Each email — or every email from a sender — runs through your prompts to find its folder.
Sender-level smart categories, one-click undo, multi-action rules. You control the AI.
Each email flows through your AI filter and lands in the right folder
Personal
From people I know personally or have emailed before
Spam & Sales
DeleteCold outreach, LinkedIn spam, or someone trying to sell me something
Favorite Shop Newsletter
StarDeals and updates from the shops I actually buy from
Waiting for emails...
on your LLM or oursA pragmatic toolkit, not a magic black box.
Categorize once per sender — every future email from them is sorted instantly, no extra LLM call.
Every AI decision is logged. Made a wrong call? Revert it with a single click.
Move, flag, mark-read and forward — chain several actions inside a single category.
Forward newsletters or vendor emails with an AI-generated summary instead of the raw mail.
See volume, top senders and category breakdown at a glance — know where your time goes.
Connect a mailbox, pick a preset, watch the AI sort your inbox — in under three minutes.
Try it free, then subscribe for unlimited email processing
or $60/year (save 17%)
Unlimited classifications
Process as many emails as you need
Bring your own LLM
OpenAI, Ollama, or any endpoint
Any email provider
Gmail, Outlook, any IMAP
200 free to start
No credit card required
Need more email accounts?
2 included, +$2.50/month each extra
The 200 free emails are a one-time trial to test the service. Subscribe anytime to continue with unlimited processing.
Common questions about AI-powered email filtering
AI email filtering uses Large Language Models (LLMs) to automatically sort and organize your emails based on context and meaning rather than simple keyword matching. You create custom email filters using natural language descriptions like "urgent client requests" or "newsletter subscriptions," and the AI intelligently categorizes incoming emails by understanding their content, sender, and intent.
We process each email to classify it (subject, sender and a short body preview are sent to the language model), but we only store the headline data long-term: subject, sender, date and the chosen category, so the History tab can show what happened and let you undo it. The full body of your emails is never persisted. With your own LLM no email content ever leaves your infrastructure.
Anything that speaks IMAP/SMTP — Gmail, Google Workspace, Outlook, Yahoo, ProtonMail, Fastmail, Mailcow, your own server. No migration needed. Note that Gmail/Workspace requires an App Password (we do not use OAuth).
Absolutely. Point us at OpenAI, Anthropic via a proxy, a local Ollama instance or any OpenAI-compatible endpoint. With BYOL no email content ever leaves your control and you pick the price/quality trade-off.
Yes. Every action — move, flag, forward, delete — is recorded in the History tab. One click reverts a move; you can re-run categories after editing the rules. Nothing the AI does is permanent.
The 200 emails are a one-time trial. After that you can subscribe for $6/month for unlimited processing. No emails are deleted — the system simply pauses classification until you upgrade.
Accuracy depends on how clearly your category prompts describe what belongs there. Sender-level smart categorization helps too: once a sender is classified the decision is cached, so future emails from that sender are sorted instantly and consistently. You can re-categorize any sender at any time.
We're here to help. For any questions, technical issues, or support requests, please email us at [email protected]. We typically respond within 24 hours. [email protected]
Recent insights and articles
Traditional email filters rely on rigid IF-THEN rules that break constantly. Learn why plain English AI filters deliver better email filtering for Gmail, Outlook, and Mailcow.
How small businesses can organize emails by client and project automatically – without an IT department and without spending hours maintaining filter rules.
Explore all articles and tutorials
Got questions, feedback, or just want to say hi? I'd love to hear from you!
