What is context in an AI agent?
Context is everything you feed a model so it can actually do a task: documents, live web data, structured records, the tools it can call, and the systems where it stores and retrieves. As the models commoditize, the quality of that context is the part that compounds.
Context ManagementRAG & Retrieval
1. Documents
The unstructured pile. PDFs, slide decks, contracts, reports. Most enterprise knowledge is locked in these, and most of it is read badly by older tools. Getting a document into a form an agent can actually use, accurately, is its own hard problem and the bet Jerry Liu pivoted his whole company toward.
2. The web
Live information the model was not trained on. The ability to search and crawl so the agent is working from what is true today, not what was true at training time.
3. Structured data
The clean stuff already sitting in SQL databases and warehouses. Numbers, records, transactions. The agent needs a path to query it in natural language instead of waiting on a human to write the report.
4. Tools the agent can call
The software it can reach through connectors like MCP. Confluence, Salesforce, your internal systems. This is where context stops being a lookup and becomes an action: the agent does not just read, it operates the tools.
5. Systems of record
Where the agent stores and updates state. A CRM entry, a Notion page, an internal wiki. Jerry’s point is that these stick around because agents need somewhere durable to act on and retrieve data, not just read it once.
Why it matters
Pick any agent that fails in production and the cause is usually not the model. It is one of these five sources being missing, stale, or badly represented. Jerry’s framing: stop asking which model is best and start asking what context you are giving it. The model is converging. The context is yours.
From the conversation
This explainer is drawn from these episodes — each carries its full transcript.
