Guides / illustrated walkthrough
Use Jev Decision Nodes in Heym for Model Routing
Configure a Heym workflow with Jev for typed language checks and runtime model routing, then inspect the decision path in execution traces.
Quick takeaway
The walkthrough configures a Jev decision model in Heym, tests a language question with English and Spanish input, and reviews an orchestrator trace where the selected model changes by task. Treat the displayed probability and trace timings as one demo run, not a general accuracy or performance benchmark. Verify fallback behavior, provider access, and thresholds in your own Heym version before relying on them in production.
Video source
Heym
Step-by-step walkthrough
- 1
Separate normal model criteria from the routing fallback
The Heym credential editor lists distinct model options with a short “Use this when” description. One option is marked for use when routing fails. Keep that fallback role explicit, choose task criteria that are easy to tell apart, and test how your deployed workflow behaves when the preferred route is unavailable; the video does not establish a universal failover guarantee.
Make the fallback role visible instead of hiding it in a broad model description.Watch at 1:08 - 2
Run a Spanish sample through the language-check workflow
The video enters “¡Hola!” as a contrasting input and runs the Heym workflow. This frame captures the Jev Decision node while it is still executing; use the next frame to inspect the completed branch before connecting it to a consequential action.
The execution indicator is still active in this frame; the result appears moments later.Watch at 1:32 - 3
Check the completed result and its conditional output
The execution highlight shows “Not English” with probability 0.03, and the workflow connects the false side of `isEnglishCheck` to `notEnglishOutput`. This is one example response, not an accuracy claim. Validate the question criteria and downstream actions with labeled cases, including short or ambiguous text.
The completed run follows the non-English branch in this example.Watch at 1:34 - 4
Compare the English result before choosing a workflow branch
A later run uses “hi” and shows an English result with probability 0.98 in the execution highlights. The Noul question feeds an `isEnglishCheck` condition, which connects to separate English and non-English outputs. This single result is not a measured accuracy rate; evaluate representative labeled examples and decide what should happen when evidence is weak.
Compare both sides of the condition and test ambiguous inputs separately.Watch at 1:45 - 5
Audit runtime model choices in the execution trace
The orchestrator trace records separate routing turns for a fast task and a creative task, followed by their downstream calls. Inspect which decision selected each model and where it occurred in the workflow. The displayed durations and token count belong to this sample run; measure your own tasks before drawing performance or cost conclusions.
Trace rows help explain which model was selected at each runtime decision point.Watch at 2:08
Frequently asked questions
Can I use Jev to route models inside a Heym workflow?
The video demonstrates a Heym decision model selecting different configured models for different task types. Your workflow still needs clear routing criteria, credentials, and a tested fallback path.
Does the configured fallback guarantee that every failed route recovers?
No universal guarantee is established by the walkthrough. It shows a model option marked for routing failures. Test provider outages, invalid credentials, timeouts, and the resulting workflow state in the Heym version you deploy.
Does the 0.98 language result prove the workflow is 98% accurate?
No. It is the probability shown for one example input in the video, not a measured accuracy rate. Evaluate representative labeled examples and define what happens when evidence is weak or the input is ambiguous.
How is this different from a general Jev model-router guide?
This page follows the Heym interface, its Decision node, and its execution trace. The general model-router guide covers platform-independent routing design and trade-offs.
Related guides
Jev Model Router: Local and Cloud Model Routing
Compare platform-independent routing criteria and local-versus-cloud model choices.
ReadJev Model: Choice, Score, and Noul
Choose the typed output that fits a route, category, score, or yes/no gate.
ReadJev API Examples: curl, Python, and JavaScript
Review typed question payloads and responses outside the Heym interface.
ReadJev Log Triage with Expanso Edge
See selective Jev decisions used to route operational log events.
ReadJev Lead Enrichment with Treg
Compare another workflow that uses typed Jev decisions for lead categories.
ReadJevGate for n8n: the community-node route
Heym platform on this page, n8n canvas on that one — two no-code homes for the same three primitives.
