# Actions Source: https://docs.anagram.ai/actions/overview Things your agent can do beyond answering questions. Actions give your agent hands. Answering questions is the baseline; actions let it show a store locator, push a lead into Klaviyo, or log survey answers to a spreadsheet, right in the middle of a conversation. You manage them on the **Actions** page. Each action has an on/off toggle and its own configuration. Actions are set up once for your whole agent and work across every placement. ## Show stores Displays an interactive map and list so shoppers can find your physical locations. Click **Set up stores**, add your locations, and enable the action. Stores save as you add them. Once enabled, the agent can bring up the locator whenever a shopper asks where to buy in person. You can also make it the very first thing shoppers see on an Embedded inline placement, using the **Show stores** [suggestion mode](/launch/conversation-starters#show-stores). ## Send to Klaviyo Lets the agent send a shopper's details to a Klaviyo list, so conversations can feed your email and SMS flows. Someone asks about a sold-out item, the agent offers to notify them, and their profile lands in Klaviyo. This action needs your Klaviyo account connected first; the card walks you through it. After configuring, use **Test connection** to verify the list is reachable, or **Send a sample profile** to push a real test profile into the list and see it land. ## Send to Google Sheet Appends a row to a Google Sheet you choose. Handy for collecting structured answers without more tooling: wholesale inquiries, feedback, quiz responses. Connect your Google account, pick the spreadsheet, then use **Test connection** to confirm Anagram can see it, or **Send a sample row** to write a real test row. The two sample tests write real data: a real profile in Klaviyo, a real row in your sheet. Delete the test entries afterward if they'd get in the way. ## Telling the agent when to act Enabling an action makes it available; the agent decides when to use it based on the conversation. If you want more control over the moment, write a [skill](/brain/skills). For example, a skill triggered by "when a shopper asks to be notified about restocks" can instruct the agent to collect an email and send it to Klaviyo, in that order, every time. # Analytics Source: https://docs.anagram.ai/analytics/overview What each card on the Analytics page means, and exactly how the numbers are counted. The **Analytics** page answers the question your CFO will ask: is this thing working? Use the date range picker at the top to set the reporting window (it defaults to the last 30 days). This page walks through every card in the order it appears, but start with the three words that trip everyone up. ## Messages, engagements, and visitors These are three different counts, and they nest inside each other: * A **message** is one thing a shopper sends: a typed question or a tapped suggestion chip. A single conversation usually has several. * An **engagement** is a chat. Specifically, it's a conversation in which the shopper sent at least one message. Ten messages back and forth in one chat is still one engagement. A shopper who opens the widget, looks, and leaves without sending anything is zero engagements; seeing the agent doesn't count. * An **engaged visitor** is a person. If the same shopper chats with your agent on Monday and again on Thursday, that's two engagements but one engaged visitor. A worked example: one shopper has two conversations, sending four messages in the first and two in the second. That's 6 messages, 2 engagements, 1 engaged visitor. Most of the page counts engagements, because a chat is the natural unit of "the agent did some work." Engaged visitors show up where people are the right unit, like conversion rate. Your own preview chats inside Anagram never count. Every number on this page comes from real shoppers on your live site. ## The cards, top to bottom ### Usage Total engagements in the period, with a chart of engagements per day. This is your "are shoppers using it" number, and the suggestion chips on your [placements](/launch/conversation-starters) are usually the biggest lever on it. Click **View details** to open the individual conversations behind any day. ### Anagram-assisted sales The number of orders attributed to the agent in the period, with a per-day chart. An order counts as Anagram-assisted when the shopper interacted with your agent and then completed the purchase within the attribution window, currently 7 days after the interaction. A few details worth knowing about how this is counted: * Attribution is anonymous. Anagram recognizes the same browser across the chat and the checkout; nobody has to log in or click a special link. * It is not last-click. The agent doesn't need to be the final thing the shopper touched before buying. If they chatted, left, came back through an email two days later and purchased, that order still counts, because the chat happened within the window. * Each order counts once, even if the shopper had several conversations. * It requires your [Shopify connection](/shopify), which is how orders get linked back to conversations. Because the window looks forward from the chat, a sale can land a few days after the engagement that earned it. Give a new launch at least a week before judging this number. ### Attributed revenue The money side of the same thing: total order value of your Anagram-assisted sales for the period, shown in your store's currency. Same attribution rules as above; this is the sum where assisted sales is the count. ### Conversion Rate The share of engaged visitors who went on to purchase within the attribution window. This one is counted in people, not chats: purchased visitors divided by engaged visitors. Hover over the number and the card shows you the exact breakdown it was calculated from. Counting people rather than chats keeps the rate honest. A shopper with three conversations and one purchase is one converted visitor out of one engaged visitor, not one out of three. ### Average Order Value Attributed revenue divided by the number of assisted orders: what the typical agent-assisted order is worth. Comparing this against your store-wide AOV is one of the more persuasive numbers here, since guided shoppers often buy more. The card shows a dash until you have at least one assisted sale. ### Top products Which products sell after agent conversations, with units sold and assisted revenue per product. Good for spotting what the agent is effective at selling, and occasionally what it recommends that people don't buy. ### Conversations Every transcript, searchable, with a **Purchases** filter to read only the conversations that ended in an order. Each conversation shows which placement it came from. This is the most underrated section on the page. Read ten transcripts and you'll find missing knowledge, an unclear policy page, or a question you never thought shoppers would ask. Fixes usually take a minute in [Brain](/brain/knowledge). ## How the date range interacts with attribution The date range selects when the engagements happened. Assisted sales are then allowed to complete inside the attribution window even if that runs past the end of the range. So "last week" means orders attributed to last week's conversations, including a purchase that closed this Monday. This also means recent periods can tick upward for a few days as their window plays out. ## A note on scope Analytics covers your whole agent across all placements. Placement shows up as a label on each conversation so you can see where chats happen, but the numbers are agent-wide. # Knowledge Source: https://docs.anagram.ai/brain/knowledge The facts your agent draws on: your catalog, your website, and anything you add yourself. Knowledge is the first tab in **Brain**, and it's where most of your agent's answers come from. There are three sources, and they work together. When a shopper asks something, the agent