Collection
Give AI the right context, memory and reusable skills
Use modern context engineering, durable memory and evaluated skills to make repeated AI work more reliable without stuffing every fact and instruction into every conversation.
8 elements · Explore in any order.
1 heuristic · 3 principles · 4 protocols
8 elements
Treat context as a budget, not a transcript
A bigger context window is not permission to turn the whole project into one prompt.
Read the idea PrincipleSeparate session state from long-term memory
What the agent needs for the next hour is not the same thing it should remember next month.
Read the idea ProtocolGive agent memory a write-manage-read policy
Memory is a loop, not a folder.
Read the idea ProtocolEvaluate what memory retrieves, not just what it stores
A perfect archive can still produce a bad working memory.
Read the idea ProtocolKeep raw evidence behind AI memory summaries
A summary should be a door to the evidence, not the place where the evidence disappears.
Read the idea PrincipleUse progressive disclosure for agent instructions
Do not make every future task pay the context cost of every past instruction.
Read the idea HeuristicTurn a recurring AI workflow into a skill only when the trigger is clear
A reusable skill should remove repeated thinking, not create a new library you now have to search.
Read the idea ProtocolAblate a skill before you trust it
If removing the skill changes nothing, the skill may be documentation for humans rather than leverage for the model.
Read the idea