ChatGPT + MCP
Route optimization from ChatGPT
ChatGPT can plan a route in conversation, but it should not be trusted to optimize dozens of stops on its own. With AIRO, ChatGPT connects to a real optimization engine through MCP and reports back what the engine computed.
Why not just ask ChatGPT to optimize my stops?
- Language models can produce plausible but invalid routes.
- They cannot reliably enforce capacity and time-window constraints at scale.
- Pasting your customer list into a chat exposes more data than necessary.
- Results are not reproducible from one run to the next.
The MCP approach
With MCP, ChatGPT calls AIRO tools: create an import, validate it, start an optimization job, read the results, compare scenarios, export files. The optimization is performed by the AIRO engine, and your uploaded file stays in the platform.
Availability
Support for MCP connectors in ChatGPT depends on your OpenAI plan and on OpenAI's current rollout. The connector is built on the open MCP standard so it can work with other compatible AI clients too, and the web portal works regardless.
Example workflow
- Upload your delivery spreadsheet via a secure link.
- Ask ChatGPT to validate it and list the problems.
- Fix the issues in the portal or by instructing the assistant.
- Ask for an optimization for your number of vehicles.
- Review KPIs and export the driver sheets.
Frequently asked questions
Does AIRO work with ChatGPT?
AIRO is built on MCP, an open standard that ChatGPT and other AI clients are adopting. Availability of MCP connectors inside ChatGPT depends on your OpenAI plan and OpenAI's current rollout. The full browser portal works regardless of which assistant you use.
What is MCP?
MCP (Model Context Protocol) is an open standard that lets AI assistants call external tools securely. In AIRO, MCP exposes actions like "validate import" and "optimize routes" to Claude or ChatGPT. The assistant is the interface; the AIRO backend does the work.
Is my customer address data used to train AI models?
No. Customer files are processed by the AIRO optimization engine, not used as training data. The full contents of your uploaded file are never sent to an LLM. When you use an AI assistant, it only receives summaries and results returned by the platform's tools.
Can I optimize routes from an Excel file?
Yes. AIRO is built around the spreadsheet you already use. Upload an Excel (.xlsx) or CSV file with your orders and vehicles, map your columns, fix any validation issues, and run the optimization. You do not need to reformat your file into a rigid template.
Join the waitlist
Get early access and launch updates. Double opt-in, unsubscribe anytime.