Agents
Bundata prepares your document base so agents can deliver accurate, grounded answers with source lineage and extraction confidence. Agentic AI needs more than raw data — it needs enriched, structured information. Bundata powers agent workflows through RAG enablement, structured data extraction, and file metadata enrichment, so agents reason over schema-aware outputs and vector-ready smart bites instead of messy raw text.
Overview
Use the Vector Catalog for retrieval, structured extraction for entities and tables, and metadata for filtering and audit. Agents built on Bundata are grounded by structured outputs: they reason over schema-aware fields and smart bites. Use cases include AI copilots (customer support, legal review, R&D), agents that reason across multiple documents, and internal onboarding assistants. Platform: Platform → Agents. Product: Product → Agents.
Key tasks
| Task | Guide |
|---|---|
| Understand what agents need from Bundata | Overview |
| Build doc-based assistants | Knowledge assistants |
| Retrieve context and pass to the LLM with lineage | Grounding from catalog |
Tutorials and concepts
- Build your first agent — Connect an agent to the catalog and surface source lineage.
- Vector Search overview — Semantic retrieval for grounding.
- Vector Catalog overview — Where smart bites and embeddings live.
Related product areas
- Extraction — Produces the smart bites and schema-aware output agents use.
- Vector Catalog — Index and store embeddings and smart bites.
- Vector Search — Semantic retrieval for agent context.
- Workflows — Keep catalog and sources up to date for agents.