Using marketing mix modelling from ChatGPT or Claude

Marketing teams now ask ChatGPT and Claude about almost everything, including the budget. That raises a fair question: do you still need a marketing mix model, or can the assistant do the analysis itself? The short version is that the assistant is a very good way to use a model, and a poor replacement for one. This guide explains the difference, what MCP changes, and what to check before you connect an MMM platform to your own AI assistant.

The short answer

A general-purpose assistant cannot run reliable marketing mix modelling on its own. Give it the same spreadsheet twice and you will get two different analyses. What it does well is act as the interface to a real model. Through MCP (the Model Context Protocol, an open standard for connecting assistants to other systems), Claude, ChatGPT or Copilot can call an MMM platform directly, run scenarios against your fitted model and return that model's numbers in plain language.

Why an assistant on its own is not an MMM

Marketing mix modelling estimates how each channel's spend drives sales, after accounting for the baseline, seasonality, delayed effects and diminishing returns. Doing that properly takes a fixed model structure, prior knowledge about how marketing works, enough history, and a check that the model forecasts sales it has not seen. It also has to give the same answer on Tuesday as on Monday.

An assistant asked to "do MMM on this data" improvises a new method each time. It may produce a plausible regression, but there is no stable model behind it, no record of the assumptions, no uncertainty you can trust and nothing to verify next month. That is fine for exploring an idea. It is not something to set a budget on.

We use AI heavily ourselves, to develop and improve the models and the framework around them. The decisions still run on a structured model with guardrails, and the assistant is how people talk to it.

What MCP changes

MCP lets an assistant use tools in another system on your behalf. When an MMM platform offers an MCP server, the assistant can ask the platform to run a scenario, an optimisation or a forecast, and get back the same numbers the platform computes, with an explanation of what they mean. Nothing is invented in the chat.

In practice, that means a CMO or CFO can ask questions like these directly, without logging in to anything:

• "We need to reach our sales target in Q4. What does it take to be 80 percent sure of hitting it?"
• "What would the model have done differently with last year's budget, and how would it have turned out?"
• "If we cut TV by a fifth next quarter, what happens to sales, and how certain is that?"
• "Which channels are close to saturation, and which still have room?"

Behind each answer, the platform runs the actual scenario on the fitted model, including the simulations that produce the uncertainty range. The assistant explains the result and can follow up. Because the setup of the model is exposed as well, a finance lead can get a direct answer while an analyst digs into the assumptions.

The same connection works before a model exists. Once the data is collected, you can ask about your own history: what was spent where, how TV prices have moved, which ads the platforms report as strongest. The structured dataset is useful on day one.

Can an AI agent plan and optimise the media budget?

Partly. The optimisation itself is done by the model: given a budget and constraints, it finds the allocation with the highest expected return. An agent can run that optimisation, compare several scenarios and write up the options. What it should not do on its own is move money in your ad accounts. The Odins MCP recommends how much to spend, where, and what to test. Acting on it stays with you, and our team reviews the monthly recommendations before they are delivered.

Which MMM platforms work with ChatGPT or Claude?

The list is growing quickly. As of autumn 2026:

• Odins launched its MCP server in May 2026. It works with Claude, ChatGPT, Microsoft Copilot and any other assistant that supports MCP, on top of a managed Bayesian model of your business. Since launch, most of our customers have moved their day-to-day use of the platform into their own assistant. How the Odins MCP works.
• Lifesight launched an MCP connector in June 2026 for its measurement products.
• ScanmarQED connects its MMM Labs product to Claude, ChatGPT and Copilot.
• Google Meridian 2.0 added an MCP-based module that guides teams building and running Meridian models themselves.

The protocol is the same everywhere. What differs is what sits behind it.

What to check before you connect one

• Is there a model of your business behind it? A connector to a generic tool, or to raw data only, will let the assistant improvise again. Ask whether answers come from a model fitted and verified on your data.
• Are the numbers the platform's numbers? The assistant should report what the model computed, with the uncertainty range, not its own estimate.
• Can you see the assumptions? Ask whether the priors, saturation curves and model setup can be queried through the same connection.
• What can it change? Check which actions are read-only and which write data, and who in your company has access.
• Who keeps the model current? A connection to a model that nobody retrains gives confident answers based on old data.

Where AI actually sits in MMM tools

When a vendor says its MMM uses AI, that can mean three different things, and it helps to separate them. The estimation itself is statistics: Bayesian sampling that fits carry-over, saturation and baseline with uncertainty. AI helps the people who build and maintain models work faster and check more. And assistants connected through MCP change who can use the model, from a few analysts to anyone in the leadership team. Only the first decides whether the numbers are right, which is why the questions about priors and verification in our vendor selection guide still matter most.

Frequently asked questions

Can ChatGPT or Claude do marketing mix modelling for us?

Not reliably on their own. They can explore data and explain concepts, but they do not hold a stable, verified model, so the same question can give different answers. Used through MCP on top of an MMM platform, they become a practical way to query a real model.

Which marketing mix modelling platforms can be used through an MCP server?

Odins, Lifesight and ScanmarQED offer MCP access to their products, and Google Meridian 2.0 includes an MCP-based module for teams running Meridian in-house.

Which tools let us ask about budget and results in plain language?

Any MMM platform with an MCP server can be queried from Claude, ChatGPT or Copilot. With Odins, you can ask about budget size, allocation, scenarios and your raw marketing data in the same conversation.

Does the assistant change our ad accounts?

Not with Odins. The model recommends; your team decides and acts.

To see what a conversation with your own model looks like, read about the Odins MCP, start with our guide to marketing mix modelling, or book a demo.