Tutorial · April 27, 2026

Setup an AEO/GEO Agent with Hermes

One evening of work. $15 to $30 per month to run. An autonomous agent that runs your AEO/GEO loop daily and pings you only when something deserves attention.

TL;DR
Five steps. Install Hermes. Add MentionsAPI as an MCP server. Define the workflow. Schedule it and route alerts. Verify. By bedtime you have an agent that monitors brand visibility across ChatGPT, Claude, Gemini, Perplexity, AI Overviews, and Bing Copilot, with persistent memory and Slack alerts.

You have probably been doing AEO and GEO manually.

Run a query through ChatGPT. Eyeball whether your brand shows up. Copy the citation URLs into a spreadsheet. Repeat next week with a slightly different list. Wonder whether anything you did mattered.

That workflow does not scale past about ten queries. I know because I tried.

The fix is to build an AEO/GEO agent that does this automatically. Hermes Agent is the right tool for the job. Persistent memory, MCP support, multi-channel alerts, all the right primitives. This article walks through the full setup.

By the end you will have an autonomous agent that runs your AEO/GEO loop daily, stores the data, and pings you when something changes. Setup time is one evening. Running cost is around $20 to $80 per month depending on how many queries you track.

The problem with how teams do AEO and GEO today

Two patterns dominate, and both are bad.

Pattern one: people pay for SaaS tools. Otterly, Frase, HubSpot AEO, Siftly. These work fine but cost $50 to $200 per month per brand and lock you into their workflows. You cannot easily run custom analyses. You cannot modify the alert logic. You cannot add new query templates without their roadmap.

Pattern two: people do it manually with a spreadsheet. They run queries by hand once a week, paste results into a sheet, and try to spot trends. This works at small scale and falls apart fast. Past about fifteen queries, manual work eats your week.

The third option is to build an agent. Until April 2026 this was not really practical. The components were too immature.

Hermes Agent ships MCP OAuth 2.1 (April 8 release), persistent memory, and seventeen messaging gateways. MentionsAPI ships an MCP server that exposes brand monitoring as native Hermes tools. The combo makes the agent option finally feasible.

This is the third option. Build an agent that runs your AEO and GEO workflow on autopilot, costs less than the SaaS tools, and lets you change the logic whenever you want.

What the agent will do

Concrete output. Daily, the agent will:

  1. Run your priority queries through four AI engines (ChatGPT, Claude, Gemini, Perplexity) plus three search surfaces (AI Overviews, AI Mode, Bing Copilot).
  2. Extract whether your brand was mentioned, where in the response, and which URLs were cited.
  3. Compare today's results to yesterday's (using Hermes's memory).
  4. Alert you on Slack when something changes meaningfully (rank drop, new competitor, citation source change).
  5. Log everything for weekly summary.
This is the full AEO and GEO loop. It runs without you. It only interrupts you when there is something worth your attention.
Get the data layer first
Sign up for a MentionsAPI key and top up $10. The setup below assumes you have one in hand.

The five steps

Install Hermes Agent

Linux, macOS, or WSL2. One command:

install.sh
curl -fsSL https://raw.githubusercontent.com/NousResearch/hermes-agent/main/scripts/install.sh | bash

This installs Hermes globally and creates a config directory at ~/.hermes/. Inside it you will find config.yaml, the file you will edit next.

Verify the install with hermes --version. You should see something like v0.11.0 or later. The official quickstart at hermes-agent.nousresearch.com covers platform-specific gotchas.

Connect MentionsAPI as an MCP server

Open ~/.hermes/config.yaml. Add this block at the top level:

~/.hermes/config.yaml
mcp_servers:
  mentionsapi:
    url: "https://mentionsapi.com/mcp/sse"
    headers:
      Authorization: "Bearer YOUR_MENTIONSAPI_KEY"
    connect_timeout: 60
    timeout: 180
    tools:
      include:
        - check_brand
        - discover_queries
        - extract_brands
        - usage

Replace YOUR_MENTIONSAPI_KEY with your actual key from the MentionsAPI dashboard. The tools.include filter is optional. It limits which MentionsAPI tools Hermes sees. Fewer tools is usually better because it reduces token usage.

Save the file. In Hermes, run /reload-mcp. You should see a confirmation that mentionsapi connected and the tools were registered.

Define the AEO/GEO workflow

This is where you tell Hermes what the agent should do. In the Hermes interactive shell, type something like this (or save it as a system prompt):

hermes prompt
You are an AEO and GEO monitoring agent.

Daily at 09:00 UTC, run mentionsapi.check_brand for the brand "[YOUR_BRAND]"
against these prompts:
  - [prompt 1]
  - [prompt 2]
  - [prompt 3]
  - [prompt 4]
  - [prompt 5]

Use mode "all_live" so we get both API and UI data.

Compare today's results to yesterday's results stored in memory.
Alert me on Slack channel #aeo-watch if any of these are true:
  - Brand rank dropped by 2 or more positions on any prompt
  - Brand was previously mentioned and is now absent
  - A new competitor appeared in the top 3 on any prompt
  - The citation URLs changed for any prompt

Otherwise, do not send any message. Just store the data.

Once a week (Mondays at 09:30 UTC), generate a summary of the week's data
and post it to #aeo-weekly with: average rank, share-of-voice change,
new competitors detected, top citation sources, and one specific
recommendation for the upcoming week.

Replace [YOUR_BRAND] and [prompt N] with real values. Five prompts is the sweet spot for starting out.

