jevbooks

← All projects

model-one-connectors

markus-tobler/model-one-connectors

Power Platform connectors for Jev and Microsoft-Decision-1 typed decisions.

Classification & Routing0.63Runner-up: Infra / SDKs / IntegrationsQuestionnaireFunnel
Automated README summary

Automatically summarized from the README on 24 Oct 2026; not a run by jevbooks. Run instructions and author-reported outcomes still need verification.

What it is

Open-source Power Platform custom connectors that bring TypeSafe AI's Jev and Microsoft-Decision-1 to Power Automate and Copilot Studio makers, so they can evaluate messages, route requests, and score cases without writing API integration code.

How it uses Jev

The 'Evaluate with Jev' action takes a state (text or structured JSON) plus questions defined in the designer. Jev returns typed answers: yes/no probabilities, a choice from named options, or a score against a rubric. These appear as named dynamic content fields used in conditions, switches, and approvals.

Primitives:choicescorenoul

Technique worth stealing

Expose typed model answers as named dynamic content so low-code flows can branch on probabilities and confidence thresholds without parsing JSON.

Try it

Download the managed JevCustomConnector solution from Releases, import it, create a TypeSafe Jev connection with an API key, and add 'Evaluate with Jev' to a flow.

View on GitHub

Start using Jev: API key and your first request →

Model judgments from README excerpts

Project signals use repository metadata, an existing summary and the first 700 README characters, not the full project. “Not found” means not detected in that material; it does not establish absence. These are the original judgments with recorded models and dates, not source audits or run results.

Models & evaluation dates

Inclusion gate
jev-1.14.0
Project signals
jev-1.14.0
Category
jev-1.14.0
Pattern tags
jev-1.14.0

Evidence

These signals use repository metadata, an existing summary and at most 700 cleaned README characters. ≥ 0.60 means reported in that excerpt; ≤ 0.40 means not found there. The middle band is inconclusive. None is a source-code audit or a test result. The runnable-tool question excludes research experiments; the recommendation question asks for a learning shortlist, not a quality verdict.

  • Jev is core to the projectnot found in the excerpt0.17
  • Shows a System One patternnot found in the excerpt0.07
  • Describes handling uncertaintynot found in the excerpt0.03
  • Reports measured numbersnot found in the excerpt0.02
  • Is a runnable toolFound in material0.94
  • Top-10 learning shortlist signalnot found in the excerpt0.16
  • Is a replica of the modelnot found in the excerpt0.03
  • Solves a common problem (0–2)score on a 0–2 scale1.10 / 2
  • About JevFound in material0.99
Signals
Jev is core to the project0.17Shows a System One pattern0.07Describes handling uncertainty0.03Reports measured numbers0.02Is a runnable tool0.94Top-10 learning shortlist signal0.16Is a replica of the model0.0300.51Solves a common problem (0–2)1.10 / 2012

no-judgment band (0.40–0.60)

Design patterns
Funnel0.95Questionnaire0.90Ghostwriter0.50Traffic light0.4000.51

no-judgment band (0.40–0.60)

The Jev model and date for each judgment stage are listed above. Card written by DeepSeek V4.1 Flash from the README on 24 Oct 2026.