brief acknowledgements such as ‘okay’.
Duration: 1 minutes 21 seconds.Aishwarya Srinivasan explains Jev’s three question types through support-ticket routing and agent checks, separating a valid answer format from a correct decision.
Duration: 22 minutes 2 seconds.Cole Medin demonstrates Jev checks before tool calls, game and browser testing, and classification of GitHub work into workflow steps and model tiers.
Duration: 17 minutes 39 seconds.Claire Vo and John Lindquist discuss Jev demonstrations spanning voice commands, record matching, layered routing, chess, agent coordination and presentation coaching.
Duration: 46 minutes 7 seconds.Liam shows how n8n’s Jev node sends information and named answer options to the model, then uses the returned probabilities to route deals and Salesforce cases.
Duration: 5 minutes 13 seconds.Underfitted walks through a Zapier integration that sends an email’s subject and body to Jev, asks about language, category and importance, then tests which workflow path the returned category would follow.
Duration: 8 minutes 59 seconds.KodeKloud follows a support ticket through small decisions that sit beside an LLM: choosing a team and a reply model, asking for human approval before a refund, and checking a drafted response against policy. It also explains why confidence needs testing on your own tickets before you let the program act.
Duration: 21 minutes 1 seconds.Prompt Engineering reports testing a Pi coding agent on three database tasks with five harness configurations. Selecting relevant instructions helped one task; tool gates exposed bypasses and added work.
Duration: 15 minutes 32 seconds.This walkthrough demonstrates how to integrate Jev decision models into an agent harness to handle routing, risk gating, and tool selection without relying on full LLM calls.
Duration: 20 minutes 24 seconds.Compare hosted Jev with local decision-model profiles using Jev Arena. The walkthrough examines task fit and input limits, and shows why short-input speed results can reverse with a long policy handbook.
Duration: 12 minutes 18 seconds.Gautam Khosla explains his ChaosNLI study comparing 750 sentence pairs with high human agreement and 750 with low agreement. He reports that Jev's Choice probabilities remained too high on contested pairs, while still helping rank which pairs were harder.
Duration: 11 minutes 15 seconds.Work through ten levels of TypeScript examples, from yes-or-no checks and support-ticket scores to Pi tool hooks, context compaction and an agent that writes its own Jev questions.
Duration: 35 minutes 17 seconds.Use a GitHub Action to ask Jev which kind of issue arrived and which coding agent should handle it. The walkthrough creates labels, adds decision logs and tests an issue before showing how a separate software factory picks up labelled work.
Duration: 16 minutes 25 seconds.
