Article
OfficialJev Guides & Articles
Manifesto: Composable AI
TypeSafe's case for machine-native composable AI: intelligence as a dependable primitive that software branches on, rather than an assistant that keeps humans in the loop.
- Format
- Article
- Reading time
- 2 min
- Published by
- TypeSafe AI
- Last verified
- Sep 2026
Works forJev for Classification
Used inJev for Software & DevTools
Highlights
- Argues the bottleneck is not raw intelligence but that today's intelligence is hard to build on.
- Compares current assistants to horseless carriages: new technology forced into the shape of the thing it replaces.
- Sets three steps: ship the shape, make it reliable enough to automate, then expose composable abstractions.
- Appendix targets global TFP growth reaching 3% within five years and holding there for ten as the economic goal.
- Frames the aim as neuro-symbolic AI, neural networks for perception paired with symbolic logic, or smart if-statements.
Watch out
A vendor position paper, not a technical evaluation; definitions for several claims live in its own appendix footnotes.
Questions about this entry
Short answers drawn from the linked project or page.
Ship the shape, make it reliable enough to automate, then expose composable abstractions. The appendix's economic target is global TFP growth reaching 3% within five years and holding there for ten.
The manifesto frames the aim as neural networks for perception paired with symbolic logic — smart if-statements — rather than an assistant in the loop. It is a position paper rather than a technical evaluation.
To pave the shortest path to an AI-based economic revolution by making intelligence composable, which it says can catalyze a Cambrian explosion of intelligent software.
It argues today's models have already crossed the threshold of intelligence needed for massive economic value, so the bottleneck is not raw intelligence but that today's intelligence is hard to build on.
It compares current assistants to early cars built as horseless carriages, new technology forced into the shape of the thing it replaces before finding its own native form.
It wants AI to be a primitive a programmer can invoke for semantic judgement and decisions, while code keeps doing exact computation and branching on bits.
It says safety is a precondition for layering: a component only runs unattended if it is reliable, and people build on it only if they can inspect, test and constrain it piece by piece.
Reactions & coverage
Posts, threads, and videos about this entry from around the web.
X: How the agent stack moved in Jev's first three days
YouTube: Diogo Almeida tells swyx what System One is, why RLHF failed his automation goal, and why AI should eventually disappear.
X: The 10-step roadmap, summarised
X: Giving your agents a decision brain
More Jev resources like this
Mariano Barcia splits an invoice pipeline by semantics: the generative model extracts supplier, number, and amount, while Jev's two Choice questions handle supplier evidence and property selection, with policy left in Java.
Jev Guides & ArticlesArticle#community#article#java
Community
TypeSafe's Series A announcement: $870M at a $7.5B valuation led by Andreessen Horowitz with Sequoia and DCVC, and what the post says the money changes for developers, businesses, and recruits.
Jev Guides & ArticlesArticle#official#article#funding
Official
A TypeSafe blog essay arguing that in ML the order that matters is doing the right task, then data, then compute, then algorithms, using the InstructGPT result as its example.
Jev Guides & ArticlesArticle#official#article#models
Official
The Jev Day release post: Jev 1.14.0 under jev-preview plus three danger-zone features — composable images on both models, the box question type on 1.14 only, and opt-in 262k context.
Jev Guides & ArticlesArticle#official#release#vision
Official
MCP.so's explainer on Jev: how Choice, Score, and Noul differ from text generation, where a decision layer fits in retrieval, verification, routing, and ranking, and the four tools in the community Jev MCP server.
Jev Guides & ArticlesArticle#community#mcp#article
Community
DeepInfra's survey of the decision-model category: pointer-head architecture, RLCD calibration, latency and cost figures for Jev and its rivals, and a landscape table spanning TypeSafe, AWS, Convai, Kev, OpenAI, and Ollaya.
Jev Guides & ArticlesArticle#community#analysis#architecture
Community
From the Jev guides
Original write-ups on what this entry is for.
From the Jev AI model community
Posts from builders shipping with Jev right now.