Jev 101 logo
Jev 101

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

3:34P8oEA-K3jPw
Visit channelWatch original

Step-by-step walkthrough

  1. 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.

    Heym model routing settings show separate fast and creative model criteria, with the fast option selected for routing failures.
    Make the fallback role visible instead of hiding it in a broad model description.Watch at 1:08
  2. 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.

    Heym language-check workflow running a Jev decision on the Spanish input “¡Hola!” before returning a result.
    The execution indicator is still active in this frame; the result appears moments later.Watch at 1:32
  3. 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.

    Heym execution highlights show the ¡Hola! input routed to notEnglishOutput with a Not English result and probability 0.03.
    The completed run follows the non-English branch in this example.Watch at 1:34
  4. 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.

    Heym Decision node returns an English language result with probability 0.98 and connects the Noul check to distinct output branches.
    Compare both sides of the condition and test ambiguous inputs separately.Watch at 1:45
  5. 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.

    Heym execution trace lists two model-router decisions, showing different models selected for fast and creative workflow turns.
    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.

Read

Jev Model: Choice, Score, and Noul

Choose the typed output that fits a route, category, score, or yes/no gate.

Read

Jev API Examples: curl, Python, and JavaScript

Review typed question payloads and responses outside the Heym interface.

Read

Jev Log Triage with Expanso Edge

See selective Jev decisions used to route operational log events.

Read

Jev Lead Enrichment with Treg

Compare another workflow that uses typed Jev decisions for lead categories.

Read

More video walkthroughs