pulls whatever is relevant, whether that's a product from your catalog, a page from your site, or a fact you typed in. ## Catalog Your product catalog is the backbone. Connect Shopify and Anagram syncs your products automatically every day, including titles, descriptions, prices, tags, collections, and metafields. The agent uses this to recommend products, answer questions like "does this come in a medium?", and show product cards in chat. To connect, open **Brain**, find the Catalog card, and click **Connect Shopify**. You'll enter your `myshopify.com` domain and approve the app install. Full details are on the [Shopify](/shopify) page. Once connected, click **Manage** on the Catalog card to browse and search everything the agent can see. If a product looks wrong here, fix it in Shopify and it will update on the next sync. ## Web search With web search on, the agent can look up answers on your website in real time. This is how it handles questions your catalog can't: shipping policies, return windows, brand story, ingredient pages. The **Web search** card has a few settings: * **Site to search** limits the agent to a specific domain. Leave it blank and it uses your store's domain. * **Also search the open web** lets the agent look beyond your site. Most brands leave this off so answers stay grounded in their own content. Web search is on by default. If your site's policy pages are accurate and current, you're in good shape without any extra work. ## Added knowledge This is for the facts that live in your head or your team's Slack, not on your website. The card calls them tribal facts, and that's the right way to think about it. Examples: * "Our candles are made from soy wax" * "We don't offer gift wrapping during December" * "The Redwood line is being discontinued; don't recommend it for restocks" Click **New entry**, give it a **Title**, write the fact, and click **Add entry**. Each entry is a single fact or a small cluster of related ones. Short, specific entries work better than long documents because the agent retrieves entries individually when they're relevant. When you test your agent and it gets something wrong, the fix is usually one knowledge entry away. Ask yourself: where would the agent have found the right answer? If the answer is "nowhere," add it here. ## When changes take effect Saving a knowledge entry makes it live for shoppers within a few minutes. Catalog changes flow in with the daily Shopify sync, or sooner if you trigger a manual sync. # Rules Source: https://docs.anagram.ai/brain/rules Always-on instructions that keep your agent on-brand and out of trouble. Rules are standing orders. Every rule you save applies to every response your agent gives, on every page, in every conversation. They're how you encode the things a good employee would just know: what to promise, what never to promise, how to talk about competitors, when to point someone to customer service. You'll find Rules as a tab in **Brain**. ## Writing a rule Each rule is one instruction with a polarity: * **Always** rules describe what the agent should do. "Always greet shoppers warmly and stay on-brand." * **Never** rules describe what it must avoid. "Never promise a specific delivery date." Pick **Always** or **Never**, write the behavior in the text box, and click **Save rule**. It's live immediately. Your saved rules appear in a list below the composer, and every rule in that list is active. To retire a rule, delete it; there's no on/off switch. ## What makes a good rule Keep each rule to a single, concrete behavior. A few patterns that work well: * **Guardrails.** "Never give medical advice; suggest the customer consult a doctor." * **Brand voice.** "Always refer to our loyalty program as The Circle, not the rewards program." * **Sales behavior.** "Always suggest a complementary product after answering a product question." * **Escalation.** "Never handle order cancellations; direct shoppers to [support@yourbrand.com](mailto:support@yourbrand.com)." Avoid stuffing several instructions into one rule. "Always be friendly, mention free shipping, and ask for their email" is three rules pretending to be one, and the agent follows three separate rules more reliably. ## Rules vs. knowledge vs. skills It's worth keeping the three straight, because the fix for a bad answer depends on which one is missing: * The agent got a **fact** wrong or didn't know it? Add [knowledge](/brain/knowledge). * The agent **behaved** wrong, was off-brand, or promised something it shouldn't? Add a rule. * The agent needs to follow a **multi-step process** for a specific task, like size finding? Write a [skill](/brain/skills). ## Testing a rule before saving While you're writing a rule, the preview chat next to the editor automatically applies it on top of what you've already saved. You'll see a "Testing unsaved changes" badge; nothing there goes live or touches your analytics. Chat with the preview, check the behavior change, and save once it looks right. This works for edits to knowledge and skills too. # Skills Source: https://docs.anagram.ai/brain/skills Step-by-step playbooks your agent follows for specific shopper tasks. A skill is a playbook. Where [rules](/brain/rules) shape every response, a skill only kicks in when a shopper's situation calls for it, and then the agent follows your instructions step by step. Think of the difference between "always be polite" (a rule) and "here's exactly how we help someone find their size" (a skill). You'll find Skills as a tab in **Brain**. ## Creating a skill Click into the Skills tab and fill out three fields: **Skill name.** A short label like "Size finder" or "Gift concierge." This is for you and the agent, not shoppers. **When should this skill be used?** This is the trigger, and it's the most important field. It controls when the agent reaches for this skill, so be specific about the shopper intent and the signals that should activate it. For example: "When a shopper asks which size, fit, or variant will work for them." **Instructions.** The playbook itself. Write it as numbered steps in plain language, the way you'd train a new hire: ```text theme={null} 1. Ask what they usually wear in other brands. 2. Ask whether they prefer a snug or relaxed fit. 3. Recommend a size using our fit guide: our tops run small, so suggest sizing up for a relaxed fit. 4. Offer to show the product in their size. ``` All three fields are required. Save, and the skill is live. Like rules, every skill in your list is active; delete a skill to retire it. ## How the agent uses skills The agent always knows which skills exist and what triggers them, but it only reads the full instructions when a conversation matches a trigger. So a shopper asking about shipping never sees size-finder behavior, and your size-finder instructions can be as detailed as you want without cluttering every other conversation. ## Skill ideas for a Shopify brand * **Size and fit finder.** Ask fit questions, apply your sizing quirks, recommend a size. * **Gift concierge.** Ask who the gift is for, the occasion, and budget, then recommend two or three options. * **Routine builder.** For skincare and supplements, ask about goals and build a multi-product routine. * **Restock helper.