What is AI knowledge? Ground agents in trusted sources
Knowledge gives an agent a trusted source set beyond its model training. AI Agent turns approved documents and websites into retrievable context, then records what the run actually used.
The concept
A plain-language definition before the product implementation.
Knowledge retrieves the right source at the right moment
Retrieval-augmented generation, or RAG, breaks source material into useful passages, represents them for semantic search, and retrieves the most relevant context for a question. Good RAG narrows the evidence before the model answers; it does not simply paste every document into the prompt.
How AI Agent uses it
Manage sources and inspect retrieval
AI Agent supports document and website knowledge sources, source processing, semantic retrieval, and trace inspection. Attach only the approved sources an agent needs, then open a retrieval trace to see which chunks and metadata supported the result.
Ingest approved sources
Add documents and supported websites as managed knowledge sources.
Retrieve selectively
Find relevant passages instead of loading an entire corpus into every request.
Keep the proof trail
Inspect source, chunk, score, and retrieval metadata in traces.
From idea to a working system.
- 01
Add
Create a source from a document, website, or supported business context.
- 02
Process
Chunk, index, and prepare the material for semantic retrieval.
- 03
Retrieve
Attach the source to an agent or chat and inspect the evidence used.
Ground answers in an approved source set
Best for
Product documentation, policies, research, and other managed documents or websites that should remain attributable and inspectable.
Choose another pattern when
Continuity from prior interactions, preferences, or decisions. That evolving context belongs in agent memory.
Included in AI Agent
The product capabilities behind the idea.
- Document and website sources
- Semantic retrieval
- Source and chunk metadata
- Retrieval trace inspection
Frequently asked questions
Keep exploring
Related product guides
Memory
Memory gives an agent continuity without forcing a person to repeat the same context in every prompt. AI Agent lets each agent use recent messages, semantic recall, structured working memory, and observations where they help.
Agents
An agent is the reasoning layer: it understands a goal, decides which approved tools to use, and works toward an outcome. AI Agent gives that reasoning a clear operating contract instead of relying on one giant prompt.
Company Brain
Query a fresh, read-only analytics copy of your Tables across sources, with freshness and provenance included in successful results.
Build the smallest useful version first.
Start with the agent and one real task. Add workflow control, context, and approvals when the work shows you where they matter.