Skip to content
Why GEO Why us Pricing
Get started free
HomeProductAgents

An agent worth trusting shows its working.

A MentionBeat agent is an assistant that does generative-engine-optimization work inside your workspace — measuring, reading the pages that beat you, drafting, queueing fixes. It reaches 40 tools built on your own data, 9 of which can write. Every run is priced before it starts and logged step by step, and it stops before anything that cannot be undone.

Four ways a run begins

The reason to automate GEO is not that the thinking is hard — it is that the loop is repetitive and nobody finishes it. Agents exist to carry the repetitive half. A run starts in whichever of these four shapes fits the job, and none of them spends a credit before an estimate is on screen.

Conversation

Ask for an outcome in your own words — “find the three prompts we lost this month and tell me why” — and the agent plans, calls what it needs and answers. Threads are kept, named and re-openable.

When a conversation passes its retention window it says so at the top of the transcript, rather than quietly serving you a beginning that is missing.

Skills

Eighteen named jobs ship with the product, written as GEO procedures rather than prompts: answer the prompt we lost, tear down the page that is beating us, correct a wrong answer an engine is giving about us, tune the prompt suite.

Edit any of them for your workspace, and revert to the shipped version whenever the edit stops earning its keep.

Batch

One instruction, run down every row. Paste a list of pages, prompts, competitors or product URLs, add a column that says what to work out for each, and the grid fills in.

Columns are priced individually, a single cell can be corrected by hand, and anything that depended on that cell knows it changed.

Formats

Named page shapes — comparison, alternatives, FAQ, category explainer — each carrying the evidence it needs before it can be written, and the case for using it at all.

Building the same page family from your approved brief, without an agent, stays free in Content Studio.

How far it may go is a setting, not a hope

The uncomfortable question about any agent is what it does while you are not watching. MentionBeat answers it with three modes you pick per run, and the mode sits on the composer where the work starts rather than buried in a settings page.

ModeWhat it doesThe caveat that comes with it
PlanPlans only. Nothing is carried out.Read-only tools still run, so the plan is grounded in real measurement rather than a guess. Every change is recorded as a proposal and executed by nobody.
ManualAsks before every change.It runs until it wants to change something, then stops with the exact call in front of you. Approving continues the same run — one trace, not two.
AutoRuns to the end without asking.Auto removes the human, not the rules. Every change still passes the policy gate, the per-run ceiling and the kill switch.

Manual is the default. A tool that shipped Auto as the default would be optimising for the demo rather than for the Monday morning after it.

What an agent can reach

Forty tools, and the split matters more than the total: 31 of them only read. They pull your visibility scorecard, the prompts you lost, the answers verbatim, the rivals named instead of you, the domains engines cite, your product brief, your site audit and the open web.

Nine can write, and every one of them writes inside MentionBeat rather than out on your property — queue a fix, compose a draft, request a measurement run, propose a skill, track a source, call an endpoint you configured yourself.

  • A policy gate — the tool list this workspace allows, readable in the app
  • A per-run ceiling — 24 steps, 10 minutes and 200 credits by default
  • An approval stop — before anything that cannot be undone
  • A kill switch — anyone can stop a run; only an admin restarts

The trace records the difference between called and proposed — not run, so a plan never reads like an action after the fact.

The estimate comes before the spend

Agent runs consume the same credits as measurement, metered per tool call. Because an agent decides for itself how many tools a job needs, the honest estimate is a range: one call if the first answer is enough, up to the ceiling if it uses every step. Both ends are shown before you start.

A run with no tools costs nothing, and says so — the model is answering from your brief alone. Agents are on every plan, including Free. Credits are the only limit, and there is no automation tier to buy.

What a run costs →

What a run leaves behind

A chat window that forgets is a demo. Work an agent finishes becomes something you can find again, version, hand to somebody, and send out — deliberately, from one place.

Artifacts

Kept, and kept by version

Documents, batches, reports and saved views written by a run, each with its history. Correct one and the things downstream of it know. Pages built from your brief stay in Content Studio — nothing appears in both places.

Publish

The only door out

One surface sends anything outward, and it dry-runs first. CMS destinations receive drafts — never a published page — so the last read before your site changes is a human’s.

The queue

Straight into tracked work

A finding an agent turns up lands in the same fix queue as everything else, and closes on the same terms: only when an automated re-check confirms the page really changed.

Questions about agents

What is a MentionBeat agent?
An assistant that carries out GEO work inside your workspace. You describe an outcome in plain words and it plans, calls tools and reports back. It reaches 40 tools built on your own measurement data — visibility, lost prompts, rival pages, citation sources, product brief, site audit — of which 9 can write anything. The other 31 only read.
Can an agent change my website?
No agent writes to your site. The furthest one goes on its own is a draft, a queued fix or a proposal inside MentionBeat. Anything leaving the workspace goes through Publish, which dry-runs first and sends only on an explicit action, and CMS connectors create drafts rather than published pages.
How much does an agent run cost?
The same credits as measurement, metered per tool call. Because an agent decides how many tools it needs, the estimate is a range rather than one figure, and it is shown before you start. A run with no tools spends nothing. Every plan including Free can use agents — credits are the only limit.
What stops an agent running away?
A per-run ceiling defaulting to 24 steps, 10 minutes and 200 credits. A policy gate listing which tools this workspace allows. An approval stop before anything irreversible, in every mode except Auto. And a kill switch — anyone can stop a run, only an admin restarts.
Can I see what the agent actually did?
Every run keeps a step-by-step trace: what it planned, which tool it called, what came back, what it proposed without running, where a tool failed, where it stopped. Proposals are labelled proposed and not run. If an agent cannot show you the step, we would rather it did not take it.
How is this different from asking ChatGPT to do the same work?
An assistant with no account on your workspace has to be told what your visibility is, and will accept whatever you tell it. A MentionBeat agent reads the measurement that produced your reported numbers, so it can name the prompt it is reacting to, the engine that answered, and the rival that was cited instead. It also cannot quietly invent a fact about your product: writing is constrained to the brief you approved.

Keep going

Put the repetitive half on rails.

Agents are included on every plan, including Free. Start in Plan mode and read what it would have done.