Answer engine optimization

How to get cited by Gemini using Hermes

Gemini 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 Gemini 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 Gemini actually decides who to name

Gemini grounds its answers in Google Search results. That makes it the engine where classic SEO still carries the most weight - if you are already surfacing in Google for the query, you are in the candidate set Gemini writes from. The grounding step then decides which of those candidates it actually names.

What moves the number on Gemini

1. 1Rank in Google for the question first. Gemini's grounding pulls from the same index, so traditional SEO is not dead here - it is the entry ticket to the room where the AI answer is written.
2. 2Structure the page so the answer is liftable: headers that match the question, a summary that stands alone, schema markup where it fits. Grounding rewards pages a machine can parse confidently.
3. 3Earn mentions on the sites Google already trusts for the topic. Grounding disproportionately names entities that appear across multiple retrieved sources, so being named on three pages beats owning one.

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.