Notice what we are doing here. We are not telling Hermes how to call the API or how to format the response. We are telling it the goal and the alert criteria. Hermes figures out the rest. This is the agentic part.

Schedule it and route alerts

For scheduling, Hermes has a built-in scheduler. The simplest path is via the config:

~/.hermes/config.yaml
schedules:
  aeo-daily:
    cron: "0 9 * * *"
    task: "Run the daily AEO check"
  aeo-weekly:
    cron: "30 9 * * 1"
    task: "Run the weekly AEO summary"

gateways:
  slack:
    bot_token: "xoxb-..."
    default_channel: "#aeo-watch"
    weekly_channel: "#aeo-weekly"

The Slack bot token is generated from a Slack App you create in your workspace. The Hermes docs cover the Slack app setup if you have not done it before.

Verify the agent is working

Test before you trust. Run a manual check:

You: Run the AEO check now for the prompt "best AI brand monitoring tools."

The agent should:

  1. Call mentionsapi.check_brand with that prompt and your brand.
  2. Return a structured response with rank, sentiment, citations.
  3. Compare against memory (which is empty on first run).
  4. Decide there is nothing to alert about and not send a Slack message.

If all four happen, the workflow is working. If the agent calls the wrong tool, asks for clarification, or fails silently, your prompt to the agent needs more specificity. Adjust and re-test.

What to expect in the first month

Some sample numbers from a typical setup running for two weeks.

6Slack alerts on day one (no memory yet, everything looks 'new')
0-3Daily alerts during the rest of week one
$14Total MentionsAPI cost for two weeks of running

Week two settles. Most days have zero alerts. The two days that do have useful information. One is typically a competitor that broke into the top three on a prompt you care about. The other is often a citation source change on Perplexity that points to a better-ranked URL.

Compare to running this in a SaaS tool: $50 to $100 for the same period. The cost story is the picks-and-shovels argument in real money.

The mistakes I see in agent setups

Three.

First mistake: too many prompts on day one. Five is plenty. I have seen people start with twenty and abandon the project a week later when their Slack channel becomes unreadable. Start with five. Add five more in week three if you have headroom.

Second mistake: not using Hermes's memory layer. Some setups configure the agent to alert on every change, regardless of comparison to history. The result is alert spam. The fix is to always include "compare to yesterday's result and only alert on meaningful deltas" in your prompt.

Third mistake: configuring the agent and then forgetting it. The whole point of the agent is that it tells you when to pay attention. But the configuration itself needs review. Once a month, look at what alerts you got. Were they useful? Did you act on them? If yes, leave the config. If no, tighten the criteria.

The agent is a tool, not an oracle. It gets better the longer it runs because (a) your tuning improves and (b) Hermes accumulates real data in its memory.

Frequently asked questions

How long does the full setup take?
About one evening. Twenty minutes for Hermes install, ten minutes for the MCP config, ten minutes for the workflow prompt, twenty minutes for Slack integration, fifteen minutes for testing. Plus a few hours over the next week tuning the alerts.
Can I run this on a hosted server or do I need my own infrastructure?
Either works. For hosted, a $5 to $20 per month VPS (DigitalOcean, Hetzner, Vultr) is fine. For local, it runs on your laptop or a Raspberry Pi. The lightweight nature of Hermes means infrastructure is rarely the bottleneck.
What is the actual cost of running this for a month?
Five prompts, daily runs, one brand: around $15 to $30 per month in MentionsAPI charges plus your VPS cost (call it $20 to $50 per month total). For multiple brands or more prompts, costs scale linearly. Ten brands, fifteen prompts: around $80 to $120 per month total.
Do I need a separate API key for each AI engine?
No. MentionsAPI handles all four LLM providers behind one endpoint. Hermes only needs the MentionsAPI key. The rest is abstracted.
Can the agent also do prompt discovery?
Yes. Use the discover_queries tool exposed by MentionsAPI MCP server. Tell Hermes to discover new prompts weekly and add the ones that look promising to your monitored set. This automates the discovery feedback loop without you doing anything by hand.
What about non-English markets?
MentionsAPI supports queries in any language the underlying LLMs support. Hermes does not care about language at the orchestration layer. Your prompts can be in Spanish, German, Japanese, or any other language. Just make sure your alerts and weekly summaries are also generated in the language you read.
Is Hermes Agent stable enough for production work?
Hermes is past 100,000 GitHub stars and has shipped five major releases in twenty days with 741 merged PRs. It is being deployed in production by hundreds of teams. For mission-critical work, run it in a redundant configuration. For monitoring work like this, a single instance is fine.

The setup is the easy part

Most of the value of this stack is not in the setup. It is in the iteration over the next three months.

Week one is about getting it running. Week two is about tuning the alert thresholds. Month two is about adding new prompts and brands. Month three is about expanding into new tasks (citation gap analysis, competitor share-of-voice, prompt discovery).

Set up the agent tonight. Tune it next week. Stop logging into a SaaS dashboard. Let the agent tell you when something deserves your attention.

Nikhil Kumar
Founder, MentionsAPI

Growth marketer at the intersection of marketing, product, and technology. 8+ years across startups and scale-ups in India, Switzerland, and the Netherlands. Founder of Landkit (landkit.pro).

Build the agent tonight.

$1 free signup credit lands in your wallet, no card required. Five steps to your first autonomous AEO and GEO monitoring agent.