Turn Algolia zero-result searches into Intercom Help Center drafts

Every Monday morning, last week's dead-end searches on your site become draft help articles sitting in Intercom, ready for a human to review and publish.

Agentic Task
AlgoliaIntercomCustomer SupportMarketingContent GenerationFeedback Triage
PromptCreate

Every Monday at 9am, turn last week's Algolia zero-result searches directly into draft Intercom Help Center articles so support content actually closes the gaps customers keep hitting.

Trigger: cron, every Monday at 09:00 in the workspace timezone.

Step 1. Call Algolia's Analytics: Top Searches with No Results for the trailing 7 days on the configured index. Pull the search term and the search volume (count) for each entry. Keep only terms whose volume is at or above a configurable threshold (default 5 searches in the week).

Step 2. Skip anything that looks like personal information (email addresses, phone numbers, order numbers, names that read like a customer identity) or an obvious misfire (single characters, random keyboard mashing, gibberish, adult or abusive language). Do not draft an article for these.

Step 3. Cluster near-duplicate queries into a single group before drafting. Typos, plurals, word order swaps, and small phrasings of the same underlying intent become one cluster (for example "refund policy", "refund policys", "how to refund", and "can i get a refund" are one cluster). Pick the clearest phrasing as the cluster label. One draft per cluster, never one article per typo.

Step 4. Call Intercom's List All Articles and page through the full library. For each cluster, compare against existing article titles and summaries and skip the cluster if it is already covered by a live or draft article. Be conservative: if you are unsure whether it is truly covered, keep the cluster and draft the new article anyway.

Step 5. For each genuinely new cluster, draft a full help article with these fields: a clear customer-facing title, a short intent summary (one to two sentences on what the customer is trying to do and what the article answers), three to five subheadings that structure the answer, placeholder body copy under each subheading that sketches what the human author should fill in, and a small set of suggested tags derived from the cluster keywords.

Step 6. For each drafted article, call Intercom's Create an Article with state set to draft. Never publish. Include the title, the intent summary as the description, and the subheadings plus placeholder body copy as the article body. Attach the suggested tags. Draft-only publishing is a hard rule so a human always reviews before anything ships to customers.

Configurable knobs: the Algolia index to analyze, the minimum weekly search-volume threshold, the day and time the workflow runs, an optional Intercom collection or author to assign drafts to, and any custom skip list of query patterns (for example the company's own brand terms if you do not want articles drafted for them).

Output: a short summary at the end of the run listing each new draft created (title and cluster of queries it covers), each cluster skipped as already covered, and each cluster skipped as personal information or a misfire, so the support lead can spot-check the run.

Additional information

What does this prompt do?
  • Pulls last week's zero-result searches from your Algolia-powered site search every Monday morning
  • Groups near-duplicate searches (typos, plurals, rephrasings) so you get one article per real customer question, not one per typo
  • Checks your existing Intercom Help Center so it only drafts articles for gaps you have not already answered
  • Writes a full draft article with title, intent summary, subheadings, placeholder body, and suggested tags, then files it in Intercom as a draft for human review before publish
What do I need to use this?
  • An Algolia account with analytics enabled on the search index that powers your site
  • An Intercom workspace with the Help Center turned on and permission to create articles
  • A rough idea of the minimum weekly search volume that makes a topic worth an article (the workflow uses 5 by default and you can change it)
How can I customize it?
  • Change the day or time the workflow runs, or make it fortnightly instead of weekly
  • Raise or lower the minimum weekly search-volume threshold so more or fewer topics turn into drafts
  • Add a skip list for query patterns you never want drafted (brand terms, internal-only pages, seasonal noise)
  • Point new drafts at a specific Intercom collection or default author so they land where your support team already reviews new content

Frequently asked questions

Will anything be published to customers automatically?
No. Every article is created in Intercom as a draft. A human on your team still opens it, edits the body copy, and decides when to publish. Draft-only is a hard rule in this workflow.
How does it avoid drafting an article we already have?
Before drafting anything, it lists every article in your Intercom Help Center and compares each cluster of zero-result searches against existing titles and summaries. Anything that looks covered is skipped, and the run summary tells you what was skipped and why.
What about typos and misspellings creating a dozen near-duplicate drafts?
Similar queries are grouped into one cluster before drafting. Refund policy, refund policys, how to refund, and can i get a refund all become a single draft, not four.
Does this work with any site search or only Algolia?
This particular workflow reads from Algolia's search analytics. If your site search runs on something else, the same pattern can be adapted, but the connection here is Algolia and Intercom.
What if a search looks like private information, like an email address or an order number?
Queries that look like personal information or obvious misfires (random characters, keyboard mashing, abusive language) are filtered out before drafting, so nothing sensitive ends up in a help article title.

Turn dead-end searches into help content your team actually ships.

One workflow, one draft article per real gap, sitting in Intercom every Monday morning ready for review.