Agent mode

Every DataMaker workspace has a built-in chat agent. It runs the same MCP toolset that Claude Code, Cursor, and Copilot get when you wire up the datamaker-mcp server — but it’s hosted, no install needed, and it’s the quickest way to drive the platform without touching the GUI.

Opening a chat

From the project sidebar, click Chat → New chat. The mode toggle in the top-right controls how the agent runs:

Chat — the agent calls a few tools and answers in one turn. Good for one-shot queries (list templates, generate 100 customers).
Agent — the agent can plan, call many tools in sequence, retry, write Python scenarios, and execute them. Use this for end-to-end work.

Switch by clicking the mode pill before sending the first message; once a chat has messages the mode is locked.

Anatomy of an agent run

When you send a prompt in Agent mode, here’s what happens:

The model receives your message plus the catalogue of MCP tools.
It plans — usually with a brief “I’ll do X, Y, Z” — and calls the first tool.
Each tool response is fed back to the model. It iterates: more tool calls, or a final answer.
If a tool fails, the model decides whether to retry, branch, or surface the error to you.
You see the live tool calls (with arguments) and outputs streaming into the chat.

There’s no per-step approval by default. To require it on a per-tool basis, see Settings → Agent permissions.

Prompt patterns that work

Bad prompts get vague answers. Good prompts get tool calls. A few patterns:

Be specific about scale: “Generate 100 SAP business partners for Germany” beats “give me some test data”.
Name the entity / target: “POST them to A_BusinessPartner in the S/4 sandbox” beats “push to SAP”.
Mention output: “Save the result as reg_bp_de_2026q2” or “show me the first three rows” gives the agent a clear endpoint.
Reference real names: if you know your template is called “Customer”, say so — the agent will skip the discovery step.

A single good prompt:

Pull 25 existing SAP Business Partners from the S/4 sandbox where Country = DE and BPRole = FLCU01, save them as a regression set called reg_bp_de_2026q2, mask TaxNumber1 with format-preserving substitution, and POST the masked set back to a new fake-customer entity.

The agent will call fetch_records, mark_field_sensitive, save_set, mask, and post_to_sap_entity in order, streaming progress.

Inspecting & replaying

Each chat run is replayable. Open the chat, scroll back, and you see every tool call with arguments. Click any tool call to:

Copy the exact JSON arguments.
Re-run it on its own (without the surrounding chat).
Pin it to your Snippets for one-click reuse.

Saving a chat as a scenario

If a chat run does something useful you want to repeat — and you’d rather not retype the prompt — click Save as scenario at the bottom of the chat. The agent generates a Python scenario that does the same thing, writes it to your Scenarios list, and you can trigger it from the API or CI.

This is the canonical path for “I figured out how to do X interactively, now make X runnable from a pipeline”.

Permissions & sensitive data

By default the agent will not export sensitive fields. If a tool tries to copy a sensitive value into chat output or out to a non-DataMaker target, the agent surfaces the block and asks. Override per chat with confirm export of sensitive fields: yes, or workspace-wide under Settings → Agent permissions.

See Templates → Sensitive fields for the model.

Limits

Plan	Agent runs / day	Max tools per run
Free	25	25
Pro	500	100
Enterprise	per contract	per contract

A “run” is one user message plus all the tool calls the agent makes in response.