** When someone mentions running out, find their product and offer the larger size or a bundle. ## Skills vs. Actions Skills are conversational playbooks: instructions the agent follows in chat. [Actions](/actions/overview) are integrations: concrete things the agent can do, like showing a store locator map or sending a lead to Klaviyo. They combine well. A "help them find a store" skill can tell the agent when and how to use the Show stores action. # How Anagram works Source: https://docs.anagram.ai/concepts/site-agent One agent, one brain, placed wherever you want it on your site. ## One agent per store Your Anagram project has exactly one Site Agent. It has one brain, one voice, and one look, no matter how many places it appears on your site. That's deliberate. Shoppers who chat with the bar on your homepage and later open the button on a product page are talking to the same assistant, with the same knowledge and the same rules. This is different from tools where you build a separate bot per page. In Anagram you configure the agent once, then decide where it shows up. ## The pieces **Brain** is everything the agent knows and how it behaves. It has three parts: * [Knowledge](/brain/knowledge) is the facts: your product catalog, your website, and anything you type in yourself. * [Rules](/brain/rules) are always-on instructions, phrased as things the agent should always or never do. * [Skills](/brain/skills) are step-by-step playbooks the agent follows for specific tasks, like walking someone through finding their size. **Placements** are where the agent appears. Each placement has a form factor (center bar, floating button, custom trigger, or an embedded widget) and its own [conversation starter](/launch/conversation-starters): the greeting and suggested questions shoppers see first. A custom trigger lets a button you already own open an Anagram panel. Placements live under **Launch**. **Style** controls how the agent looks: colors, fonts, and branding. It's set once for the whole agent, on the **Style** tab under Launch. Individual placements can override parts of it if you need to. **Actions** are things the agent can do beyond answering: show a store locator map, send a shopper's details to Klaviyo, or log responses to a Google Sheet. See [Actions](/actions/overview). **Analytics** shows engagements, Anagram-assisted sales, and every conversation transcript. See [Analytics](/analytics/overview). ## Saving goes live There are no drafts. When you save a rule, a knowledge entry, or a placement change, it's live for shoppers within a few minutes. The way to try something before committing is the preview chat, which lets you test unsaved edits against the real agent. Save when it behaves the way you want. ## What shoppers experience A shopper lands on your site and sees the agent in whatever form you placed there, with a greeting and a few tappable suggested questions. They tap one or type their own. The agent answers using your catalog and knowledge, shows product cards when it recommends something, and follows your rules the whole way. If they buy within the attribution window after chatting, that sale shows up in your analytics as Anagram-assisted. # Build a recommendation quiz Source: https://docs.anagram.ai/guides/recommendation-quiz Turn your agent into a guided product finder with one skill and one suggestion. Product quizzes convert because they do the shopper's thinking for them. The usual version is a rigid form built in a quiz app. Your agent can run the same play conversationally: ask a few questions, then recommend real products from your catalog, and handle the follow-up questions a form never could. This guide builds one with a single [skill](/brain/skills). Plan on 15 minutes. ## Before you start Your [catalog](/brain/knowledge#catalog) needs to be connected, since the recommendations come from your synced products. That's it. ## Step 1: Write the quiz as a skill Go to **Brain → Skills** and create a new skill. Here's a worked example for a skincare brand; adapt the questions and logic to your products. **Skill name** ```text theme={null} Routine finder quiz ``` **When should this skill be used?** ```text theme={null} When a shopper asks for a recommendation, says they don't know what to choose, asks to take the quiz, or asks what's right for their skin. ``` The trigger is what makes the quiz fire at the right moments, so cover the different ways shoppers express "help me choose." Notice it isn't just "when they ask for the quiz"; anyone signaling indecision is a quiz candidate. **Instructions** ```text theme={null} Run a short quiz to find the right routine. Ask one question at a time and wait for the answer before asking the next. 1. Ask about their skin type: oily, dry, combination, or not sure. If they're not sure, ask whether their skin feels tight after washing (dry) or gets shiny by midday (oily). 2. Ask what their main goal is: clearer skin, fewer fine lines, more hydration, or evening out tone. 3. Ask if they have any sensitivities or ingredients they avoid. 4. Recommend 2 or 3 products from the catalog that fit their answers, as a routine: cleanser first, then treatment, then moisturizer. For each one, say in one sentence why it fits what they told you. 5. Ask if they'd like alternatives at a different price point. Keep it light. Never diagnose skin conditions; if they mention a medical concern, suggest they see a dermatologist. ``` A few things this example does that are worth copying: * **One question at a time.** Without that line, the agent may dump all the questions at once, which kills the quiz feel. * **A recovery path for "not sure".** Shoppers who'd bounce off a form dropdown will answer "does your skin feel tight after washing?" * **A capped recommendation count.** Two or three products with reasons beats a wall of options. * **A closing offer.** The price-point question keeps the conversation going instead of ending on a list. Save the skill. ## Step 2: Test it Use the preview chat and come at the quiz from different angles: "what should I buy?", "I'm new to skincare", "take the quiz". Check that it triggers each time, asks one question at a time, and recommends sensible products. If it recommends oddly, the fix is usually in the instructions: add a line like "never recommend the exfoliating toner for sensitive skin." If a product detail is wrong, that's a catalog or [knowledge](/brain/knowledge) fix instead. ## Step 3: Make the quiz discoverable The skill only helps shoppers who talk to the agent, so put the quiz in front of them: * **Add a suggestion chip.** In your placement's [suggestions](/launch/conversation-starters), switch to Fixed suggestions and add "Find my routine" or "Take the 30-second quiz" as a chip, or keep Auto mode and rely on the agent surfacing it. A fixed chip is the more reliable pull. * **Pin it where it's relevant** with a [suggestion set](/launch/suggestion-sets). A set targeting your bestselling collection can open with "Not sure which is right for you? Take the quiz." * **Give the quiz its own placement.** An [Embedded inline](/launch/placements) placement on a "Find your routine" landing page turns the quiz into a destination you can link from email and ads. ## Variations The same skeleton works for most guided-selling problems. Change the questions and the recommendation logic: * **Gift finder**: who's it for, occasion, budget, then two or three options. * **Fit finder**: current brand and size, fit preference, then one size recommendation with your brand's sizing quirks baked into the instructions. * **Bundle builder**: their goal, what they already own, then a set of products that work together. If you build one you're proud of, we'd genuinely like to see the transcript. Send it to [support@anagram.ai](mailto:support@anagram.ai). # Anagram MCP Source: https://docs.anagram.ai/integrations/mcp Ask ChatGPT, Claude, Codex, or Cowork questions about your Anagram conversations and analytics. The Anagram MCP connects your AI assistant to Anagram Studio. You can ask questions about shopper conversations, conversation activity, commerce impact, and other analytics without exporting data first. The connection is read-only. It cannot change your Anagram projects or settings, and it only returns data from projects your Anagram account can access. ## Connection details Use these values in every client: | Field | Value | | -------------- | ----------------------------------- | | Name | `Anagram` | | MCP server URL | `https://studio.anagram.ai/api/mcp` | | Authentication | OAuth | During setup, your browser opens an Anagram sign-in page. Sign in and approve the connection. Anagram uses Clerk to complete the OAuth flow. You do not need to create an OAuth client ID