Skip to main content
Each prompt is written the way you would type it. Under it: what comes back, what it costs, and which capabilities it uses. Use an active workspace for content tasks. If you have not connected Surfer yet, start with the Quickstart.
For the six core workflows, ask for a skill instead of prompting each step.

Before you start

Four things make every prompt below more reliable.

Locations and language

The location you choose, together with the keyword, sets the SERP Surfer analyzes and the language of the guidelines.
  • Use a location name exactly as Surfer lists it, such as United States. Surfer does not reject a misspelled location. A Content Editor falls back to United States, and a workspace stores the misspelling, which breaks its SERP work later.
  • A location with a language suffix, such as Canada - FR or Switzerland - DE, uses that language.
  • A location without a suffix uses Surfer’s default language for that country. For example, India uses Hindi while India - EN uses English, and Canada uses English while Canada - FR uses French.
The full list is public and needs no API key: open https://app.surferseo.com/api/v1/locations or see List supported locations.

Provide sufficient context

Name the workspace and the target keyword in each prompt, or paste a link from the Surfer app. Without either, the assistant has to guess or ask. Your assistant can find a workspace or a Content Editor by name and keyword. That takes extra tool calls, and it can pick the wrong editor when several share a keyword. A link from the Surfer app carries the ids, so the assistant goes straight to the right object.
The assistant lists your workspaces and Content Editors to find the match. If several editors share the keyword, it asks you which one.
Remember to give your assistant sufficient outside context. For example, when optimizing a page you can provide:

Credits and limits

Each prompt below that spends a credit says so. Credits and limits lists every action that charges and the limits that apply.

Ask for retry keys when you create in bulk

Creating a Content Editor, a content template, or a custom voice accepts a retry key (an idempotency key). If a create times out and your assistant retries with the same key, Surfer returns the original result instead of creating and charging for a duplicate. Keys expire after 24 hours. Your assistant does not always send a retry key on its own. When you create several Content Editors in one request, ask for one key per editor:

Content creation

Choose how you want the article written.
  1. Surfer creates the Content Editor for one Content Editor credit and analyzes the SERP.
  2. Your assistant reads the guidelines and facts, then writes the draft itself.
  3. After each revision, it replaces the editor’s content and waits for the recalculated scores.
You see the score of every revision.Tools: Content Editors, guidelines.

Optimization

Load an existing page into a Content Editor, see what it is missing, then fix it with your assistant or with Auto-Optimize.
Surfer creates the Content Editor for one Content Editor credit. Once it has finished analyzing, you get:
  • How often each recommended term appears in your draft, next to how often the top-ranking competitors use it, scaled to your draft’s length.
  • The AI Search score, the facts your draft already covers, and the facts it lacks. Each fact carries its source URL and where that URL was found: the SERP, Google AI Overviews and AI Mode, Gemini, OpenAI, or Perplexity.
  • Whether the introduction sets expectations, names the audience, explains why the topic matters, and answers the main question up front.
Then have your assistant revise the draft and check every revision:Each saved revision replaces the whole document body and starts a score recalculation. Revising spends no credit.Tools: Content Editors, guidelines.

AI Tracker

These prompts need an AI Tracker project in the workspace; your assistant lists the projects to find it. What every read shares:
  • Refresh: reports refresh once a day.
  • Window: choose a supported report period. The assistant can tell you which dates have reports.
  • Model families: Google AI Mode, Google AI Overviews, OpenAI, Perplexity, or Gemini. The summary covers every family at once; the other reads cover one family or all of them combined.
You get the mention rate, average position, and presence score for each AI model family over a 30 day window. A combined row covers all of them. For each model family, you get the brands the AI answers mention, sorted by presence score. You can also compare how many cited webpages mention the competitor and how many mention both brands. These are different measures: one describes the AI answers, the other describes the source pages. You get one row per cited URL, sorted by how often it is referenced, with a flag for whether the crawled webpage mentions your brand. An unavailable flag means Surfer does not have that information, not that the brand is absent. The assistant keeps the rows on your domain. You get the daily mention rate, average position, and presence score across the 30 day window, oldest first. Days without a report are skipped, so the series can be shorter than the window.
  1. Surfer returns cited source URLs, each flagged by whether the page mentions your brand.
  2. Your assistant opens each candidate page and quotes where it mentions the competitor.
  3. It drafts the email in the chat or with your other connected tools.
Over MCP, Surfer flags only whether each source mentions your brand. The Surfer app shows a snapshot of competitors mentioned under a given source URL. Your assistant should always check each page live itself. That step needs web browsing in your client, and the quotes are how you verify it. Tools: AI Tracker.

