Answer engine optimization

How to get cited by Google AI Overviews using Hermes

Google AI Overviews does not recall your brand from memory. It retrieves a handful of pages and writes its answer from them, so getting cited means getting onto those pages, in a form it can lift. With Hermes, the workflow is: find the buyer questions where Google AI Overviews names a competitor instead of you, look at which URLs it keeps citing for those questions, and publish a page that out-answers them - leading with the answer, structured as a table or list, and honest about where competitors genuinely win. Then re-measure a few weeks later, because publishing without re-measuring is guessing.

How Google AI Overviews actually decides who to name

AI Overviews are generated from pages that already rank, so the AI Overview is not a separate channel you can buy your way into - it is a summary layer on top of the search results you either earned or did not. The pages it cites are drawn heavily from the top of the conventional results.

What moves the number on Google AI Overviews

1. 1Rank on page one for the query. There is no shortcut around this one: the Overview summarises the pages that are already there.
2. 2Write a passage that answers the query in a single, self-contained chunk. Overviews are assembled from extractable passages, and the page that hands one over gets the citation.
3. 3Target the questions where the Overview is currently thin or hedged. Where Google's summary is weak, a genuinely better page displaces it quickly. Where it is already comprehensive, you are fighting for scraps.

Doing it with Hermes

An open agent runtime from Nous Research, with a skill system that lets you hand the agent a playbook rather than a prompt. The choice when you want the loop to run unattended and you would rather install a capability than describe one.

1. 1Add the repo as a skill source and install: `hermes skills tap add gsmmediaro/fulcru`, then `hermes skills install fulcru`. Hermes scans third-party skills before installing and shows you the verdict, so you can read what you are about to run.
2. 2Register the Fulcru MCP server in your Hermes `config.yaml` under `mcp_servers`. The skill teaches the agent the playbook; the MCP server gives it the measured data to run the playbook against.
3. 3Ask the agent to audit your domain. It builds the buyer question set, runs each question, and records who gets named and which URLs keep appearing across answers. Those recurring URLs are the pages the engines actually read in your category.
4. 4Have it draft the page for the worst gap, then read the draft yourself before it goes anywhere near your domain. Publish, then let the agent re-run the same set on a schedule so you are comparing against a fixed baseline rather than a moving one.

What this will not do

The part everyone skips

Re-measuring. A published page that you never check is a belief, not a result. Run the same question set again a few weeks later and compare: were you named in 2 of 10 answers before, and 5 of 10 after? That number is the only thing that tells you the work landed - and when it does not move, that is information too. It usually means the answer set is dominated by a source you have not gotten onto yet.