Agent Core
On this page
Purpose
Agent Core combines one input Message, instructions, automatic session history, a selected model, and optional tools. The model decides whether to call the connected tools before it responds.
When to use it
- Build an assistant that can calculate, retrieve data, or call approved tools.
- Run a bounded multi-step task where the model chooses the next tool call.
- Use Language Model instead for one response with no tool selection.
Required setup
Arkus is the default provider and needs no provider setup. Anthropic, Google Generative AI, and OpenAI require their matching API key.
How to use it
- Connect Chat Input to Input.
- Write instructions that state the task, limits, and expected output.
- Select a model provider and model.
- Connect only the tool-mode components the agent may use to Tools.
- Connect Response to Chat Output.
Configuration
| Setting | What it controls | Recommended starting point |
|---|---|---|
| Agent Instructions | The instructions given to the agent. | Replace the default with the task, limits, and allowed tools. |
| Model Provider | Selects the model and its provider-specific fields. | Start with Arkus. |
| Number of Previous Turns | The number of prior turns loaded from this agent's own execution history for the active session. Each turn holds the input the agent received and the response it produced. | Start at 100. |
| Current Date | Adds one Current Date tool for each run. | Leave on when date or time affects the answer. |
| Handle Parse Errors | Lets the agent recover from malformed tool output. | Leave on. |
| Verbose | Enables detailed execution logs. | Leave on while building. |
| Max Iterations | Caps the agent's tool and response cycles. | Start at 15. |
Expected result
Agent Core returns one Message. Its observable Agent Steps contain input, tool activity, timing, errors, and output records. They do not expose private model reasoning. Chat history loads automatically for the active session, and Current Date adds a fresh tool on every run when enabled.
Reference details
OpenAI JSON Mode is not available in Agent Core because it conflicts with tool calling. Connect only the tools needed for the task, then lower Max Iterations for tightly bounded work. Deployment availability depends on the components connected to the agent. Check the Agent Deployment guide before deploying.
Provider credentials and credits
Arkus uses platform credentials and Arkus credit metering. OpenAI, Anthropic, and Google Generative AI use the selected provider account. A deployed external key must be a saved owner Credential reference. Credential-bearing deployment availability still depends on the target environment.
Related components
- Chat Input supplies the conversation Message.
- Chat Output displays the response.
- Calculator and Current Date are useful bounded tools.