or secret. ## Choose your client Install the official Anagram plugin from ChatGPT's Plugins Directory. Add Anagram as a custom connector in Claude. Connect from the ChatGPT desktop app, Codex CLI, or Codex IDE extension. Add Anagram to your Claude account, then use it in Cowork. ## Try the connection After connecting, start with a question such as: * "Which Anagram projects can I access?" * "What did shoppers ask about most often this week?" * "Show me the products with the most assisted sales last month." * "Find conversations where shoppers asked about sizing." Analytics pass through a buffered event pipeline, so the newest activity may take a short time to appear. # Connect Anagram to ChatGPT Source: https://docs.anagram.ai/integrations/mcp-chatgpt Install the official Anagram plugin from ChatGPT's Plugins Directory. Anagram is available as an official plugin in ChatGPT's Plugins Directory. You do not need developer mode or an MCP server URL. ## Connect Anagram Open **Plugins** from the ChatGPT sidebar, or go to **Settings → Plugins**. Search for `Anagram` and open its listing. Select the plus button to install Anagram. ChatGPT will prompt you to connect your Anagram account. Select **Connect**, sign in to Anagram, and approve access. ChatGPT completes the connection securely through OAuth. Start a new chat and ask ChatGPT to use Anagram. For example: "Use Anagram to show me what shoppers asked about most often this week." If **Connect** is unavailable or shows **Disabled by admin**, ask your ChatGPT workspace admin to enable Anagram. Plugin availability can depend on your plan, workspace settings, role, and region. The Anagram connection is read-only and only returns data your Anagram account can access. See [OpenAI's Plugins Directory guide](https://help.openai.com/en/articles/20001256-plugins-in-chatgpt-and-codex) for plan and workspace details. # Connect Anagram to Claude Source: https://docs.anagram.ai/integrations/mcp-claude Add the Anagram MCP as a custom connector in Claude. Anthropic calls remote MCP connections "custom connectors." The connection is saved to your Claude account, so you can use it in Claude on the web, desktop, and mobile. ## Individual accounts In Claude, open **Customize → Connectors**. Select **+ → Add custom connector**. Enter: * **Name:** `Anagram` * **Remote MCP server URL:** `https://studio.anagram.ai/api/mcp` Leave the OAuth Client ID and OAuth Client Secret in **Advanced settings** empty. Select **Add**. After selecting **Add**, complete the Anagram sign-in and approval screen when Claude asks. OAuth is handled automatically through Clerk. Start a conversation. Select **+ → Connectors**, then turn on **Anagram**. Free Claude accounts can add one custom connector. ## Team and Enterprise accounts An Owner or Primary Owner must add Anagram to the organization first: 1. Open **Organization settings → Connectors**. 2. Select **Add**, hover over **Custom**, then select **Web**. 3. Add `https://studio.anagram.ai/api/mcp`. Leave the optional OAuth client ID and secret empty. 4. Select **Add**. Each member can then open **Customize → Connectors**, find **Anagram** with the **Custom** label, and select **Connect** to sign in. Adding Anagram to an organization does not give every member access to the same data. Each person signs in separately, and Anagram only returns projects that person can access. See [Anthropic's current custom connector guide](https://support.claude.com/en/articles/11175166-get-started-with-custom-connectors-using-remote-mcp) for plan and workspace details. # Connect Anagram to Codex Source: https://docs.anagram.ai/integrations/mcp-codex Add the Anagram MCP to the Codex desktop, CLI, and IDE clients. Codex shares MCP settings across the ChatGPT desktop app, Codex CLI, and Codex IDE extension. ## ChatGPT desktop app In the ChatGPT desktop app, open **Settings → MCP servers** and select **Add server**. Set the name to `Anagram`, choose **Streamable HTTP**, and enter: `https://studio.anagram.ai/api/mcp` Save the server, then select **Restart**. Find Anagram in the server list and select **Authenticate**. Complete the Anagram sign-in and approval screen. OAuth is handled automatically through Clerk. Type `/mcp` in the Codex composer. Anagram and its tools should appear in the connected server list. ## Codex CLI Run: ```bash theme={null} codex mcp add Anagram --url https://studio.anagram.ai/api/mcp codex mcp login Anagram ``` Your browser opens the Anagram sign-in and approval screen. After signing in, run `codex mcp list` to check the connection. ## Configuration file You can also add Anagram to `~/.codex/config.toml`: ```toml theme={null} [mcp_servers.Anagram] url = "https://studio.anagram.ai/api/mcp" auth = "oauth" ``` Then run: ```bash theme={null} codex mcp login Anagram ``` The IDE extension reads the same configuration. A trusted project can instead keep the entry in `.codex/config.toml`. ## Codex IDE extension The IDE extension does not have a separate add-server form. Open its settings and choose the option to edit `config.toml`, add the configuration above, then run `codex mcp login Anagram` in a terminal. See [OpenAI's current Codex MCP guide](https://developers.openai.com/codex/extend/mcp) for all configuration options. # Connect Anagram to Cowork Source: https://docs.anagram.ai/integrations/mcp-cowork Add Anagram to your Claude account and use it in Cowork. Cowork uses the remote connectors saved to your Claude account. You do not create a second connection inside Cowork. ## Connect Anagram In Claude, open **Customize → Connectors**. Select **+ → Add custom connector**, then enter: * **Name:** `Anagram` * **Remote MCP server URL:** `https://studio.anagram.ai/api/mcp` Leave the OAuth Client ID and OAuth Client Secret in **Advanced settings** empty. Select **Add**. After selecting **Add**, complete the Anagram sign-in and approval screen when Claude asks. OAuth is handled automatically through Clerk. Start a Cowork session by selecting **Cowork** in the message box on the Claude home screen. In the session, select **+ → Connectors**, then turn on **Anagram**. If you use a Team or Enterprise account, an Owner or Primary Owner must add the custom connector under **Organization settings → Connectors** before members can connect it. Anagram is a remote connector. It works through your Claude account and does not require the Claude Desktop app to stay open. Cowork on web and mobile is in beta and rolling out by plan. If you do not see **Cowork** in the message box, update the app and check Anthropic's current availability. See [Anthropic's current connector guide](https://support.claude.com/en/articles/11176164-use-connectors-to-extend-claude-s-capabilities) and [Cowork client guide](https://support.claude.com/en/articles/15520349-use-claude-cowork-on-web-desktop-and-mobile) for current availability. # Introduction Source: https://docs.anagram.ai/introduction Anagram puts an AI shopping agent on your store that answers questions, recommends products, and helps shoppers buy. ## Meet your Site Agent Anagram gives your store a **Site Agent**: an AI assistant that lives on your site and talks to shoppers the way your best salesperson would. It answers product questions, recommends items from your catalog, helps people find the right size or a nearby store, and nudges browsers toward checkout. You set it up once. There is one agent per store, and it shows up wherever you place it: as a search-style bar in the middle of the page, a floating chat button, or a panel embedded right into a page. ## How it fits together Everything you do in Anagram happens in four areas: What your agent knows and how it behaves. Knowledge, Rules, and Skills live here. Where your agent appears on your site and what shoppers see first. Things your agent can do beyond chatting, like showing store locations or sending leads to Klaviyo. Engagements, assisted sales, and full conversation transcripts. ## Where to start If you're new, the [onboarding](/onboarding) page