Skip to content
Why GEO Why us Pricing
Get started free

Draw the workflow. Price it. Leave it running.

A flow is a branching graph of agent steps: read your measurement, fork on what it says, repeat once per row, stop for a person, write a draft, call another system. You draw the path instead of hoping a model picks it, the whole graph is costed before it runs, and it can run every Monday without you.

Four flows that already run

A blank canvas is a worse front door than a list of things that work, so the palette opens with whole flows wired from GEO verbs rather than generic ones. Each drops onto the canvas complete, and appends rather than replaces — dropping one onto work in progress cannot lose anything you built.

FlowThe steps it arrives withWhat you get at the end
Content refreshRead the page → compare it against the page that wins → branch on whether we are behind → rewrite → lint → approvalA checked rewrite of a page that slipped, or an early exit saying it did not need one
Answer what we loseList lost prompts → read what was said instead, once per prompt → plan → write → lintA draft that answers the questions engines currently answer without you
Why they winList competitors → list the sources cited → tear each rival page apart → compare how each brand is described → summariseThe three things your pages would have to change to be cited instead
A page for a gapMeasured gaps → the brief → what you already say → plan → write → lint → approvalA measured content gap taken all the way to a draft somebody has approved

Every step above is a real tool on your own data, not an illustration. The palette also holds each step on its own, and a search that covers tool descriptions as well as names — because somebody looking for “Slack” is searching for a word that appears in no tool name.

Five kinds of step

Beyond the tools themselves — the ones that read your data and the smaller set that write — a graph is built from five shapes. Read-only steps come first in the palette on purpose: the cheap, ungated ones are what a graph should be mostly made of.

Prompt

A thinking step

A free-text instruction with a typed answer. It runs no tool, so it reaches nothing and writes nothing — useful for turning three earlier outputs into one judgement.

Branch

The graph forks

Answers one true/false question and sends the run down the matching wire. This is what lets a flow do nothing when nothing is wrong.

Each row

Fan out, then rejoin

Runs the step once for every row it was handed — every lost prompt, every rival page — and passes the answers on as a list.

Approval

Stops for a person

Runs nothing itself. The flow halts with the exact next action on screen and waits, however long that takes, including on a scheduled run at 7am.

Call

Reaches another system

Sends a request outside MentionBeat. You set the address when you build the flow; the running model cannot read it, change it or redirect it.

Every node says which it is

A step that only reads is labelled Reads. A step that writes is labelled Writes and carries a mark on the palette before you ever place it. You should not have to run a graph to find out what it touches.

The price is on the header, not the invoice

The cost of the whole graph sits beside the Run button and updates as you wire it. An empty canvas reads nothing to run yet rather than a misleading zero, and a step whose price cannot be known says so instead of guessing low.

Flows spend the same credits as measurement and agent runs. There is no automation tier, no per-seat automation fee and no plan that unlocks the canvas — credits are the only limit, on Free as much as on Enterprise.

  • Save — a flow is a document you keep, name and come back to
  • Schedule — daily or weekly, your hour, weekday and timezone
  • Run — with the estimate visible before the click
  • Stop — mid-run, by anyone in the workspace

A scheduled run cannot double-fire

Each scheduled flow is claimed before it starts, so a crash or a restart mid-run does not produce a second one spending the same credits twice. The next fire is computed from the moment it actually ran, which means a flow that takes an hour can never be immediately due again.

It is the same reasoning as scheduled measurement, applied where the stakes are higher: a flow can spend credits and reach somebody else’s system.

How scheduled measurement works →

Questions about flows

What is a flow in MentionBeat?
A graph of agent steps you draw on a canvas. Each node reads something, writes something, thinks, forks on a true/false question, repeats once per row, waits for a person, or calls another system. Connect one node to the next and the answer travels along the wire. Unlike a single agent run, the path is yours rather than the model’s.
Do I have to build one from scratch?
No. Four working flows ship in the palette and drop straight onto the canvas: content refresh, answer what we lose, why they win, and a page for a gap. They append rather than replace, so dropping one onto work in progress cannot lose anything, and cloning one to adjust a step is the normal way to use them.
What does a flow cost to run?
The whole graph is priced before you start it, in the header beside the Run button, and the estimate updates as you add steps. An empty canvas reads “nothing to run yet” rather than zero. Flows spend the same credits as everything else, and there is no separate automation tier.
Can a flow run without me?
Daily or weekly, at an hour and weekday you choose, in your timezone. A scheduled run is claimed before it starts so a crash cannot double-run it, and the next fire is computed from the moment it ran. Any approval step still stops and waits for a person.
Is it safe to let a flow call another system?
The address is fixed by whoever built the flow, and the running model can never reach it. This matters because an agent reads untrusted content by design — competitor pages, the open web, engine answers — so an injection hidden in any of it could otherwise name a destination. An injection can still influence what a call sends. It can never influence where.
When should I use a flow instead of just asking an agent?
Ask an agent when the job is one-off and you do not mind it choosing its own path. Build a flow when you want the same path every time — because it runs weekly, because somebody has to approve step four, or because you are running it for twenty clients and the variation should be the data, not the method.

Keep going

Wire it once. Run it every Monday.

Flows are on every plan, including Free. Drop a working one on the canvas and read what it would cost before you run it.