> ## Documentation Index > Fetch the complete documentation index at: https://docs.glood.ai/llms.txt > Use this file to discover all available pages before exploring further. # Agents > Create an agent from a template or from scratch, and configure what it does An agent watches a store for you. It wakes on a schedule or when something happens, reads your store's data, records what it finds, and, when you let it, acts on what it finds. Three things make an agent: * **Instructions**: what it should do, in your own words. * **Skills**: written procedures it reads when they apply. See [Skills](https://docs.glood.ai/platform/agents/skills.md). * **Schedules**: when it wakes, and what it does then. See [Schedules and triggers](https://docs.glood.ai/platform/agents/schedules.md). An agent does nothing until you [deploy it to a store](https://docs.glood.ai/platform/agents/deploy.md). Open **Agents** in the left rail. The list shows each agent's mode, how many stores it runs on, how many deployments are running or paused, and how many open findings **need you**. Filter by **Store** or by status (**Active**, **Archived** or **All**). ## Create an agent Choose **New agent**, then pick a starting point. A template fills in every field, and everything it fills in stays editable. | Starting point | What it does | Needs | | - | - | - | | **Store monitor** | Watches traffic, add to cart, checkout, orders and the storefront itself. When a number breaks from its usual range, it finds the change behind it and tells you once | Shopify, the storefront snippet, and browser checks | | **Fraud agent** | Reads every new cash-on-delivery order against your instructions and tags the risky ones before they ship | Shopify | | **Create your own agent** | A blank agent. Say what you want watched in your own words, then pick its skills | | The wizard has four steps. A finished step collapses to a summary; select its header to change it. **1. Basics** A **Name** no other agent in the organization has, and an optional one-sentence **Description** (up to 280 characters) for the agents list. **2. Instructions** What this agent does on top of its skills, in your own words, up to 20,000 characters. Headings, lists and tables all work. **3. Skills** Pick the skills it may read. Glood's own skills that every agent gets are already ticked and marked **Every agent**. This step needs the `skill:attach` permission; without it, the agent gets only the skills every agent gets. **4. Review and create** Lists the checks a template starts with. **Create agent** saves it. There is no model or mode to choose. Every agent runs on Glood's model and starts in **Act** mode. You can turn a deployment down to Recommend or Observe on its own Settings. See [Modes](https://docs.glood.ai/platform/agents/deploy.md#modes). ## Write good instructions The instructions are the agent's standing brief. The template's instructions are a good model: * Say what to watch and what to do about it, as a short list. * Name the skills it should follow, by slug, for example *"follow the fraud-policy skill"*. * Say what deserves a finding and what does not. *"Never record a finding for a coincidence"* saves you noise. * Say what to do when it cannot find a cause. When you need the agent to call a specific tool, use the tool's exact name. See [Agent tools](https://docs.glood.ai/platform/agent-tools.md). ## Configure an agent Open an agent and choose the **Configuration** tab. It is one page of sections; each header summarises its state. | Section | What it holds | Saves | | - | - | - | | **Basics** | Name and description | With the save bar | | **Instructions** | The agent's instructions | With the save bar | | **Rules** | Settings for agents whose kind has them, the Fraud agent today | With the save bar | | **Skills** | The skills it reads. See [Skills](https://docs.glood.ai/platform/agents/skills.md) | At once | | **Schedules** | When it wakes. See [Schedules and triggers](https://docs.glood.ai/platform/agents/schedules.md) | At once | | **Archive** | Retire the agent | After you confirm | Each change to the instructions is kept as a new version, so a past run can always say what it was told. Changing an agent needs the `agent:write` permission. Without it the Configuration tab is read only. ### Rules The Fraud agent's Rules tune how it scores and flags orders. Each setting shows its default, and **Reset** puts it back. Only settings you change from the default are saved. | Group | What it sets | | - | - | | **When to flag an order** | The bar for each risk: return to origin (RTO), fake or prank order, return after delivery, chargeback, fraud after delivery, and rare events. A lower bar flags more orders | | **Order value** | When an order counts as high value, as a multiple of the store's typical order or a fixed amount in its currency | | **Buyer history** | What the same buyer did before: RTO orders, returned orders, return rate, one phone shared by several buyers, and too many COD orders in a window | | **Block lists** | Pincodes, phones and emails treated as fake, whatever the scores say | | **Tags the agent may add** | Your own tags the agent may write to orders. Glood's own `glood-` tags are always allowed | | **Advanced** | How the scores are built. Collapsed by default. Change these with a reason | ### Archive an agent **Archive agent**, in the Archive section, stops every deployment of it, takes it off the list, and means it can never be deployed again. Its runs, findings and history are kept. Type the agent's name to confirm. ## Next > [card] [Schedules and triggers](https://docs.glood.ai/platform/agents/schedules.md) > > When the agent wakes, and what it does then > [card] [Deploy and set the mode](https://docs.glood.ai/platform/agents/deploy.md) > > Put it on a store and decide how far it may go > [card] [Chat with an agent](https://docs.glood.ai/platform/agents/chat.md) > > Ask it about the store it runs on > [card] [Runs, findings and changes](https://docs.glood.ai/platform/agents/activity.md) > > What it did, what it found, and how to undo a change This documentation is built and hosted on [Mintlify](https://mintlify.com), a developer documentation platform.