How it works
- Parse: Airstore sends your query to an LLM
- Translate: The LLM converts it to the source’s native query format (Gmail search syntax, GitHub filters, etc.)
- Execute: Airstore runs the query against the source API
- Materialize: Results become files in the folder
- Sync: Background process keeps the view fresh
Query examples
Good queries are specific and describe what you want:| Source | Query | What you get |
|---|---|---|
| Gmail | ”emails from investors in the last 30 days” | Recent investor correspondence |
| Gmail | ”unread emails with attachments” | Emails you haven’t opened that have files |
| GitHub | ”open PRs in acme/api with full diffs” | PR diffs ready for review |
| GitHub | ”issues labeled bug assigned to me” | Your bug backlog |
| Linear | ”high priority issues in the current sprint” | Urgent work items |
| Drive | ”PDF contracts from 2024” | Last year’s contracts |
| Notion | ”meeting notes from January” | Recent meeting documentation |
File structure
Smart folders contain files that represent query results:Sync behavior
Smart folders sync automatically in the background:- Sync: Periodic background refresh
- Consistency: Eventual (reads may be slightly stale)
- Manual sync:
airstore sync sources/gmail/investor-emails
Nested smart folders
You can create smart folders at any level:Limitations
Smart folders depend on what the source API supports:- Gmail: Supports most search operators (from, to, subject, date ranges, labels)
- GitHub: Supports filters on PRs, issues, repos
- Linear: Supports project, assignee, status, priority filters
- Drive: Supports file type, date, owner filters
- Notion: Supports database queries, page searches