ReadMore video walkthroughs
- Jev Classification Quickstart: OpenRouter API, Primitives & Real Probabilities
- Jev Architecture Explained: Why 70ms Decision Models Beat LLMs for Workflow Automation
- Ultra-Fast Browser Agents with Jev: 178ms DOM Loops & Dual Model Orchestration
- Open Jev Models Are Here: Semif, Nimble, Decider, DiffusionGemma & Laya Hands-On
- Jev vs LLM: Will Jev Replace LLMs? Krish Naik's Whiteboard Explainer
- Jev Trader Tutorial: Build a Subsecond AI Trading Bot on Monad
- Jev Model Router: Build a Privacy-Gated LLM Router with Jev & OpenJev
- Jev Tutorial for Beginners: State, Questions & the TypeScript SDK
- Run Jev Locally: Kev, SemIf & Von on Your Own GPU (OpenJev Guide)
- Jev RAG Reranker: Policy-Steered Reranking for Retrieval-Augmented Generation
- When to Use Jev: An Engineer's Audit of Claims, Gates, and Failure Modes
- LangChain + Jev Integration Tutorial: Routing, Guardrails & Evals
- Jev MCP Server: Connect Jev Decisions to Claude Code & Cursor
- Jev vs Luna: Independent Benchmarks Put "Better, Faster, Cheaper" to the Test
- Jev Agent Harness: Where the Decision Gate Sits in Your LLM Loop
- Jev Playground Walkthrough: The Hotdog Lesson, Criteria, and a Four-Console Token Test
- Jev Text Classification API: Zero-Shot CLI & REST with classifier.dev
- Jev API Examples: First Request, curl & All Three Question Types
- Jev Log Triage with Expanso Edge
- Jev Lead Enrichment with Treg: ICP and Signup Scoring
- Laya Tutorial: Open-Source AI Routing With Calibrated Probabilities (Laya vs Jev Setup)
- Train Your Own Jev: Fine-Tune a Jev-Style Decision Model for $5–$17 (What You Can and Cannot Train)
- Jev Tips: 8 Best Practices for Better Decisions (State, Questions, Criteria & Thresholds)
- Jev Context Compaction: Prune AI Agent Memory Without Generative Summaries
- Jev as an LLM Judge: Confidence-Gated Cascades at 0.36% of the Cost
- TypeSafe Computer Use: Local Desktop Automation with Jev, Step by Step
- Jev Resume Screening: Build an AI Resume Evaluator with the Jev JavaScript SDK
- Jev + Claude Code Guide: Voice-Controlled Browser Automation with Typed Decisions
- Jev + Codex: Install the TypeSafe Skill and Triage a Real Gmail Inbox
- Jev vs Ollama: Can Local AI Replace Hosted Jev Without Sending Your Data Away?
- Build Your Own Jev: Train a Free Open-Source Zero-Shot Classifier (That Plays Doom)
- CUA-S1-Forms: a 706K-Parameter Jev-Like Model That Fills GUI Forms on Your CPU
- NOC/SOC Alert Triage with Jev: Rules First, One Typed Question, a Policy Gate
- Ollama Decision Models: Run tev1 and Nimble Locally (Tested on an 8 GB Card)
- Jev Guardrails in Production: A Five-Step Playbook for Decision Automation
- A Session Drift Guard for Pi Agent: Let the Jev Model Propose, Let Code Decide
- 50 Tev1 Use Cases: What a Local Decision Model Can Actually Do (Tested on an 8 GB Laptop)
- Jev, Hands-On: Where the Official Claims Meet Independent Remeasurement
- Jev Ticket Classification in a Real App: the After-Insert Hook and the Calculated Field
- OpenJev RLCD: Run the Open-Source Calibrated Decision Model Locally (Full Guide)
- Clef-Flash vs Jev: I Tested Cloudflare's Decision Model Locally in Ollama (Q4_K_M)
- Clef-Flash Tutorial: Install and Run Cloudflare's 9B Multimodal Decision Model Locally on Ubuntu
- CLM-8B: the Contrastive Decision Model That Scores 1,024 Options in 44 ms (13x Faster Than Jev)
- Nox 4B Tutorial: Run the Decision 2.0 Model Locally and Put It Through Four Real Decisions (One Ends in a Fail)
- Julia-1 Tutorial: Install the Open-Source Jev Replacement in Pure Python (and Watch It Beat If-Statements 9 to 2)
- OpenJev 0.8B on CPU: I Built a Ticket-Routing Inbox and Calibrated the Thresholds
- Jev n8n Integration: the JevGate Community Node, Step by Step (Plus a Plain-HTTP Fallback)
- NanoJev Tutorial: Install the 0.6B Open-Source Jev Replica and Watch It Route Decisions at 47 ms
- PPLX Decider Tutorial: Perplexity's Open 27B Decision Model, Its Decisions API, and a 12-Ticket Triage Run
- AutoTrust JEV-27B Tested Locally: Four Arms, 72 Cases, and One 0.969 Score That Was Wrong
- Clef 27B Locally: Watch Cloudflare’s Multimodal Decision Model Read an Image, a Video and an Uzbek Newspaper in One Pass
- Ollaya Guide: Install the "Ollama for Decision Models" Runner, Read Every Vendor-Reported Number, and Run the CPU Test It Leaves Open
- Strands Decider 2B Tutorial: Install the AWS Strands Decision Model on an 8GB Laptop — and Keep Its Failures In
- Liquid AI Open d1 Locally: d1-3B and d1-omni-600M on a MacBook Air M5 — Guardrails, Screen Checks, Voice Routing and Document Triage, Every Number Frame-Checked
- Image Decision Models for RPA: Watch Two Open Models Review an Unsigned W-8BEN With No OCR
- GLiNER2.5-Decide (340M) vs Jev (4B): Which Decision Model Actually Wins? A Frame-by-Frame Selection Guide
- Decision Models on Jetson: Jev vs Strands Decider 2B vs Laya vs d1-3B — Skill Master Scores, Thor Latency and JevBench, Every Number Frame-Checked
- Microsoft Decision-1 Tested: 146 Independent Tests, a 93% Mean, 124/125 When Confident — Every Number Frame-Checked
- Wire Jev into an Azure AI Foundry Agent as the Evaluation Layer — OpenAPI Tool, TypeSafe Connection, Triage Instructions and an Honest First-Run Failure