Create and Query Your First Agent
This guide walks you through creating a datastore, uploading documents, and building an agent—all through the Contextual AI web interface.Step 1: Create an Agent
Log in to app.contextual.ai with your user credentials. On the left-hand side navigation, click on Agents. From the Agents overview page, click on+ New Agent to create a new agent. Give your agent an:
- Agent Name
- Description
Step 2: Create a Datastore
Under Datastores, click+ Create new datastore. Give your new datastore a Datastore Name, accept the defaults (File Upload, Unstructured) amd click Next.
Go back to your Datastores overview page and click on the name of your new datastore. Click Upload to add documents to it. Contextual AI securely stores your documents and parses them in formats optimized for RAG pipelines and agents.
Once your document has been processed, it will display Processed as its status.
For best results:
- Use renderable PDFs and documents with text that can be copied and pasted.
- Don’t have your own documents ready? Use these sample documents.
Step 3: Prompt Your New Agent
ClickAgents in the left-hand navigation, followed by the name of your new agent. Try asking your agent a question.
Note: You can query your agent only after at least one document in the datastore has been fully processed.
Next Steps
- Agent Composer — Build custom agent workflows (enterprise) or use templates (self-serve)
- Platform Quickstart (API) — Create agents programmatically via the Python SDK
- Datasources & Connectors — Connect your enterprise data sources