AI Assistance / Ask Intelligence
Ask your business a question. Get the figure, and its source.
Ask Intelligence is the box at the top of every page. It reads your own data through read-only tools scoped to the brand you have open, and answers with the real number. When the data is not there, it says so.
Demo workspace. Invented brand and figures.
Four steps between the question and the figure.
Anywhere
One box, at the top of every page
Type the question the way you would ask a colleague. In your language. A follow-up refines the last answer, and the thread holds while you stay on the page.
It decides
It picks the tools the question needs
Rankings, content plans, spend, findings: the analyst chooses which of its 21 tools to call and calls them, up to eight rounds, then it has to answer.
We enforce
Every query is filtered on the brand you have open
The scope is applied in code before a query reaches the database. The model never chooses the scope, so it can’t widen it.
It answers
The figure, the source, and the price
A short answer first, the detail in a table when a table helps. Under it, which sources were read, the tokens, and the billed cost of that one answer.
The 21 tools, each one returning rows for a single brand.
Fourteen read the brand you have open. Seven read the organization, and each of those is offered only when your role can see that data. A tool you may not use is never shown to the model.
Search and visibility
Brand profile, tracked keywords, Google rankings per market, AI visibility (what the assistants say).
Content
Content plans, blog articles by stage and funnel role, what shipped and what is waiting.
Advertising
The keywords picked for search ads, the campaigns assembled here, and their live performance.
Social and work
What went out on each network, and the board: planned, in progress, done.
Agents and spend
What the watchers flagged, the weekly operating reviews, and what this brand cost in AI and data, by action.
The organization, behind a right
Pipeline and clients, revenue, the project board, and the Assets Library. Each is offered only to people whose role can see it.
Full list in the product help, under Ask Intelligence.
Not a chatbot with your logo on it.
A general assistant answers a question about your business the way it would answer anyone: from memory, confidently, with no source. Ask Intelligence has nothing to remember. It has tools, and each tool returns rows from your account.
So the answer to “what did we spend on this brand” is the figure in your ledger. The answer to “which clusters have no content yet” is your list of clusters. And when the data can’t support the question, you get a sentence saying so instead of a plausible number.
> which deals went quiet this month?
A general assistant
- Answers from what it read on the internet.
- Sounds certain, cites nothing.
- Will produce a figure whether or not one exists.
- Has no idea which brand you mean.
- Cost is somebody else’s subscription line.
Ask Intelligence
- Answers from the rows it just read in your account.
- Lists the sources under the answer.
- Quotes the real figure or says the data is not there.
- Scoped to the brand you have open, in code.
- Prints its own price under every answer.
Six rules, written into the analyst.
Counts, volumes, budgets, spend: it quotes the rows it read. It doesn’t make up a keyword, a campaign, a figure or an address.
And says which part of the product would produce it, which is usually a module you haven’t switched on yet.
Every tool is read-only. Nothing here publishes, launches or spends. When an answer becomes work, a person makes it a card on the board.
Ask in French, get French. The rule is written into the analyst.
Eight tool rounds at most per run. The billed cost comes back with the answer and is written to the ledger with your name and the brand.
A Zoho or custom MCP connection your administrator switched on adds its read tools to the box. Write tools are stored and never run.
The price line under every answer. The same line lands in the ledger.
The same data, one door over.
Nothing here is an integration. These run on the same account, the same brand, the same ledger, so a finding on one page becomes work on the next.
Not built yet, said first
- A focused version inside each module page exists in the API, not yet in the interface.
- Answers arrive whole, not streamed word by word.
- The thread lives on the page. Reload, and you start a new conversation.
The catalog lists every agent as built, partial, or not built. Checked against the product on September 3, 2026.
Usage is metered in tokens from a prepaid wallet, with no seat fee. The rates are on thepricing page.
It answers from whatever data you have added.
Switch on one module, ask the first question the same afternoon. Every answer says what it read and what it cost.
No subscription. No seat fee. No card needed to request an account.