explains the setup wizard you'll see on first sign-in, and the [quickstart](/quickstart) walks through the four-step launch checklist on your Anagram home page: add knowledge, test the agent, configure a placement, and put the snippet on your site. If something isn't working, check [troubleshooting](/troubleshooting) first. If you're still stuck or can't find what you need in these docs, email [support@anagram.ai](mailto:support@anagram.ai). A real person reads it. # Add to your site Source: https://docs.anagram.ai/launch/add-to-your-site Put the code snippet on your storefront and go live. Once a placement is configured, getting it onto your site is one small code snippet. Click **Launch** on your Anagram home page, or **Copy snippet** on the placement, and you'll get something like this (copying the snippet is where your [plan or free trial](/plans-and-billing) kicks in): ```html theme={null} ``` Each placement has its own snippet. The snippet never changes after you paste it; everything you edit later in Anagram, from suggestions to style to the form factor itself, flows through automatically. The one exception worth knowing: if you switch a placement between a floating form factor and an embedded one, you may want to move the snippet, since embedded widgets render exactly where the snippet sits. ## Where to paste it It depends on the form factor: * **Center bar** and **Floating button** float above the page, so the snippet can go almost anywhere. The convention is just before the closing `` tag, which applies it site-wide. * **Custom trigger** also floats above the page, but stays closed until your site dispatches `anagram:open`. Put the snippet before ``, then connect your own button as shown on the [Placements page](/launch/placements#form-factors). * **Embedded panel** and **Embedded inline** render exactly where the snippet sits, so paste it at the precise spot on the page where the widget should appear. ## On Shopify For a site-wide placement (center bar, floating button, or custom trigger): 1. In Shopify admin, go to **Online Store → Themes**. 2. On your live theme, click the **⋯** menu, then **Edit code**. 3. Open `theme.liquid` under Layout. 4. Paste the snippet on its own line just above ``, near the bottom of the file. 5. Click **Save**. For an embedded placement on a specific page, add a **Custom Liquid** section in the theme editor where you want the widget, and paste the snippet there. If editing theme code makes you nervous, this is a two-minute task for whoever manages your theme. The snippet is a single line and doesn't touch anything else. ## Checking it worked Open your storefront in a regular browser window and you should see the placement. If you don't: * Give it a few minutes. Placement settings are cached briefly, so a just-created placement can take a moment to appear. * Make sure the placement still exists in Anagram. A deleted placement's snippet renders nothing. * For center bars with **Reveal after one page scroll** turned on, scroll down. It's working; it's waiting. Still not showing? The [troubleshooting page](/troubleshooting#the-agent-isnt-appearing-on-my-live-site) has the full checklist. ## Taking it down Two options. Deleting the placement in Anagram stops it from rendering immediately, no theme edit needed. Or remove the snippet from your theme, which does the same thing from the other side. For a temporary pause, deleting the placement in Anagram is faster, but note that you'd recreate it (and re-paste its new snippet) to bring it back. # Conversation starters Source: https://docs.anagram.ai/launch/conversation-starters What shoppers see before they type: the greeting, and auto or fixed suggested questions. Before a shopper types anything, your agent shows a conversation starter: an optional greeting plus a few tappable suggested questions, which we call chips. This first impression does a lot of work. Most shoppers won't compose a question from scratch, but they will tap "What's your best seller?" if it's sitting right there. Each placement has its own conversation starter. You'll find it in the placement editor on the **Launch** page. ## Greeting A short line of text above the suggestions, like "Hey! Looking for something?" It's optional. If you skip it, shoppers just see the suggestions. ## Suggestion modes Under **Suggestions**, pick one of three modes. ### Auto The default, and what we recommend for most placements. The agent generates suggestions from the page the shopper is on. On a product page for a hiking boot, shoppers might see "Is this waterproof?" and "How does the sizing run?" On your homepage, they'll see broader questions about your brand and catalog. You don't write anything. The suggestions come from your synced catalog and your site's pages, and they update as your pages change. The very first time a shopper lands on a page Anagram hasn't seen before, suggestions for that page are still being generated, so the shopper may briefly see just the greeting. Every visit after that gets the full set. ### Fixed suggestions You write the suggestions yourself, and every shopper sees the same ones on every page. Type each one into the **Add a suggestion** field and click **Add**. Remove one by clicking the x on its chip. Fixed mode makes sense when you want tight control over the first interaction, like a placement on a landing page with one job: "Find my shade", "Take the quiz", "Talk to us". ### Show stores Available only on Embedded inline placements. Instead of a chat greeting, the widget opens straight into your store locator, with a map and list of locations. Shoppers can still chat from there. This mode needs the **Show stores** action enabled with your locations added. If it isn't set up yet, the editor links you to **Configure Show stores** on the Actions page. See [Actions](/actions/overview). ## Suggestion order On Embedded panel and Embedded inline placements, you can choose whether suggestions appear above or below the text input: **Suggestions first** or **Input first**. Suggestions first is the default and generally the better bet, since the chips are what pull people in. ## Pinning suggestions for specific products Both Auto and Fixed modes can be overridden on particular products. If you want every product in your "Bestsellers" collection to open with "Why is this so popular?", that's a [suggestion set](/launch/suggestion-sets). # Placements Source: https://docs.anagram.ai/launch/placements Where and how your agent appears on your site. A placement is one spot where your agent shows up. Your homepage might get a center bar, your product pages a floating button, and a "Help me choose" landing page an embedded panel. Same agent, same brain, different front doors. Placements live on the **Launch** page. Click **Add placement**, name it something you'll recognize later ("Homepage bar", "PDP button"), and pick a form factor. ## Form factors **Center bar.** A search-style bar sitting in the middle of the page. Shoppers type into it or tap a suggestion, and it opens into a chat drawer. This is the default, and it earns that spot: it reads as "ask us anything" rather than "here's a chatbot," and it gets strong engagement on homepages. Under **Advanced settings** you can turn on **Reveal after one page scroll**, which keeps the bar hidden until the shopper scrolls about one screen down. **Floating button.** The familiar chat bubble pinned to the corner of every page. You can set the **Button color** and pick a **Button icon**, including uploading your own. Good as a site-wide safety net. **Embedded panel.** A widget that renders inside a page exactly where you place it, and opens into a larger chat panel when the shopper engages. Good for dedicated pages like a quiz replacement or a "get advice" section. **Custom trigger.