AQL 0.13: One Read, Thirteen Verbs
AQL 0.13 replaces seven rounds of additions with one smaller language. One read verb, branches as namespaces, aliases instead of entity merges, and about 60 keywords.
Read the post
AQL 0.13 replaces seven rounds of additions with one smaller language. One read verb, branches as namespaces, aliases instead of entity merges, and about 60 keywords.
Read the post
AQL 0.13 replaces seven rounds of additions with one smaller language. One read verb, branches as namespaces, aliases instead of entity merges, and about 60 keywords.
Template, clone, branch, merge and inherit, for an agent's flows and its memory. A design post on how A3T and ADB will let agents share rules, test against real memory and change safely.
Agent identity, delegation, and why the enterprise still needs a gateway. What Entra Agent ID, Cross App Access and token vaults solve in 2026, the five gaps they leave, and how A3T closes them.
Every verb of AQL 0.13, the Agent Query Language, as one expanding tree. Open RECALL, STORE, LINK, BRANCH, MERGE, PIPELINE and the rest, clause by clause, each with an explanation and an example.
From how brains remember to AQL, a declarative language for storing, recalling, linking and learning across five kinds of agent memory.
The whole CNCF Serverless Workflow schema as one expanding tree. Open document, use, do, call, try and the rest, layer by layer, each with an explanation and an example.
Maps, lists, indentation, quotes and multi-line text, in eight short lessons you can edit, with the JSON a program reads updating as you type.
How to make your LLM know about enterprise data without breaking the cache (or the bank).
LLMs encode more information per token than any structure humans have ever designed. They also waste most of it, because we don't yet understand what we put inside them.
LLMs have no memory of your project, so every session starts from zero. Prose rots; formal artifacts checked in CI keep a codebase coherent across sessions.
Nothing here yet.