I planned a walk in 60 seconds, then walked for two hours (open-weight AI, no GPU)

Description and use

The app lets users get a two‑hour walk plan in about a minute, including route, nature cue, packing list, and map pin, using an open‑weight LLM without GPU and at zero cost.

Problem

People struggle to plan a quick outdoor walk that fits a tight time budget and provides useful details like a loop, nature cue, packing list, and weather.

Outcome

The app delivers a one‑minute walk plan that users can act on immediately, with a 60:1 screen‑to‑outside time ratio. It runs for $0, uses no GPU, and remains functional despite provider changes.

Workflow

• 1. User enters location and time budget on the web form.
• 2. App queries Open‑Meteo for weather (cached).
• 3. App sends prompt to the LLM (openai/gpt‑oss‑20b) via Groq.
• 4. LLM returns walk plan: time window, loop, nature cue, packing list, map pin.
• 5. App displays plan and map pin.
• 6. User closes tab and walks.

Evidence

One input gives you one walk: the best time window, a loop idea, a nature cue and a packing line, plus a live map pin.

Source

On my own test walk I spent about one minute on the screen and one to two hours outside — roughly sixty to one.

Source

The plan named a destination I would not have picked myself — the lake promenade — and the "no car needed" line meant I walked instead of driving somewhere and sitting in a car park.

Source

Weather never rendered on the deployed app. Render's free tier shares one outbound IP across many instances, and Open‑Meteo rate‑limits that IP.

Source