** Anagram renders the panel but no launcher. Use this when your site already has its own button, such as an "Ask us" action in the header. The button opens the placement by dispatching a targeted browser event: ```js theme={null} window.dispatchEvent( new CustomEvent('anagram:open', { detail: { placementId: 'your-placement-id' }, }), ) ``` The `placementId` must match the `data-placement` value in that placement's Anagram script. Repeated events are safe and do not create another panel or conversation frame. **Embedded inline.** The whole conversation happens inline, inside the page. This is the only form factor that supports the **Show stores** opener, which launches straight into a store locator. See [Conversation starters](/launch/conversation-starters#show-stores). ## Input placeholder Every form factor has an **Input placeholder**: the grey prompt shown in an empty text input, such as "What are you shopping for?" instead of the default "Type anything here...". It applies wherever that placement renders an input — the center bar and embedded panel launchers, and the conversation itself once the shopper opens it. Leave it blank to use the default. ## Panel settings For every form factor except Embedded inline, you can set: * **Panel title.** The heading on the open chat panel, like "Anagram Assistant" or "Ask Glow Co." * **Panel image.** An optional logo or avatar shown in the panel. * **Panel placement.** Whether the open panel appears as a **Left panel**, **Center modal**, or **Right panel**. ## Conversation starter Each placement has its own greeting and suggested questions, so your homepage bar can say something different from your product-page button. That's covered in [Conversation starters](/launch/conversation-starters) and [Suggestion sets](/launch/conversation-starters). ## Editing and deleting Select a placement on the Launch page to edit it. You'll see a live preview alongside the settings; nothing changes on your site until you click **Save changes**, and then it goes live within a few minutes. Deleting a placement takes it off your site immediately, even if the code snippet is still in your theme. The snippet just stops rendering anything. Past conversations from that placement stay in your analytics. ## One agent, many placements Remember that placements don't have their own knowledge or rules. Everything in [Brain](/brain/knowledge) applies everywhere. If you want different behavior on different pages, that's usually a job for [suggestion sets](/launch/suggestion-sets) (different starting questions per product) rather than a separate placement. # Style Source: https://docs.anagram.ai/launch/style Make the agent look like part of your brand, not a bolted-on widget. Style controls how your agent looks everywhere it appears. Set it once on the **Style** tab of the **Launch** page, and every placement inherits it. There's a live preview alongside the settings, so you can see each change as you make it. ## What you can set * **Font** and **Font color** for the chat. * **Primary color**, used for buttons and accents. Match your brand's primary or a strong accent color. * **Background color** of the chat surface. * **Corner radius**, from sharp 0px corners to fully rounded 32px. Match whatever your site's buttons and cards do. * **Animation style** for the agent's ambient gradient: Ember, Nebula, Beam, or None. * **Show shadow behind input**, a subtle depth effect on the text field. * **Show Powered by Anagram**, which toggles the small attribution line. ## Per-placement overrides Occasionally one placement needs to look different, like a dark-themed landing page while the rest of your site is light. Individual placements can override parts of the shared style in their editor. Anything you don't override keeps following the Style tab, so a later brand-color change still flows through everywhere. Keep overrides rare. The point of one shared style is that shoppers recognize the agent as the same assistant across your site. ## Form factor settings live with the placement Button color and icon for the floating button, panel title, panel image, and panel position all belong to the individual [placement](/launch/placements), not the Style tab, because they can reasonably differ per spot. # Suggestion sets Source: https://docs.anagram.ai/launch/suggestion-sets Pin specific suggested questions to a collection, a tag, or individual products. Suggestion sets let you decide exactly which suggested questions appear on certain product pages, while [Auto or Fixed suggestions](/launch/conversation-starters#auto) handle everything else. When a shopper views a product that matches one of your sets, the set's suggestions replace the usual ones. Some examples of where this earns its keep: * Every product tagged `sale` opens with "When does this deal end?" and "Can I return sale items?" * Your supplements collection opens with "How do I take this?" and "Can I stack this with other products?" * One hero product gets bespoke questions tied to its launch campaign. You'll find **Suggestion sets** in the placement editor on the **Launch** page, below the suggestion mode picker. ## Creating a set Click **Add suggestion set** and choose what the set targets: * **Collection.** Matches any product in a Shopify collection you pick. * **Tag.** Matches any product carrying a tag you pick. * **Specific products.** Matches only the exact products you search for and select. Then add the suggestions for that set, the same way you'd add fixed chips. Something like "What sizes are available?" works as a template: short, tappable, in the shopper's voice. Save the placement and the set is live. ## How matching works Suggestion sets apply on product pages, because matching is based on the product the shopper is viewing. When a product matches more than one set, the set higher in your list wins, so put your most specific sets first: a set targeting one exact product above a set targeting its whole collection. New products join automatically. If you add a product to the "Bestsellers" collection in Shopify tomorrow, it picks up the Bestsellers suggestion set after the next catalog sync, with no changes needed in Anagram. On pages where no set matches, including non-product pages, the placement falls back to its normal Auto or Fixed suggestions. ## Requirements Suggestion sets need a connected catalog, since the collections, tags, and products come from your Shopify sync. If your catalog isn't connected yet, the editor shows a **Connect a catalog** link that takes you to [Brain](/brain/knowledge#catalog). ## Suggestion sets are per placement Each placement has its own suggestion sets. Usually that's what you want: your product-page placement carries the product-specific sets, and your homepage placement doesn't need any. If you run the same sets on two placements, you'll add them to each. # Onboarding Source: https://docs.anagram.ai/onboarding What happens when you first sign up, and what Anagram sets up for you automatically. The first time you sign in, Anagram walks you through a short setup wizard before dropping you on your project home page. It takes a couple of minutes, and a few of the answers matter more than they look, so here's what each step does. ## The setup wizard Enter your store's web address. This one is worth getting right, because Anagram uses it in three places: * **Placement previews.** The Launch page screenshots your real pages so you can see the agent on your actual homepage and product pages. * **Web search.** By default, the agent answers questions using pages on this domain. * **Style.