The prompt
Paste this into Claude, ChatGPT, Cursor, or any MCP-compatible client connected to your Bourd account. Replace the highlighted placeholders with your own values before sending.
In the {{ workspace name }} workspace, find every prompt where {{ your domain }} is cited in the source list but {{ your brand }} isn't mentioned in the answer text on any model. List them with response counts, then ask me which one to focus on. Wait for my answer before continuing.
For the prompt I pick, compare {{ your domain }}'s page against the other cited pages and figure out why {{ your brand }} is being passed over for the mention. Then write a brief that fixes it.
Steps:
1. List the cited URLs across all models and the competitor brands mentioned in the answer. Note which cited URLs belong to brands that get mentioned.
2. Pull {{ your domain }}'s page and the top three or four other cited URLs through Bourd's path extraction.
3. Compare {{ your domain }}'s page against the cited pages whose brands get mentioned. Form a hypothesis for why {{ your brand }} is being passed over: coverage gaps, less direct claims, weaker structure, vocabulary mismatch with the prompt, or some combination. Cite specific differences from the page content.
4. Based on the hypothesis, recommend one of two paths:
- Rewrite {{ your domain }}'s page to address what's missing
- Write a new page if {{ your domain }}'s page is answering a different question than the prompt is asking
Default to the rewrite if it's plausible. State which path you're proposing and why.
Brief format:
- Proposed H1
- H2 outline
- Unique angle in one sentence
- Three to five questions the mentioned-brand pages answer well that {{ your domain }}'s page doesn't (or under-answers)
Stop at brief level. The writer drafts from there. 11 placeholders to fill in. The agent will call: list_prompts, list_prompt_responses, list_citations, and 1 more.
What this workflow does
Picks a prompt where models cite your page but don't mention your brand in the answer. Reads your page and the top three or four pages cited alongside it. Compares them to find what the others cover that yours doesn't. Returns a one-page brief: a proposed H1, an H2 outline, a one-sentence angle, and three to five questions the other pages answer better than yours. You edit it and hand it to a writer.
Why mentions matter more than citations
A citation puts your URL in the source list. A mention puts your brand in the sentence the buyer reads. Buyers read the sentence and skip the list, so citations are a tactical input and mentions are the outcome. Use the citation data to write the page that earns the mention, then track mentions to confirm it landed.
Why it works
Most content-gap tools stop at "these are the URLs." This one reads the pages. Bourd extracts clean text from every cited page, including yours, so the agent compares them side by side instead of scraping live URLs. Pages Bourd couldn't extract (paywalled, login-walled, robots-blocked) are flagged so the writer knows where the brief has thin sourcing.
What a good brief looks like
One page, with:
- A proposed H1
- Three to six H2s
- A one-sentence angle
- Three to five questions where other cited pages answer better than yours, each naming the page that falls short (including yours when it applies)
- A recommendation to rewrite your cited page or commission a new one, with the reasoning
Anything longer is the writer's job. If the agent returns four pages of outline, push back and ask for the cuts. The writer needs room to write.
Common failure modes
Three patterns to watch for. The agent picks a prompt with two or three responses and treats it as representative; constrain it to prompts with at least 20 responses or the brief targets noise. The agent invents an angle that sounds related but doesn't fill a real gap; tell it to source the angle from a question the existing pages literally don't answer, and to cite the question's absence on each page. The agent recommends a new page when a rewrite would do; default to the rewrite if your page is on-topic, and only escalate when it's answering a different question than the prompt is asking.
How to extend it
- Ask for three brief variants at different intents (informational, comparison, decision-stage) so a single session covers a cluster instead of one query.
- Have the agent draft the meta title and description in the same turn.
- Chain into a Notion or Google Docs MCP to land the brief in the writer's workspace.
- Tag the source prompt so you can re-check whether your brand earns a mention 30 days after the page ships.
When to skip it
If your URL isn't cited for the prompt at all, use the uncited-prompt brief instead. With nothing of yours in the cited set, the brief has to be scoped from competitors alone. If the prompt has fewer than 20 responses, the cited URL set isn't stable enough to brief against. Wait for response volume to build, or pick a higher-traffic prompt in the same cluster.
Tools the agent calls
The agent picks from these 4 Bourd MCP tools based on the prompt. You do not call them directly.
list_prompts list_prompt_responses list_citations get_path_extraction
Pairs with
MCP agents chain across servers. Add these alongside Bourd and the same prompt can hand output straight to the tools you already work in.
Notion Google Docs Linear