Outwards Days — make a little room for outside

Description and use

Outwards Days uses local AI and deterministic scheduling to suggest realistic short outdoor activities for busy users.

Problem

Busy schedules make it hard to find realistic reasons to go outside.

Outcome

Outwards Days successfully integrates local AI inference with deterministic scheduling to provide realistic, time‑budgeted outdoor suggestions for busy users.

Workflow

• 1. User inputs schedule, preferences, and travel limits into the app.
• 2. The Mastra workflow gathers calendar, weather, place, and history context.
• 3. Gemma 4 E2B (via Ollama) proposes personalized outdoor activities.
• 4. Code validates suggestions against free intervals, daylight, weather, and activity frequency.
• 5. If validation fails, the workflow attempts a repair or falls back to a basic catalogue.
• 6. User reviews the generated week, accepts or moves outings, and records what actually happened.
• 7. Completed plans are synced idempotently to the server for future use.

Evidence

Outwards Days helps someone with a crowded week find a realistic reason to go outside.

Source

It starts with their actual schedule: work, busy blocks, lunch gaps, preferred times, travel limits, and the days they really have free.

Source

A Mastra workflow gathers schedule, weather, place, and bounded history context, then asks Gemma 4 E2B through Ollama to choose and personalize eligible outdoor activities.

Source

The model does not get to decide whether a suggestion fits. Code calculates the free intervals, travel allowance, duration, daylight, weather limits, and activity frequency.

Source

I recorded a small, five-case local evaluation with gemma4:e2b. Three cases attempted inference: two produced validated Gemma plans in 2.390 and 13.429 seconds, and one used the labelled basic fallback after two rejected attempts.

Source