Chore Starter：AI 負責準備，最後決定權仍在用戶手上

This is a submission for the Hacktoberfest Open-Source AI Challenge Week 3: Slow and Steady

What I Built

Some tasks aren’t difficult. They’re just annoying to start.

Ask for a refund. Write an awkward message. Figure out how to tackle the pile on your desk. You know it needs doing, but opening a blank document feels like more work than the task deserves.

Chore Starter is a minimal AI personal assistant for that first bit of effort.

Give it the messy version:

“My headphones arrived with a cracked headband. Help me ask for a replacement without sounding rude.”

It prepares an editable email, message or practical plan, alongside a short checklist and the details you still need to supply. Missing information stays as a placeholder—not an invented order number or a promise the shop never made.

The important part: preparation is not permission.
Chore Starter can prepare everything, but copying, downloading or opening an email draft requires a separate preview and confirmation. It never sends email, makes purchases, submits forms or schedules things.

The interface is deliberately small: one task box, one prepared result, and a few clear next steps. Previously prepared tasks stay on your machine, so you can come back later.

A simple walkthrough:

1. Describe a chore, such as asking for a replacement.
2. Review the draft and fill in the missing details.
3. Click Copy draft or Open email draft.
4. Inspect the exact content in the confirmation dialog.
5. Cancel—or explicitly confirm.

Opening an email draft only hands it to your email app. You still review and send it yourself.

Code

MasterFloppa / Chore-Starter

A local AI assistant that prepares the chores you put off. Nothing leaves without your confirmation.

Chore Starter

Give it the task. Get the first draft. You stay in charge.

A minimal, local-first AI personal assistant for the chores you keep putting off. It prepares a useful draft and a small checklist from a plain-language task. Nothing is sent, submitted, purchased or scheduled automatically.

Built for the Hacktoberfest Open-Source AI Challenge, Week 3: Slow and Steady.

Status

Initial project scaffold. Application implementation follows this commit.

License

MIT

Chore Starter uses a locally installed Ollama model. The default is gemma3:4b.

How I Built It

The stack is React + Vite, TypeScript + Hono, and Gemma 3 4B through Ollama.

There are two deliberately separate parts:
Preparation: Gemma turns the request into a structured response: the draft, a short checklist, and missing information. It has no tools, account credentials or ability to perform the chore. The response is validated before it becomes a saved task.

Permission: ordinary application code controls the next step. The model cannot approve its own output.

For each action, the server creates a short-lived confirmation tied to:

• the task;
• its current revision;
• the specific action;
• the exact content being reviewed.

Edit the draft, and the old approval stops working. Cancel it, and it cannot be used. Confirm once, and it cannot be replayed.

That matters more than a reassuring “Are you sure?” button. The server—not just the interface—enforces the boundary.

The available actions are intentionally modest:

• Copy draft: copies the reviewed text.
• Download task: downloads a Markdown file with the draft and checklist.
• Open email draft: opens the chosen recipient, subject and body in your email app without sending it.

Tasks are stored locally. Model failures produce an explicit error rather than a pretend-success response.

The automated checks cover the important boundaries: missing confirmation, cancellation, expiry, changed drafts, repeated confirmation, stale edits, persistence and failed model calls.

Why Does Open Innovation Matter?

The task can stay where it started. A refund request, personal message or household chore may include information I don’t want to upload to another AI service. Gemma runs locally through Ollama; the app does not need a hosted AI API key.

A small model is enough for a small job. I’m not asking it to operate my computer. I’m asking it to turn rough context into a useful first draft. Keeping the scope narrow makes a locally running 4B model a practical choice.

The permission boundary is inspectable. Anyone can read the application code and see that the model’s output does not trigger a send, payment or background action.

The model is replaceable. An installed Ollama model can be selected in Settings. The app’s confirmation rules remain the same regardless of which model prepares the text.

Open weights provide the language layer. Open application code makes the limits visible.

The Lazy Payoff

The payoff is getting past the blank page.

Instead of thinking through tone, structure, missing details and the next step separately, you describe the task once and review something concrete.

It does not eliminate your judgment. It eliminates some of the preparation that makes small chores feel bigger than they are.

I’m not claiming a measured number of minutes saved yet. The intended trade is simple: less time getting ready to do the thing, while keeping control over actually doing it.

Prize Categories

• Best Use of Gemma: Gemma 3 4B prepares the draft, checklist and missing-information prompts locally through Ollama.
• Best Use of GitHub Copilot: GitHub Copilot was used as the coding agent to build the app and its automated checks.