# TypeSafe’s Jev sparks copycat decision models after researcher claims prior work

Digest AI · Generative AI & Models · published 2026-10-12T16:00:00Z

Canonical: https://digestai.news/story/typesafes-jev-sparks-copycat-decision-models-after-researcher-claims-p

## Summary

The release of TypeSafe’s Jev API—designed for direct probability-based decision-making—has triggered a flood of competitors. Jev lets developers feed structured data (like shopping transactions) and ask yes/no or multiple-choice questions, returning probabilities for conditional logic in code. Unlike traditional LLMs, it avoids token-by-token generation, conversation history, or hallucination, instead delivering fast, parallel answers at lower cost.

Nandakishor Mukkunnoth, founder of ConvAI Innovations, accused TypeSafe of copying his earlier research. Mukkunnoth published an *arXiv* paper on **SalesRLAgent** in March 2025, detailing a probability-estimation model and open-source weights. He later refined the idea in a September paper, aligning closer to Jev’s architecture. Frustrated by what he called “vertical use-case neglect,” he released **Laya**, an open-source Jev-like model with multi-language support, on the same day TypeSafe launched Jev. Both models reference **System One** from Kahneman’s *Thinking, Fast and Slow*, though their implementations differ—TypeSafe’s is hosted, while Laya runs on user hardware using Bert-family encoder-only models.

Within weeks of Jev’s debut, major players rushed alternatives: Microsoft’s **Decision**, OpenAI’s **Decisions API**, and Fastino’s **Glide**. Open-source projects like **Strands Decider 2B**, **Kev**, **Von**, **Jeff**, **jevlike**, **SemIf**, **OpenJev**, **NanoJev**, and **Ollaya** emerged, often repurposing lightweight models like Alibaba’s Qwen. Cloudflare’s **Clef** and Perplexity’s **Decider** also joined, offering open weights for self-hosting.

## Key points

- TypeSafe’s Jev API lets developers feed structured data and get probability-based answers for conditional logic, avoiding LLM pitfalls like hallucination or slow generation
- Nandakishor Mukkunnoth claims his 2025 *arXiv* paper on **SalesRLAgent** and September follow-up inspired Jev, releasing his own open-source **Laya** model in response
- Competitors like Microsoft, OpenAI, Fastino, Cloudflare, and Perplexity launched Jev-like tools within weeks, while open-source projects (e.g., **Strands Decider 2B**, **Ollaya**) proliferated

## Why it matters

Jev’s architecture simplifies decision-making for developers by replacing LLM prompts with structured probability outputs, cutting costs and latency. The rush of copycats signals broad industry interest in lightweight, domain-specific AI tools—though Mukkunnoth’s claims highlight tensions over credit and open-source contributions.

## Sources

1. [Jev-like decision models are flooding the AI market, after researcher claims TypeSafe copied their research](https://tomshardware.com/tech-industry/artificial-intelligence/jev-like-decision-models-are-flooding-the-ai-market-after-researcher-claims-typesafe-copied-their-research-microsoft-openai-among-companies-releasing-lightweight-system-one-ai-models) (Tom's Hardware, 2026-10-12)

Part of the developing story: [AI Startup Jev's Meteoric Rise](https://digestai.news/thread/typesafe-jev-hits-100m-arr-7-5b-valuation-three-weeks-after-launch) (2 stories)

## Cite

Digest AI, "TypeSafe’s Jev sparks copycat decision models after researcher claims prior work", 12 October 2026, https://digestai.news/story/typesafes-jev-sparks-copycat-decision-models-after-researcher-claims-p

---

Written by Digest AI's editorial model from the linked sources; the sources are the record. Headlines, digests and key points are written by Digest AI and may be quoted with a link to the story page. Linked articles belong to their publishers. Terms: https://digestai.news/terms#reuse
JSON: https://digestai.news/story/typesafes-jev-sparks-copycat-decision-models-after-researcher-claims-p.json