$AXS
Fading QuicklySnapshot Window: 2026-09-24 08:10 UTC · ← Back to Crypto Overview
Social Momentum Summary
Total Engagement - Comments: 1, Retweets: 0, Likes: 3, Impressions: 64
Verbatim Community Citations & Social Evidence 1 source posts analyzed
Coding agents are a while loop around a model and a handful of tools. That's it. That's the whole secret. And almost nobody has rethought that loop since it was invented. Someone just compiled a working note built on design notes from Diogo Almeida, the founder behind Jev, and
AI visual note: The image is a labeled diagram from a September 2026 working note titled "JEV ENGINEERING FOR CODING AGENTS," subtitled "The TypeSafe Founder's Blueprint for Building with Jev." It illustrates the architecture of a coding agent, showing a "User" feeding into a central "Runtime" module composed of six core chunks — Tool calls, Reasoning, User items, AGENTS.md, Chunks store, Chunk scoring, Router, and Context Assembly — alongside a Decision section for chunking, caching, and routing, and an LLM block containing frontier, sub-agent, cheap/open, and background models. The caption relates to the post by visualizing the "while loop" structure it describes, depicting the explicit tool calls, reasoning steps, and routing decisions that form the control flow every coding agent runs.