# Typesafe > Markdown twin of https://roboterminal.app/companies/typesafe · https://roboterminal.app/companies/typesafe.md ## On shared sources - [OpenAI](https://roboterminal.app/companies/openai) (6) - [Anthropic](https://roboterminal.app/companies/anthropic) (4) - [DCVC](https://roboterminal.app/companies/dcvc) (4) - [Vercel](https://roboterminal.app/companies/vercel) (3) - [Braintrust](https://roboterminal.app/companies/braintrust) (2) - [Cloudflare](https://roboterminal.app/companies/cloudflare) (2) - [LangChain](https://roboterminal.app/companies/langchain) (2) - [Langfuse](https://roboterminal.app/companies/langfuse) (2) - [Alibaba](https://roboterminal.app/companies/alibaba) (1) - [Browser Use](https://roboterminal.app/companies/browser-use) (1) - [Cerebras](https://roboterminal.app/companies/cerebras) (1) - [Convai Innovations](https://roboterminal.app/companies/convai-innovations) (1) - [Groq](https://roboterminal.app/companies/groq) (1) - [Martian](https://roboterminal.app/companies/martian) (1) - [System One AI](https://roboterminal.app/companies/system-one-ai) (1) - [xAI](https://roboterminal.app/companies/xai) (1) ## Pulse - [@stretchcloud on X](https://x.com/stretchcloud/status/2102074878857777225) The bottleneck in most agent stacks right now isn't intelligence. It's the cost of the thousand small decisions an agent makes before it writes the sentence a user reads: classify this ticket, check t… - [@stretchcloud on X](https://x.com/stretchcloud/status/2101989826442477694) The decision layer inside AI agents just became its own product category, separate from the model doing the talking. TypeSafe AI shipped Jev, a model that never generates text. Hand it a piece of stat… - [@stretchcloud on X](https://x.com/stretchcloud/status/2101949552664457715) The shift I keep coming back to this week: not every AI call needs to write a sentence. Diogo Almeida's Jev proved that in nine days. Jev is what TypeSafe calls a System One model. It skips token by t… - [@stretchcloud on X](https://x.com/stretchcloud/status/2101919353595957682) The bottleneck in agent costs just moved, and I don't think most people are measuring the part that actually got expensive. For a year, agent economics meant output tokens: what a model charges to gen… - [@stretchcloud on X](https://x.com/stretchcloud/status/2101743192466948513) Jev doesn't generate text. It decides. TypeSafe AI came out of stealth Sep 15. System One is a classifier. Returns choice, score, or null. Not an LLM. Something fundamentally different. - [@stretchcloud on X](https://x.com/stretchcloud/status/2101370744479588635) System One AI models just entered production. Here's what that means for builders: 1/5 - A new model category Jev from TypeSafe does one thing: it classifies and decides. It takes structured input and… - [@stretchcloud on X](https://x.com/stretchcloud/status/2101258750548226083) What changes when a model returns typed decisions instead of text? Everything about cost, speed, and reliability. TypeSafe just shipped Jev -- a System One Model for decision-making. - [@stretchcloud on X](https://x.com/stretchcloud/status/2101139212741574866) The category is crystallising: System One models are purpose-built for high-volume, low-latency decisions—routing, scoring, classification. Not text generation. Jev by TypeSafe AI: typed probabilistic… - [@stretchcloud on X](https://x.com/stretchcloud/status/2101058682419294389) We're not just getting faster frontier models. A completely different model category shipped this week. TypeSafe AI released Jev on Sep 15. Built by Diogo Almeida, one of the people behind ChatGPT's r… - [@stretchcloud on X](https://x.com/stretchcloud/status/2100963059992756485) The Berkeley HarnessTax study deserves more attention than it got. 21 model-harness pairs tested across SWE-bench Lite and Terminal-Bench 2.0. The result: the same model running in different harnesses… - [@stretchcloud on X](https://x.com/stretchcloud/status/2100833951384584366) The bottleneck moved from generating text to making decisions. Jev from TypeSafe AI launched this week out of stealth. It is not a chat model. It is a System One model: it accepts any unstructured con… - [@stretchcloud on X](https://x.com/stretchcloud/status/2100443378186166632) The routing problem in a multi-harness agentic stack has been an LLM call problem. You route to Claude Code, Codex, Opencode, or another harness by putting logic in a system prompt and burning tokens … - [@stretchcloud on X](https://x.com/stretchcloud/status/2100078473419104388) My read: When software needs to route between agents, classify intent, or make a binary API decision, it doesn't need a paragraph. It needs a number. That's what TypeSafe AI built Jev for. System One … - [@frontrunvc on X](https://x.com/frontrunvc/status/2099966030260978077) FUNDRAISE 💰: @typesafeai just came out of stealth with a $40M seed led by @DCVC. On @frontrunvc, the story started 71 days ago. jul 6: @typesafeai flagged. in stealth. jul 21: @frontrunvc posted in E… --- Source: Roboterminal · https://roboterminal.app/companies/typesafe.md