Waitlist open — launching soon
Turn Your Delivery Spreadsheet Into Optimized Routes
Upload your orders and vehicles, validate the data, and generate driver-ready routes — directly from Claude, ChatGPT, or your browser.
No complex TMS implementation. No new dispatch workflow. Start with the spreadsheet you already use.
- Excel & CSV
- Claude & ChatGPT
- Driver-ready exports
Manual route planning wastes time, fuel, and vehicles.
If your dispatcher builds tomorrow's routes in a spreadsheet, you already know where the hours go.
Hours of manual sorting
Dispatchers re-sort rows by hand every day, then copy the result into driver sheets.
Extra kilometers
Routes built by eye zig-zag across town. Every unnecessary kilometer is fuel, wear and driver time.
Missed time windows
Juggling morning slots and customer promises in a grid is error-prone, and late arrivals cost trust.
Uneven vehicles
Some vans end up overloaded while others run half empty, because capacity is hard to balance manually.
No way to compare plans
Testing “what if we used 4 vans instead of 5?” means rebuilding everything from scratch.
Tools built for big fleets
Enterprise routing software is heavy and expensive. Small fleets are left with Excel and guesswork.
From spreadsheet to routes in three steps
Step 1: Upload your spreadsheet
Import orders, vehicles, depots, capacities, and time windows.
Step 2: Validate and optimize
Detect address, capacity, and scheduling issues before optimization.
Step 3: Get driver-ready routes
View routes on a map, review KPIs, and export Excel or CSV files.
MCP connector
Optimize routes directly in Claude or ChatGPT.
Connect AIRO to your preferred AI assistant through MCP. Ask Claude or ChatGPT to validate a file, optimize routes, compare scenarios, or export a driver-ready plan.
The AI assistant connects to the AIRO optimization engine through MCP. It does not perform the optimization itself: the engine is deterministic, and your full file is never sent to an LLM.
- Authenticated with OAuth, scoped to your company
- Every action is logged and idempotent
- Also fully usable from the web portal
User
I uploaded today's delivery file. Please optimize it for 5 vans and make sure all morning time windows are respected.
Assistant
I found 82 valid stops and 5 vehicles. I optimized the routes, assigned all stops, and reduced estimated distance by 18%. Would you like to compare this with your original plan or export the driver sheets?
Everything between your spreadsheet and your drivers
Built for dispatchers who plan in Excel, not for enterprise logistics teams.
Excel and CSV import
Bring the file you already have. .xlsx and .csv are both supported.
Column mapping
Match your own headers to the fields the engine needs, with automatic suggestions.
Address validation
Catch incomplete or ambiguous addresses before they break a route.
Geocoding status
See which addresses resolved, which need attention, and why.
Duplicate detection
Spot repeated orders and stops that appear twice in your file.
Vehicle capacity constraints
Respect each vehicle's load limit, with clear reports when demand does not fit.
Time windows
Plan around customer availability, with unserved stops reported rather than hidden.
Multi-vehicle route optimization
Split stops across your fleet from a single depot to reduce distance and duration.
Built for small fleets that plan in spreadsheets
Wherever vehicles visit multiple stops a day, routing is a spreadsheet problem first.
Local delivery
Plan daily runs for bakeries, florists, pharmacies and retailers delivering within a metro area.
Learn more about local deliveryLast-mile delivery
Sequence dense parcel and package drops across a small fleet of vans.
Learn more about last-mile deliveryField service
Route technicians between jobs with service times and appointment windows.
Learn more about field serviceHome services
Cleaners, installers and repair crews visiting several homes per day.
Learn more about home servicesFood distribution
Deliver to restaurants and stores inside tight morning receiving windows.
Learn more about food distributionCourier operations
Handle same-day courier runs with many stops and changing daily volumes.
Learn more about courier operations
Estimate what better routes could be worth
Adjust the assumptions to match your operation. This is a back-of-the-envelope estimate, not a promise: real savings depend on your stops, geography and constraints.
Estimated yearly impact
$15,600
in avoided distance cost
24,000 km
fewer kilometers per year
Illustrative estimate based on the values you enter. Results vary by operation, and no savings are guaranteed.
Your data stays in the engine, not in an LLM
AIRO is designed around data minimization: customer files are processed by deterministic backend services.
- Data encrypted in transit
- Encrypted backups
- Role-based access
- Audit logs
- Configurable file retention
- No training of AI models on customer files
Customer files are processed by the optimization engine, not used as LLM training data.
Frequently asked questions
What is AIRO?
AIRO is an AI-native route optimization platform for small fleets. You upload a spreadsheet of orders and vehicles, the platform validates the data, a deterministic optimization engine builds the routes, and you export driver-ready files. You can do all of it in the browser or through an AI assistant such as Claude or ChatGPT.
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.
Does AIRO work with Claude?
Yes. AIRO is designed to connect to Claude through MCP (Model Context Protocol). Once connected, you can ask Claude to validate an import, launch an optimization, compare scenarios or export driver sheets. Claude calls the AIRO engine, which performs the optimization.
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.
Do I need a TMS to use AIRO?
No. AIRO is not a TMS and does not require one. There is no dispatch system to implement. You start with the spreadsheet you already have and export files your drivers can use.
Be first to turn your spreadsheet into routes
Join the waitlist for early access. No spam, double opt-in, unsubscribe anytime.