The problem
Shared inboxes mix time-sensitive issues, invoices, and routine mail. A naive AI agent can route quickly but may also make a confident-looking mistake with no review trail.
The workflow classifies an incoming email as urgent, invoice, or routine—but AI never gets the last word when confidence is low.
Public demonstration using synthetic, mocked, or fictional data; not a paid-client result. Accounts and credentials are not included; the workflow uses buyer-supplied services.
Edit the subject lines — one per line — then run the triage. The classifier is keyword-deterministic and runs entirely in this page: no AI service is called and no inbox is connected. Write something the rules do not recognise and watch it stop at the gate instead of guessing.
Use synthetic sample data only. Do not enter confidential information, personal data, credentials, or customer records. Input stays in this page and is discarded on reload or close.
Shared inboxes mix time-sensitive issues, invoices, and routine mail. A naive AI agent can route quickly but may also make a confident-looking mistake with no review trail.
The model must return a fixed JSON schema: category, confidence, and one-sentence reason. Confidence below 0.70 bypasses automation and alerts a human-review queue.
Urgent messages alert the team, invoices move through filing and ledger steps, and routine messages are labeled. The workflow—not the model—chooses the allowed action.
The importable n8n JSON contains no credentials. Operators connect their own inbox, model, team-chat, storage, and sheet accounts after reviewing the nodes.
email → {category, confidence, reason} → confidence gate → route → decision logThe complete workflow is available as an importable starter kit. The same pattern can be adapted to lead intake, support queues, document review, or approval routing without claiming autonomous judgment.
Send the categories, exception examples, tools, and desired human-review rule.
[email protected]