Product · Automate

AI content workflows — the content grid that runs itself.

A content grid is a spreadsheet where every column can execute work: LLM drafts, citation checks, brand-voice tests, and Search Console data — all in one table, automated on a schedule. Use it alongside AI content optimization to turn visibility gaps into published, cited content without manual hand-offs.

Topic
LLM draft
Citation check
GSC clicks
best payments platform
Drafted ✓
5/6 cited
1,240
embedded payments
Drafted ✓
4/6 cited
880
usage-based billing
queued…
610
Inside automate

What is a content grid?

A content grid is a spreadsheet where columns execute work — LLM prompts write drafts, citation checks verify each row against six AI engines, and brand-voice injection keeps every cell on-message. Drop in topics; get drafted, checked, on-brand content out.

STEP 01 BUILD A GRID TOPIC LLM DRAFT CITATION BRAND ✓ best payments Drafted ✓ 5/6 cited 92% embedded pay Drafted ✓ 4/6 cited 88% usage billing queued… LLM COLUMN
01 · Grids

Build the grid

Add topics to the first column, then attach column types: LLM Draft for copy, Citation to check which engines cite you, Brand ✓ for voice alignment. One row = one piece of content, built end-to-end in a single table.

STEP 02 RUN COLUMNS TOPIC LLM DRAFT CITATION BRAND ✓ best payments Drafted ✓ 5/6 cited 92% ✓ embedded pay Drafted ✓ 4/6 cited 88% ✓ usage billing running 2 / 3 rows complete Cost this run: $0.018 Cap: $1.00 RUNNING
02 · Columns

Run the columns

Hit run. LLM columns draft every row; citation columns test each output across six AI engines; brand-voice columns score the result. Cost is tracked per cell. A cap stops the run before it overspends.

STEP 03 AUTOMATE WEEKLY TRIGGER cron weekly RUN GRID LLM + citation check OUTPUT grid + notify AUTOMATION FLOW branch on condition Last run: Mon 09:00 UTC Next: Mon 09:00 UTC
03 · Automations

Automate on a schedule

Wire a cron trigger to the grid run, add a branch for conditions, route the output back to the grid or fire a notification. Every week the grid re-runs — new drafts, fresh citation checks, same brand voice — without anyone clicking a button.

Grids

Columns that think

Each column can be an LLM prompt, a web search, a scrape, or a Mentionova-native check — citation status, competitor overlap, Search Console clicks — so a row goes from topic to drafted, fact-checked and scored without leaving the grid. Use the grid alongside AI visibility tracking to prioritize which topics to draft first based on live citation data.

Automations

Run it on a schedule, not by hand

A visual builder wires triggers to channels to outputs — run on a cron, pull metrics, branch on a condition, and save the result to a grid or fire a notification. The busywork runs while you sleep. Pair automations with AI brand monitoring to trigger drafts automatically when your visibility changes.

Brand voice

One voice, every draft

Your brand-voice profile — guidelines plus real content examples — is injected into every LLM column, so a hundred drafts read like your team wrote them, not a hundred different robots.

The numbers

How do content automations work?

A visual builder connects a trigger — scheduled, webhook, manual or API — to channels like LLM or web search, then routes the output to a grid, a notification, or a CMS push. The whole sequence runs unattended so recurring content work happens on a clock, not a to-do list.

Column types5 families

Data, reference, execution, Mentionova-native and formula.

Native checks4+

Citation check, competitor overlap, GSC sync, prompt sync.

Automation stepstrigger→output

Triggers, channels, logic and output nodes.

Cost controlper cell

Per-cell and run-level cost tracking with a cap.

0
column families
0
trigger types
0%
in your voice
~0 min
to first signal
Content grid

A spreadsheet that runs itself

Drop a list of topics in the first column. The LLM columns draft, the citation-check columns verify, and the brand-voice profile keeps every cell on message — the whole thing fires on a schedule while you're doing something else.

Topics in → drafted, checked, on-brand rows out

TOPIC LLM DRAFT CITATION BRAND ✓ best payments Drafted ✓ 5/6 92% embedded pay Drafted ✓ 4/6 88% usage billing running… stripe vs adyen queued… SCHEDULED · DAILY · RUNS AUTOMATICALLY Cost this run: $0.032 Cap: $1.00
Every signal, rendered

What are LLM columns?

LLM columns are executable grid columns that send each row's topic to a large language model. Write one prompt; the column runs it across every row and writes the output back — draft, summary, structured data, or anything else — so one instruction scales to hundreds of pieces. Every LLM column inherits your shared brand-voice profile automatically.

Free AI visibility report

Put your content ops on rails.

Enter your domain and we'll show you the AI visibility gaps worth a grid — then you can run the drafts, checks and publishing from one table.

https:// Get my report

Takes ~3 minutes · no credit card

FAQ

Questions, answered.

What is a content grid?+
A spreadsheet-style table where each column can execute work — an LLM prompt, a web search, a citation check, or a brand-voice test — so a list of topics becomes drafted, fact-checked, on-brand rows without leaving the grid.
How do content automations work?+
A visual builder wires a trigger (schedule, webhook, manual, API) to channels (LLM, web search, metrics) and outputs (save to grid, notify, push to CMS) — so recurring content workflows run on their own instead of by hand.
What are LLM columns?+
Column types inside a Mentionova grid that send each row's data to a large language model. You write one prompt; the column runs it against every topic row and drops the draft — or any other output — back into the cell.
What can the columns do?+
Columns come in five families: data, reference, execution (LLM, Perplexity research, web fetch, scrape, Google search, CMS push), Mentionova-native (citation check, competitor overlap, Search Console sync, prompt sync), and formulas — so a grid both generates and verifies content.
How does brand voice stay consistent?+
Your workspace brand-voice profile — guidelines and real content examples — is injected into every LLM column, so drafts across the grid read in one consistent voice.
Can I control the cost of running a grid?+
Yes. Cost is tracked per cell and per run, and a cost cap stops a run before it overspends, so large grids stay predictable.
How do AI content workflows help with AI visibility?+
Grids run citation checks natively — every LLM-drafted row is tested across the six AI engines before it publishes. Topics where your brand is already cited get prioritized, and brand-voice injection keeps every output aligned with how models already describe you.