Recommendations

Surfer recommends existing pages to optimize, content ideas to write, and pages where your brand can earn a mention in AI answers. Each list is sorted by score, highest first.
Pages to optimize come from Content Audit. Each carries its URL, its keyword, and the keyword’s average Google position over the last 30 days next to the 30 days before.For each page that has not been started, Surfer opens the page’s own Content Editor. That is the same action as the Optimize button in the app.
  • It costs one Content Editor credit, unless that editor was already paid for.
  • You get each editor’s SEO Guidelines: structure targets, competitors, recommended terms, and topics.
To continue, follow Optimization.
Tools: workspaces and recommendations, guidelines, AI Tracker.

Workspace management

Create a workspace, then set its brand knowledge, templates, and voices.
Spell the location exactly as Surfer lists it. A workspace keeps a misspelled location as written, and its SERP work fails later.
Locations and language explains how the location sets the language. Creating a workspace needs:
  • An organization owner or admin.
  • A name.
  • The site URL.
  • A location.
What happens, in order:
  1. Setup runs in the background and your assistant checks the workspace until it is ready for activation.
  2. Your assistant activates the workspace, making it available for brand reads and content work.
  3. You get the generated brand knowledge to review. Brand analysis is skipped on plans without brand knowledge.
Your assistant reads the current brand knowledge and writes the revised version back as Markdown. Only what you change is written, and the brand’s site URL cannot be changed this way. Surfer stores the sections verbatim as the template’s reference text and learns the voice’s style from the sample articles. Ask to make either one the workspace default. Your assistant checks the reference text against the tools’ current input requirements. Tools: workspaces and recommendations, templates and voices.

Reporting

These prompts only read: Content Editor lists, content scores, recommendations, AI Tracker reports, and Search Console data. None of them consumes a credit. Surfer does not schedule reports; if your client can run a saved prompt on a schedule, these are the prompts to schedule. You get every Content Editor created since the date you name in the workspaces you belong to, each with:
  • Its main keyword.
  • Its state: scheduled, executing, completed, or failed.
  • Its SEO, AI Search, and total scores.
Name a date range and workspace to keep the report focused. Without a workspace filter, the list spans every workspace you are a member of in the organization. The list already carries each editor’s scores, so your assistant filters it. For an editor whose score is missing or still recalculating, it reads that score on its own. You get both kinds; ask for more to go deeper.
  • Pages to optimize carry their average position over the last 30 days and the 30 days before, so position drops stand out.
  • Ideas to write carry search volume and difficulty.
  • You get a daily trend per AI model family, one family at a time, over a 90 day window.
  • The mention gap reports, per competitor, how many cited webpages mention them and how many mention both brands.
Your assistant queries the workspace’s Search Console property once per month, grouped by page, and compares the two lists. Results come straight from Google, most clicks first. The workspace needs Search Console connected in the Surfer app. Tools: Content Editors, workspaces and recommendations, AI Tracker, Search Console.

Tips

  • Name the workspace when you have more than one, or keep a standing instruction in your client about which workspace to use. Otherwise the assistant lists your workspaces and asks.
  • Choose which outline you want to review. The SERP outline is available after editor analysis. Reviewing an AI Article outline requires starting generation first, so on plans with separate AI Article credits the credit is already reserved before approval.
  • Chain with your CMS’s own MCP server. Your assistant reads the finished document as Markdown or HTML and hands it to the CMS server to publish in the same conversation. No Surfer tool publishes anywhere.