Latenode

AI Weather Agent (With HTTP request)

This workflow demonstrates how to build an AI Weather Agent in Latenode. It uses HTTP requests to fetch weather data from an external API.

The agent understands natural language queries (e.g., “What’s the weather in Berlin tomorrow?”) and returns the forecast through Telegram, Slack, or an HTTP endpoint.

Updated Aug 31, 2026Est. run: 8 secEst. cost: $0.005
How Latenode estimates time and cost

Latenode bills workflow runtime in CPU seconds. The first 10,000 CPU seconds are free each month, then usage follows pay-as-you-go CPU-second pricing. Plug-and-Play (PnP) AI nodes are billed separately—each PnP token is $1 USD, charged pay-as-you-go at vendor cost plus a small processing fee, with no API keys required.

Full pricing — how CPU seconds work →
AI

Workflow preview

What this template does

  • Ask for weather in natural language
  • Fetch live forecasts through an HTTP API
  • Return answers via Telegram, Slack, or HTTP
  • Reuse an AI Agent + HTTP Request pattern for other APIs

How it works

1
Trigger

Receive a weather question

A user asks something like “What’s the weather in Berlin tomorrow?” through chat or HTTP.

2
AI

Understand location and time

AI Agent extracts the place and timeframe from the natural-language query.

3
Action

Fetch weather via HTTP Request

HTTP Request calls the external weather API and returns the forecast payload.

4
AI

Format a readable answer

AI Agent turns the API response into a clear forecast reply for the user.

Setup guide

1

Clone the template

Clone “AI Weather Agent (With HTTP request)” into Latenode.

2

Add AI Agent credentials

Connect the AI Agent integration used to parse questions and format answers.

3

Configure the weather API

Set the HTTP Request URL, headers, and parameters for your weather provider.

4

Attach a reply channel

Connect Telegram, Slack, or expose an HTTP endpoint, then run a sample city query.

Requirements

Latenode account
AI Agent credentials
Access to a weather API (key/URL as required)
Optional Telegram/Slack channel or HTTP client

FAQ

Common questions about this template

Each run uses credits on your Latenode plan. We charge for processing time (1 credit = 30 seconds). Your actual cost depends on your plan and how long the run takes. See pricing plans for plans and how credits work.