A workflow published on GitHub gives search engine optimisation teams a ready-made way to expand a single seed keyword into a broader list of related phrases, keyword ideas and autocomplete suggestions. The project, part of the cuebicai n8n-workflows collection, combines the workflow automation tool n8n, the Airtable database and the YepAPI keyword data service, and stores the output in Airtable for later review.
What the workflow does
The repository describes the workflow as a tool for long-tail keyword research. Long-tail keywords are longer, more specific search phrases. They usually attract narrower audiences than broad terms, and content teams often use them to plan articles that answer particular questions. Finding them by hand across several tools is slow, which is the gap this workflow is meant to close.
According to the GitHub listing, the process starts when a seed keyword research request arrives through a webhook. From there, the workflow retrieves the matching seed keyword record from Airtable, checks its research status and prepares the keyword for analysis. Once the research is complete, the results are written back to Airtable and the original seed record is updated.
How the process runs step by step
The workflow follows a clear sequence, which makes it easier to audit and adapt. The main stages are:
- Receive the research request through a webhook and load the matching seed keyword record from Airtable.
- Check the current long-tail research status and mark the record as in progress.
- Pass the seed keyword to three separate discovery paths in YepAPI.
- Split each response into individual items and standardise the fields so that all paths produce the same structure.
- Store the resulting keyword records in Airtable and update the seed record with the outcome.
Because each stage is a separate node, a team can inspect the output of any step if something looks wrong.
Three ways to discover keywords
Related keywords
The first path asks YepAPI for keywords related to the seed term. The returned collection is split into single items, and a preparation step maps the fields into the format used for storage.
Keyword ideas
The second path requests additional keyword ideas connected to the seed keyword. As with the first path, the response is separated into individual entries and then standardised before it reaches Airtable.
Autocomplete suggestions
The third path is the most indirect. The workflow retrieves autocomplete suggestions, which are the phrases a search engine offers as a user types. These suggestions are then gathered into a single structure and sent through a further YepAPI request that returns keyword data for each one. The repository presents this chain as a way to discover variations that users actively type, rather than only those a tool classifies as related.
Where the data lands in Airtable
The workflow writes its results to Airtable records that include the company associated with the research, the original seed keyword, a competition metric, a keyword difficulty metric and, where the API returns them, the keyword itself. The source also lists fields for search volume and cost per click, which are used in the broader Airtable interface. The repository notes that the exact metrics depend on the YepAPI endpoint, the request parameters and the availability of the underlying data.
The same Airtable base is also designed to support a later subtopic stage. Fields for initiating subtopic research, storing selected subtopics and tracking their status sit alongside the keyword tables, which suggests the project is meant to form one part of a larger content planning system.
Caveats before relying on the output
The repository is clear that the output is raw material rather than a finished shortlist. Keywords from the three paths can overlap, so the number of stored records should not be read as the number of unique opportunities unless deduplication has been applied. The README also suggests adding normalisation, source tracking and keyword intent clustering before the list is treated as a set of content targets.
Reliability is another consideration. The documentation advises teams to check how failed API requests and incomplete responses affect the research status, and to test the workflow with seed keywords that return very different numbers of results. It also recommends confirming that the status field is updated correctly, since a misconfigured status check could leave a record stuck in progress or skip work that is needed.
Why it matters for content planning
Keyword research tools have multiplied in recent years, but many SEO teams still move data between spreadsheets, dashboards and project boards by hand. A workflow that connects these steps can reduce repetitive work and give editors a consistent format to review. For smaller teams, the value lies less in any single metric and more in having a repeatable process that can be run again whenever a new topic is proposed.
Anyone considering the project will need an Airtable account with the right base and fields, a personal access token, and access to the relevant YepAPI endpoints. The setup guide also recommends testing each request separately before activating the workflow. With those steps in place, the repository offers a practical template for turning a single seed term into a structured, reviewable set of search opportunities.
Related: Free n8n Workflow Builds Local Business Leads from Google Places · n8n Workflow Parses Gmail Invoices Into Sheets With Slack Alerts
Comments (0)