Skip to content
JevDirectory.org
Core ConceptsLLM agentAgentic loop

Agent loop

A control pattern where the model chooses its next step repeatedly; TypeSafe's guidance is to prefer a code-owned workflow instead.

Open docs.typesafe.aiAll 117 terms
Category
Core Concepts
Also known as
LLM agent, Agentic loop
Related terms
4
Directory entries
2
Docs
docs.typesafe.ai
Added
2026-09-24

Definition

The how-to-build guide describes agents as loops where the model processes instructions and chooses its next action. That works when a person is monitoring the process, but every loop adds another opportunity to go off the rails.

Jev is explicitly not an agent: it does not generate code or choose its own next action. The recommended replacement is a workflow of atomic questions whose answers code composes, with agent loops reserved for cases a workflow cannot express.

Tagsarchitectureagents

Related terms

Definitions that connect to this one.

AI-powered softwareThe architecture TypeSafe recommends: code owns the workflow and the model appears only where programmable common sense is needed.Core ConceptsCoding agentThe fastest-growing corner of the Jev ecosystem: MCP servers, tool-call gates, context pruners, and skill rankers.EcosystemDecompositionBreaking a broad judgment into one question per factor, then combining the answers with weights and rules you control in code.Core ConceptsAtomic questionA question that asks one specific, well-scoped thing — the kind of judgment a knowledgeable person makes in a few seconds.Core Concepts

From the directory

How to Build with TypeSafe
Design AI-powered software by keeping code in control and giving System One narrow, structured decisions to make.
Practices & PatternsDocs#official#patterns#architecture
Official
System One
The idea behind Jev: models that return typed decisions and probabilities instead of generated text, named after Kahneman's fast-thinking System 1, with confidence to route around uncertainty.
Sites & GuidesDocs#official#docs#architecture
Official

From the community

Posts from builders shipping with Jev right now.

Follow @typesafeai

LLM-as-a-judge, sped up

Yuchen Jin
Yuchen Jin
Databricks
@Yuchenj_UW
·

Jev has spoken. It picked which model is AGI. 20–200x faster. 40–400x cheaper. This could make things like LLM-as-a-judge insanely fast and nearly free. (I tried a bunch of prompts and still didn’t burn through $0.10.)

Image
Diogo Almeida
Diogo Almeida
TypeSafe AI
@CompleteSkeptic

After co-inventing ChatGPT, I kept asking myself: why have superhuman chat models not led to AGI? I’ve spent the last 2 years in stealth building a new way to train models (RLCD), and a new type of frontier AI model that we are releasing today: Jev • 20-200x faster • 40-400x

Watch on X
Reply
Read 93 replies

Instant compaction with Jev

A Claude session from 1M to 86K tokens

Alex Volkov
Alex Volkov
CoreWeave
@altryne
·

This is actually insane. This uses @typesafeai Jev model, as a plugin in Claude to review all the un-nesseasary tool calls, and it takes 1s to run! Like, literally, 1 second to take my Claude session from nearly 1M to ... 86K tokens! 😮 Ask your claude to install it and be  Show more

Image
Image
tamara
tamara
@tamarajtran

found the perfect use case for @typesafeai Jev: instant compaction in 2026, why is compaction still a summarization prompt? Jev can make it instant by scoring every tool call and dropping what’s irrelevant

Watch on X
Reply
Read 164 replies

Vercel's fx safety reviewer, 18x faster

Guillermo Rauch
Guillermo Rauch
Vercel
@rauchg
·

We're seeing extraordinary results from @typesafeai. Default mode in 𝚏𝚡 is auto, with a safety reviewer analyzing every command. That reviewer runs on GPT Luna today. Jev is up to 18x faster (p95) *and* more accurate. It's coming to @vercel AI Gateway and likely new default.

Pranit
Pranit
Vercel
@fazxes

We benchmarked fx auto mode (safety) classifier with @typesafeai's Jev. tl;dr: ~5-18x faster and more accurate than 𝚐𝚙𝚝-𝟻.𝟼-𝚕𝚞𝚗𝚊, our current top choice

Image
Reply
Read 137 replies

Jev lands on OpenRouter

700 leads scored for $0.09