Connect restaurant and foodservice data to your AI tools
An AI connector links an AI assistant or agent to an outside data source so it can answer from that data. Dashmote's restaurant and foodservice data, covering 60+ countries, works in AI tools that accept a connection key, or through our API, and our team sets up the connection for your workspace. Apps that connect only through a personal sign-in are available on request.
The trusted intelligence layer for teams selling to Hospitality & Retail
One dataset, many AI tools
Most teams no longer work in one AI tool. Analysts use Claude, developers work in GitHub Copilot or Gemini CLI, and IT and AI teams build agents in Copilot Studio or on OpenAI and Google models. Dashmote fits in with them.
The same outlet, menu, price and delivery app data that powers DashONE and DashLeads is available to AI tools in two ways:
- Our MCP server, for AI assistants and agents that connect to MCP servers with a connection key. See MCP server for restaurant data.
- Our API, for any tool, automation or in-house system that calls an API. See the Dashmote API.
Whichever route your tool uses, the answers come from the same licensed data, so a number in a chat matches the number in your dashboard.
The AI tools your teams already use
Dashmote connects today with the assistants and agent platforms that accept a connection key, and with anything that calls our API, including:
- Claude (Anthropic): Claude Code, Claude Desktop, and Claude for Team and Enterprise, for analysts and managers who want to ask questions, compare markets and draft reviews. See Dashmote in Claude.
- OpenAI models: agents and apps your company builds on OpenAI models with OpenAI's Responses API or Agents SDK. See Dashmote with ChatGPT and OpenAI models.
- Microsoft: Copilot Studio agents for account teams, and GitHub Copilot in VS Code for developers. See Dashmote in Microsoft Copilot.
- Google: Gemini CLI, and agents built with Google's Agent Development Kit (ADK) or on Vertex AI. See Dashmote with Google Gemini.
- Developer and automation tools: coding assistants such as Cursor, and workflow tools such as n8n, Zapier or Make.
Apps that connect only through a personal sign-in, such as the ChatGPT app or the Gemini app, are on request: ask us about connecting them for your workspace. If your tool is not on this list, ask us as well.
Local models and open agent tools
Some teams prefer to run AI on their own machines or with open models, for cost, privacy or control. Dashmote works there too, because the connection is a standard MCP server or API rather than a feature of one vendor's app.
- Open and local models: an agent running an open model on your own hardware can read Dashmote data in the same way a hosted assistant does.
- Open agent tools: such as OpenClaw, a free, open-source personal AI agent that runs on the user's own machine and takes instructions through messaging apps, so a rep could ask about an outlet from a chat app on the way to a visit. Or such as Hermes Agent from Nous Research, an open-source, MIT-licensed agent that connects to MCP servers and switches between LLM providers, so a team can keep Dashmote data in place while changing the model behind it.
- Agent frameworks: in-house agents built with common agent frameworks can call our MCP server or our API directly.
The governance stays the same in every case: the connection is scoped to your workspace and your licence.
What your teams can ask
Two groups get the most from Dashmote in an AI tool.
eCommerce and digital shelf managers look after how the brand shows up on delivery apps. They want to know where the brand is listed, at what price, whether it is in stock and how that compares with competitors, by platform and by city. Typical questions:
- 'Which burger restaurants in this city list our soft drink on one delivery app but not on another?'
- 'What does a large cola cost on each delivery platform in this market?'
- 'Where is our brand listed but marked unavailable this month?'
Field sales reps and key account managers look after outlets. They want to know which outlets to visit, what each one already serves, whether it is on a delivery app, and which accounts have the biggest gap to close. Typical questions:
- 'Which cocktail bars in my territory do not serve our gin yet?'
- 'What does this outlet serve, and is it on a delivery app?'
- 'Which outlets should I visit first this week, and why?'
Follow-up questions build on the answer before, so a long list becomes a short, practical one in a few turns.
How the connection is set up
There is no form to fill in. Connecting Dashmote to an AI tool is a short project we run with you:
- Tell us which tools your teams use and which questions they need answered.
- We agree the scope: the markets, platforms and data your licence covers.
- We connect the first tool with you, through our API or our MCP server, and check the first answers together.
- You roll it out to the teams that need it, and add more tools later on the same workspace.
Because every tool reads the same data, adding a second or third tool does not create a second version of the truth.
Governance in plain words
Connecting an AI tool does not widen what anyone can see. The connection is set up for your Dashmote workspace, so it reaches only the markets, platforms and data your licence covers, and nothing else.
- Licensed data only: the assistant answers from the Dashmote data your company has licensed, not from the open web and not from other customers' workspaces.
- Scoped per workspace: your admin decides which teams use the connection, and every answer stays inside your workspace's scope.
- Dated answers: every answer carries the refresh month it comes from, so a number in a chat can be traced back to the same refresh you see in DashONE.
- Clear definitions: an outlet is a physical venue and a storefront is its listing on one delivery app. The assistant keeps the two apart, so counts are not mixed up.
Frequently asked questions
What is an AI connector?
An AI connector links an AI assistant or agent to an outside source so it can use that source's data while it answers. With Dashmote connected, an assistant can answer questions about outlets, menus, prices and delivery app listings.
Which AI tools work with Dashmote?
Tools that accept a connection key, and anything that calls our API. Today that includes Claude Code, Claude Desktop, Claude for Team and Enterprise, GitHub Copilot, Copilot Studio agents, Gemini CLI, agents built with Google's ADK or on Vertex AI, agents built on OpenAI models, coding assistants, workflow tools, local models and open agent tools such as OpenClaw and Hermes Agent. Apps that connect only through a personal sign-in are on request.
Do we need developers to connect it?
Not for most tools. Our team sets up the connection with you for your workspace and checks the first answers together. For agents you build yourself, for example on OpenAI or Google models, your developers own the agent and we connect it with them.
Can every user see all Dashmote data?
No. The connection is scoped to your workspace and your licence, so people only see the markets, platforms and data your company has licensed.
How fresh are the answers?
Every answer carries the refresh month it comes from, the same refresh you see in DashONE, so you always know how current a number is.
Related reading
The business case for your AI or data lead
Why connect the data once, at the source:
- Use the AI tools you already pay for: one workspace connection serves Claude, Copilot, Gemini CLI, agents on OpenAI and Google models, open models and in-house agents.
- One version of the truth: every tool answers from the same licensed data as DashONE and DashLeads, so numbers match across teams.
- Grounded answers: assistants answer from dated outlet, menu and delivery app records instead of guessing from the open web.
- No lock-in: if your company changes AI vendor, the data connection moves with you.