Jev 1.14.0
The latest Jev preview model, adding experimental image input, Box localization, and an experimental 262K context mode.
TypeSafe APIStructured OutputsExperimental Images
Reviewed Oct 19, 2026
JEV applications, models, and workflows
Explore JEV models, applications, and workflows.
Discover curated JEV resources alongside reviewed AI models, reusable messages, and workflow patterns with clear primary sources.
Type Safe is an independent directory and is not affiliated with TypeSafe AI or other listed providers.
Browse by decision task
Start with the decision you need to make
Implementation resources
Compare the evidence, then build the workflow
JEV spotlight
JEV models and application workflows
Browse sourced JEV model information and editorial application patterns without invoking the model.
ModelTypeSafe AI
WorkflowType Safe Workflow
Jev Image and Box Workflow
A display-only workflow for checking whether a visual target exists before Jev 1.14 returns one Box result for review.
Jev 1.14Jev 1.13Experimental Images
Reviewed Oct 19, 2026
ModelTypeSafe AI
Jev 1.13.0
A System One model for fast, type-safe structured decisions in software workflows.
TypeSafe APIStructured OutputsExperimental Images
Reviewed Oct 19, 2026
WorkflowType Safe Workflow
Jev-as-a-Judge
A confidence-gated evaluation pattern that accepts clear Jev judgments and escalates uncertain cases to a comparator or human reviewer.
JevComparator modelHuman review
Reviewed Sep 28, 2026
WorkflowType Safe Workflow
Jev with LangGraph
An editorial workflow pattern for routing typed Jev decisions through LangGraph checkpoints, retries, and human review.
JevLangGraphPython
Reviewed Sep 28, 2026
Ecosystem research
AI ecosystems worth tracking this week
Nine research directions grounded in first-party English sources. Opportunity scores are Type Safe editorial judgments.
RisingEvidence strength: High
Decision Models and APIs
Typed decisions for classification, scoring and routing, with explicit uncertainty and review boundaries.
9.7 / 10
Type Safe editorial opportunity score
Representatives: OpenAI Decisions API · Jev
Last verified:
RisingEvidence strength: High
Intelligent UI and AI Artifacts
Interactive answers, dashboards and motion artifacts turn prompts into interfaces people can inspect and reuse.
9.2 / 10
Type Safe editorial opportunity score
Representatives: GPT-6 Intelligent UI · Claude Dashboards
Last verified:
RisingEvidence strength: High
Local Multimodal Search
Shared embeddings make text, code, image, video and audio collections searchable across modalities on local infrastructure.
8.9 / 10
Type Safe editorial opportunity score
Representatives: EmbeddingGemma 2
Last verified:
Editor picks
Featured contracts
Recently reviewed
Fresh from the directory
ModelTypeSafe AI
Jev 1.14.0
The latest Jev preview model, adding experimental image input, Box localization, and an experimental 262K context mode.
TypeSafe APIStructured OutputsExperimental Images
Reviewed Oct 19, 2026
WorkflowType Safe Workflow
Jev Image and Box Workflow
A display-only workflow for checking whether a visual target exists before Jev 1.14 returns one Box result for review.
Jev 1.14Jev 1.13Experimental Images
Reviewed Oct 19, 2026
ModelTypeSafe AI
Jev 1.13.0
A System One model for fast, type-safe structured decisions in software workflows.
TypeSafe APIStructured OutputsExperimental Images
Reviewed Oct 19, 2026
Browse by job
Start with the work in front of you
Agent Lab
Adapt a contract with the Type Safe agent
Bring a resource into the lab, describe your context, and receive a reviewable workflow draft.
Directory updates