The Token-Oriented Object Notation format is here. As much as JSON reduced the size of XML, TOON is doing the same to JSON. Why? Tokens cost money! Developed by Johann Schopplich, TOON reduces the size (30-50%), and therefore the number of tokens burned when ingesting data. From his github page:
Why TOON?
AI is becoming cheaper and more accessible, but larger context windows allow for larger data inputs as well. LLM tokens still cost money ā and standard JSON is verbose and token-expensive:
{
"users": [
{ "id": 1, "name": "Alice", "role": "admin" },
{ "id": 2, "name": "Bob", "role": "user" }
]
}
YAML conveys the same infromation with fewer tokens:
users:
- id: 1
name: Alice
role: admin
- id: 2
name: Bob
role: user
TOON conveys the same information with even fewer tokens:
users[2]{id,name,role}:
1,Alice,admin
2,Bob,user
There are .NET libraries that convert C# objects to TOON. Maybe weāll see them included for Epicor Functions someday. 
