Operations

A weather brief for every site

Checks the three-day forecast for each of your sites, warns about heavy rain, strong gusts and hard frost, and lists any active US weather alerts.

The run behind the Chicago warning: three forecast calls, the alert check and the model's steps, each with its time and cost.
Recorded in the staging demo workspace, using public APIs.

One recorded run

Heavy rain in Chicago, spotted ahead of time

Who it is for

Operations and logistics teams who plan work at warehouses, ports and depots around the weather.

On 11 November an ops planner listed three sites with their coordinates: a warehouse in Berlin, the port in Rotterdam and a distribution centre in Chicago. The agent asked a public forecast service once for each site, and the US weather service for active alerts in Chicago: four calls in all.

The brief gave one line per site and day, and one warning: on 12 November Chicago expected 24.2 mm of rain and gusts of 60.5 km/h. Berlin and Rotterdam had no warnings. The run took under ten seconds and cost less than half a cent.

Recorded once in the staging demo workspace against public APIs. The numbers are copied from that run; another run, other data or another model can give a different result.

What the agent does

  • Gets a three-day forecast for every site you list
  • Checks active weather alerts for sites in the United States
  • Copies the numbers as the service returned them, and adds a warning for rain over 20 mm, gusts over 60 km/h or frost below -5°C
  • Keeps every run, with each call it made and what came back

What you need

  • Your sites, with their coordinates
  • An AI model connected in almyty
  • Nothing else: both weather services are public and free

Set up your own

Three steps to a version of this.

The docs walk through an agent of this kind step by step. It is a guide to the pattern, not a copy of this exact agent.

Read the guide
  1. Connect the weather services

    Paste the link to each service's API description. almyty lists what each one can do.

  2. Build the agent

    Describe the brief in plain words: which numbers per day, and when to warn.

  3. Ask it, or schedule it

    Send it your list of sites, or let a schedule send it every morning.

Keep exploring

Other recorded examples.

Start with a job like this one.

Connect the service, describe the result you want and check the first run yourself.