** Anagram scans the site for your colors and fonts and pre-fills the agent's [Style](/launch/style) settings to match your brand. Your domain can't currently be changed from the Settings page. If you entered the wrong one, email [support@anagram.ai](mailto:support@anagram.ai) and we'll fix it. Pick the platform your store runs on: Shopify, Webflow, WordPress, Squarespace, and so on. If you pick Shopify, you'll get an extra step to connect your store right away. Just for us. Answer and move on. Enter your store's `myshopify.com` subdomain and click **Connect**. This installs the Anagram app and starts syncing your product catalog, which is what lets the agent recommend products and answer questions about them. Two things to know: * The field wants your **internal Shopify subdomain**, the one ending in `.myshopify.com`, not your public domain. Find it in Shopify admin under **Settings → Domains**. * You can click **Skip this step** and connect later from [Brain](/brain/knowledge#catalog). Nothing is lost by skipping; the agent just won't know your products until you connect. ## What Anagram sets up for you After the wizard, a few things are already working before you touch anything: * **Web search is on.** The agent can answer from your website's pages immediately. This is also why the "Knowledge added" step on your launch checklist may already be checked when you first arrive. * **Your brand style is pre-filled.** The colors and fonts from the domain scan land in the Style tab. Check them; the scan is good but not psychic. * **Your catalog is syncing**, if you connected Shopify. The first sync can take 5 to 30 minutes depending on catalog size, and you'll get a notification in Anagram when it finishes. What Anagram does not do is write your agent's brain for you. Rules, skills, and added knowledge start empty, on purpose. The [quickstart](/quickstart) picks up from here. ## Inviting your team You don't have to do this alone. Open the project switcher (your project name in the sidebar) and choose **Invite to project**. Type or paste email addresses, and each person gets an invitation email. Invited teammates skip the setup wizard entirely and land straight on the project, with the same access you have. # Plans and billing Source: https://docs.anagram.ai/plans-and-billing What's free, what needs a plan, and how the trial works. ## What's free to do Everything up to the moment your agent goes live on your storefront. You can complete onboarding, connect Shopify, build out your agent's [Brain](/brain/knowledge), create and style [placements](/launch/placements), and chat with the agent in preview as much as you like, all without a plan. The paywall sits at exactly one spot: copying the embed snippet. When you click **Launch**, Anagram asks you to start a plan before handing over the code that puts the agent on your site. This is deliberate. You should know exactly what your agent sounds like and looks like before you pay anything. ## The free trial Every Site Agent plan starts with a 7-day free trial. Click **Launch**, choose a plan, enter payment details through our checkout (handled by Stripe), and you're launched. You won't be charged until the trial ends, and you can cancel during the trial. ## How plans are structured Site Agent pricing is based on engagements. An engagement is a shopper who actually talks to the agent by typing a message or tapping a suggested question; someone who just sees the widget doesn't count. It's the same definition used in your [Analytics](/analytics/overview), so you can see exactly what you're using. Plans come in a few shapes: * **Pay as you go**, with no monthly fee and a per-engagement price. * **Monthly plans** that include a set number of engagements, at Base, Pro, and Growth volumes. Yearly billing is discounted. * **Enterprise**, for high-volume brands. Contact us through the pricing page. Current prices are on the plan picker inside Anagram, on your project's subscribe page. AI Visibility is a separate Anagram product with its own plans. Subscribing to one doesn't unlock the other. ## After checkout You'll come back to Anagram with your subscription active, usually within a few seconds. If you see an "Activating Site Agent" screen, that's Stripe confirming the payment; it resolves on its own. Then click **Launch** again and the snippet is yours. From there, follow [Add to your site](/launch/add-to-your-site). # Quickstart: launch your agent Source: https://docs.anagram.ai/quickstart Go from empty project to a live agent on your storefront. When you open your project in Anagram, the home page shows a **Launch checklist** with four steps. This guide walks through each one. It picks up right after the [onboarding wizard](/onboarding); if you connected Shopify there, you're ahead already. You don't need a developer for any of it, though pasting the final code snippet is easier if you have someone who edits your theme. Your agent is only as good as what it knows. Go to **Brain** and connect your knowledge sources: * **Catalog.** Click **Connect Shopify** and enter your `myshopify.com` domain. Anagram syncs your products daily, so the agent can recommend items and answer questions about them. See [Shopify](/shopify) for details. * **Web search.** Leave this on and the agent can pull answers from your website, like shipping and returns pages. * **Added knowledge.** Add facts the agent can't find anywhere else, like "Our candles are made from soy wax" or your holiday shipping cutoff. You can also add [Rules](/brain/rules) and [Skills](/brain/skills) now, but they aren't required to launch. Most brands launch with just knowledge and tighten behavior later. Use the preview chat on your home page and ask the questions your customers actually ask. "Do you ship to Canada?" "What's your best moisturizer for dry skin?" "Can I return sale items?" If an answer misses, go back to Brain and add the missing fact as a knowledge entry, or add a rule to correct the behavior. When you're happy, click **Mark as ready**. A placement is where and how the agent appears on your site. Go to **Launch**, click **Add placement**, give it a name, and pick a form factor: * **Center bar** sits in the middle of the page like a search bar and opens into a chat drawer. This is the default and a strong starting point. * **Floating button** is the familiar chat bubble in the corner. * **Custom trigger** lets a button already on your site open an Anagram panel. * **Embedded panel** and **Embedded inline** render inside a specific page, like a dedicated "Ask us anything" section. Then set the [conversation starter](/launch/conversation-starters): the greeting and suggested questions shoppers see before they type. **Auto** mode is the default and generates suggestions from whatever page the shopper is on. Click **Launch**. If you're not on a plan yet, this is where Anagram asks you to start one; every plan begins with a 7-day free trial, and everything up to this point has been free. See [Plans and billing](/plans-and-billing). Then copy the code snippet. It looks like this: ```html theme={null} ``` Paste it into your site. For Center bar, Floating button, and Custom trigger, anywhere before the closing `` tag works because the panel floats above the page. Custom trigger does not render its own launcher—dispatch `anagram:open` from your button to open it. For embedded placements, paste it exactly where you want the widget to appear. See [Add to your site](/launch/add-to-your-site) for Shopify-specific instructions. That's it. Once a shopper sends their first message, you'll see it in [Analytics](/analytics/overview). Changes you save in Anagram go live right away. There is no separate publish step for your agent's brain or placements. The preview chat is where you test edits before saving them. # Shopify Source: https://docs.anagram.ai/shopify Connect your Shopify catalog so your agent can recommend and answer questions about your products. Anagram connects to your Shopify store to sync your product catalog. Once connected, your agent can recommend products, answer questions about them, show product cards in chat, and attribute sales back to conversations in [Analytics](/analytics/overview). ## Connecting 1. In Anagram, go to **Brain** and open the Catalog view. 2. Click **Connect Shopify**. 3. Enter your `myshopify.com` domain. You can find it in your Shopify admin under **Settings → Domains**. 