The Agent chooses how · Context controls where and what · tools run in parallel
Modern AI chat products are not a single LLM. An agent chooses tools, a context layer controls scope and policy, and retrieval or action tools run in parallel.
This OKPy special maps Agent vs Context, web search vs browser automation, nine RAG styles, and how Cursor, ChatGPT, Claude, and Gemini fit the same architecture.
❓
Question
The model does not know
📜
Long Context
Skip search · expensive
🧭
Agent
Decide how to answer
🧠
Memory
Dialogue · experience
⚙️
Context Layer
Gate · where · what
Meaning
What is being asked?
Clarify the request and narrow ambiguity
Permission
Where may it go?
Allow only visible data and systems
Policy
What is allowed?
Filter harm, secrets and personal data
Only passed scope ↓ to tools
PARALLEL TOOLS · choices at the same tier
RETRIEVAL
ACTION · SENSE · SOLVE
Agent & Context in detail
🧭 Where tool-selection criteria live
The rules are not only “inside the model.” Developers provide descriptions, rules and routing.
In short: The Agent may choose the database, but Context can block it or narrow its scope.
Product comparison, in plain language
How Cursor, ChatGPT, Claude and Gemini cover the same roles
Easy to confuse: Realtime web is a search API, not Chrome. Clicking Chrome is GUI Agent / Computer Use.
Real paths · how a question moves
A rough path from request to answer
9 RAG methodologies
Select a card to see details
9 other methodologies
Approaches that complement RAG or do not retrieve document chunks
Rule of thumb: documents → RAG · relationships → GraphRAG · numbers → SQL · current facts → web · complex work → Agentic tools.