# Agents > An agent is a prompt, a model and, optionally, a script. It uses only the connections, functions, widgets and other agents you give it. Builders work from a coding agent and operators from an AI client, both through the MCP server, or in the Studio. In Mindset, an agent is a prompt and a model, held to an order by a script when needed. It uses connections to outside systems, operations on them, functions and widgets. Every change is a version, and every execution is a run. Every piece sits on one security and compliance layer: the org sets its posture once, and every agent works under it, with the audit trail and, once an admin turns it on, personal data redaction. The platform runs in your own cloud (AWS, GCP or Azure) or is hosted by Mindset. Your app reaches agents through the SDK, your server through the API, and people through the Hub and schedules. Highlighted: Agent. An **agent** talks to people and systems and makes the judgment calls. It has: | Part | Holds | | ------------- | ---------------------------------------------------------------------------------------------------------------------------------------------------- | | **Prompt** | Five fields: purpose, personality, background, policy rules and output formatting, up to 2,000 characters each. The prompt applies for the whole run | | **Model** | One of the models your org has a provider key for | | **Script** | Optional. Holds the agent to an order, such as waiting for a person. See [Scripts](https://docs.mindset.ai/docs/scripts) | | **Resources** | The [operations](https://docs.mindset.ai/docs/connections-and-operations), [functions](https://docs.mindset.ai/docs/functions), [widgets](https://docs.mindset.ai/docs/widgets) and other agents it may use | > **Info:** Every agent runs under your org's [compliance rules](https://docs.mindset.ai/docs/compliance): personal data protection, write approval and the audit record. They're org settings, so nothing in an agent's prompt, model or resources can switch them off. ## Why it matters Mindset enforces an agent's resource list whatever the prompt says. Its prompt and model live in Mindset, so changing how it behaves means activating a new [version](https://docs.mindset.ai/docs/versions-and-going-live), with no release of your code. > **Tip:** The model follows the prompt's policy rules, but Mindset enforces the resource list. Leaving a resource out is the firmest rule you can set. ## Which one to use | The work | Put it in | | ------------------------------------------------------------------------------ | ------------------------------- | | Who the agent is, what it knows, how it behaves | The prompt | | A judgment call, such as whether a $340 overage is worth querying | The agent | | Work with one right answer, such as comparing an invoice to its purchase order | A [function](https://docs.mindset.ai/docs/functions) | | The same action for every item in a list | A [function](https://docs.mindset.ai/docs/functions) | | A step that must wait, or must not be skipped | A [script](https://docs.mindset.ai/docs/scripts) | | A task another agent already does | That agent, added as a resource | A pasted skill becomes prompt text by default. ## Orca and the builders In the Studio, admins can also build with **Orca**, the agent in the workspace rail that plans and provisions other agents from a Claude skill, a spec, a description or an MCP server. | Step | What Orca does | | ------------- | -------------------------------------------------------------------------------------------------------------------- | | **Brief** | Restates what it read and what it couldn't convert | | **Inventory** | Lists what already exists, to reuse it | | **Plan** | Shows one row per piece, each marked **Build it** or **Use existing**, and stops. Nothing is built until you approve | | **Provision** | Builds connections, then functions and widgets, then the agent and its script | Orca creates the agent itself and hands every other new piece to the **Connection Builder**, **Function Builder**, **Widget Builder** or **Script Builder**. The **Agent Builder** creates or changes one agent: its prompt fields, model, script, resources, schedules and behavior tests. It can't connect a system or build a function or widget. - **Orca matches on names**, so a connection named after a project can be missed. Check **Connections** before you approve. - **Long skills are condensed** to fit each prompt field. Orca says what it shortened. - **Orca tests what it built**, and waits for your go-ahead before a test run writes. - **Orca activates a new agent's first version.** A builder's edits to a live agent wait as a new version for a person to activate. - **New agents stay unavailable.** A builder ticks only **Other agents**, **Schedules** or **Triggers** when its own wiring needs them. See [How agents are started and reached](https://docs.mindset.ai/docs/how-agents-are-started-and-reached). Orca and the builders can't: - Approve a write operation. No agent can. See [Security and approval](https://docs.mindset.ai/docs/security-model). - Run a skill's bundled code. Nothing in Mindset runs a skill's scripts, programs or data files. - Read files on someone's computer. - Drive a website's screens. No connection type logs in and clicks through a site. - Write a script shape the language refuses: a route back to an earlier phase, an action repeated per item, or a model named per phase. Orca lists what it couldn't convert in its plan and again in its final summary. To build one from your coding agent, see [Build an agent](https://docs.mindset.ai/docs/build-an-agent).