← back to examples
ai intermediate

Jido.AI Weather Multi-Turn Context

Local weather assistant demo showing real city context carryover, deterministic tool calls, and one intentional retry/backoff event across turns.

primary showcase ai l2 ai-tool-use weather jido_ai

Related guides and notebooks

Concept
Reasoning strategies compared
Reasoning strategy context for weather assistants.
Livebook
Reasoning strategies compared
Run the companion notebook in Livebook
Source
weather multi-turn demo script
Upstream script with retry/backoff helpers and semantic checks.
Explanation

What this example teaches

Interactive Demo

Run the agent and inspect state

Source Code

Read the production implementation

What you’ll learn

  • How multi-turn prompts preserve location context across follow-ups without repeating the city
  • How a local weather tool can trigger deterministic retry/backoff behavior on a transient busy response
  • How to inspect preserved context, retry events, and tool-call payloads from a real local example

Demo note

This page now runs a real local weather assistant workflow. The weather data is deterministic and local, but the turn execution, context carryover, retry handling, and transcript are all produced by the shipped demo modules rather than a replayed transcript.