Agents UI guide
Create and manage agents through the SeekrFlow web interface.
Agents SDK guide
Create and manage agents programmatically with the Python SDK.
Agent primitives
Agents are built from two core primitives:Models
A model serves as the agent’s cognitive engine, providing the reasoning capabilities needed to understand tasks, determine the best course of action, and generate responses. SeekrFlow supports both base models and fine-tuned models.
Tools
Tools are modular components that extend an agent’s capabilities beyond built-in reasoning. With tools, agents can take actions, access external systems, or query knowledge stores.
Agent configuration
When creating an agent, you configure several key properties:Reasoning effort
Reasoning effort controls how much reasoning the agent uses when working through a request. The default ismedium.
Agent status
Each agent has a status that indicates its deployment state:An agent is demoted to Inactive after two weeks of inactivity. Creating, deploying, or running an agent resets the two-week period, but updating one does not. The agent’s definition is retained. Promote the agent to deploy it again and return it to Active.