4. Approve the install. Connecting installs the Anagram app on your Shopify store. You don't need to manage anything in the Shopify admin afterward; all configuration happens in Anagram. ## How syncing works Anagram syncs with your Shopify catalog automatically every day. If you've just changed products and don't want to wait, open the Catalog in Brain and click **Sync now**. Syncs can take a few minutes depending on how many active products you have. Anagram notifies you when a sync finishes. ## What gets synced Product information including titles, descriptions, prices, tags, collections, and metafields. The agent uses all of it, so richer product data in Shopify means better answers. Tags and collections also power [suggestion sets](/launch/suggestion-sets), which pin specific suggested questions to groups of products. Anagram also picks up your store's default currency and uses it on product cards shown to shoppers. The agent can only be as accurate as your catalog. If descriptions are thin or sizing details live only in an image, consider moving that information into the product description or metafields. Shoppers will start asking the agent about it either way. # Troubleshooting Source: https://docs.anagram.ai/troubleshooting The most common places people get stuck, and how to get unstuck. Symptoms first, fixes second. If your problem isn't here, email [support@anagram.ai](mailto:support@anagram.ai) with your project name and what you were doing. ## Setup and Shopify ### Shopify won't connect The connect step wants your internal Shopify subdomain, the one ending in `.myshopify.com`, not your public store URL. Find it in Shopify admin under **Settings → Domains**. If you see "Failed to connect to Shopify. Please check your store domain and try again," this is almost always why. You also need to be logged into Shopify as a user with permission to install apps. ### My products aren't showing up yet The first catalog sync takes 5 to 30 minutes depending on how many products you have. Anagram notifies you when it's done. Check progress by opening the Catalog in **Brain**. If you get a "Shopify sync failed" notification saying your connection is no longer authorized, the app's access was revoked on the Shopify side (this happens if the app is uninstalled or the connecting staff account is deactivated). Reconnect Shopify from the Catalog and sync again. ### Products look wrong or outdated in chat The agent sees your catalog as of the last sync. Fix the product in Shopify, then open the Catalog in Brain and click **Sync now** rather than waiting for the daily sync. ### I entered the wrong domain during onboarding Your domain powers placement previews and web search, and it can't currently be edited from Settings. Email [support@anagram.ai](mailto:support@anagram.ai) and we'll change it for you. ## Building the agent ### "Knowledge added" was already checked and I didn't do anything Not a bug. Web search is on by default, so your agent can already answer from your website's pages the moment you arrive. The checklist counts that as knowledge. It's still worth connecting your catalog and adding brand facts; see [Knowledge](/brain/knowledge). ### The agent gave a wrong or off-brand answer Work out which of the three it is, because each has a different fix: * **It didn't know a fact, or made one up.** Add the fact as a knowledge entry in [Brain](/brain/knowledge). Ask yourself where the agent could have found the right answer; if the answer is nowhere, that's the gap. * **It knew the facts but behaved wrong**: promised a delivery date, recommended a competitor, got the tone wrong. Add a [rule](/brain/rules), usually a Never rule. * **It fumbled a multi-step task** like size finding. Write or tighten a [skill](/brain/skills). Test the fix in the preview chat before saving. Unsaved edits apply to the preview automatically, with a "Testing unsaved changes" badge so you know you're in test mode. ### My preview conversations are cluttering my analytics They aren't. Preview chats in Anagram never count as engagements and never appear in your analytics. Only real shoppers on your live site do. ## Placements and previews ### The Launch page won't show a preview of my site Placement previews screenshot your live site, which requires the production domain from onboarding. If you skipped it or it's wrong, previews can't load; email support to set the domain. If you see "Preview is busy right now," it's a temporary rate limit; wait a moment and hit **Refresh preview**. The preview not loading doesn't affect your live agent. It's only the picture in the editor. ### The agent isn't appearing on my live site In rough order of likelihood: 1. **Wait a few minutes.** Placement settings are cached briefly, so a brand-new placement or a just-saved change can take a few minutes to appear on your storefront. 2. **Check the snippet is actually in your published theme.** On Shopify it's easy to paste into a draft theme instead of the live one. 3. **Check the placement still exists in Anagram.** A deleted placement's snippet renders nothing, silently. 4. **Scroll down.** Center bars with **Reveal after one page scroll** turned on stay hidden until the shopper scrolls. 5. **Check the snippet wasn't modified.** It should be one line, exactly as copied, including the `defer` attribute. ### My custom trigger does nothing Custom trigger placements intentionally render no Anagram button. Keep the placement snippet before ``, then dispatch `anagram:open` from your own button with the placement ID: ```js theme={null} window.dispatchEvent(new CustomEvent('anagram:open', {detail: {placementId: 'your-placement-id'}})) ``` ### Suggestions aren't showing, just the greeting If the placement uses **Auto** suggestions, the very first visit to a page Anagram hasn't seen yet shows only the greeting while suggestions generate in the background. Reload the page and they should be there. If it persists across visits, check that the placement's suggestion mode is what you expect in the [placement editor](/launch/conversation-starters). ### My suggestion set isn't kicking in Three things to check, in order: 1. Suggestion sets match on **product pages only**, based on the product being viewed. They won't fire on your homepage or collection pages. 2. The set needs a **connected catalog**, since collections and tags come from your Shopify sync. 3. If the product matches multiple sets, the one **higher in your list** wins. Reorder so the specific set sits above the broad one. ### I picked "Show stores" and it won't work The Show stores opener needs two things: an **Embedded inline** placement (it's not offered on other form factors) and the **Show stores** action enabled with locations added on the [Actions](/actions/overview) page. The placement editor links you there if it's not set up. ## Launching and billing ### Clicking Launch shows a pricing screen instead of the code That's the paywall. Configuring and previewing the agent is free; putting it live on your site requires a plan, and every plan starts with a 7-day free trial. See [Plans and billing](/plans-and-billing). ### I'm stuck on "Activating Site Agent" after checkout This screen means we're waiting for Stripe to confirm the subscription, and it normally resolves within seconds. If it doesn't, refresh the page. Your payment went through if Stripe showed a confirmation; if the subscription still doesn't activate after a few minutes, contact support rather than checking out again. ## Analytics ### Engagements are showing but assisted sales are zero Assisted sales need your Shopify connection, which is how orders get linked back to conversations. If Shopify is connected and you're still seeing zero, remember that a sale counts only when the shopper purchases within the attribution window after chatting, so sales naturally lag conversations. Give a new launch at least a week before judging. The [Analytics page docs](/analytics/overview#anagram-assisted-sales) explain exactly how attribution is counted. ### I see conversations but no engagement count Only messages from real shoppers on your live site count. Your own preview chats in Anagram are excluded by design.