💡 New script: gmail-ai-triage (Gemini-powered inbox classifier)

[github-actions[bot]]

Summary

Add a new catalog script — gmail-ai-triage — that uses Gemini (via the Apps Script Vertex AI Service) to automatically read incoming Gmail messages, classify them against a user-defined set of categories, and apply the matching Gmail label. Configuration is a list of { labelName, description } pairs entered via Step 4 of the deploy page. This is the open-source, browser-deployable, single-Google-account answer to the n8n / Lindy / Shortwave AI-triage workflows.

Market Signal

AI email triage is the single most-cited workflow in 2026 no-code automation roundups. The n8n-email-ai-agent repo exists specifically as "AI-powered Gmail email triage workflow … automatically classifies emails, applies labels, and drafts AI responses." Lindy and Gumloop's 2026 Gmail-AI-assistant comparisons rank this exact workflow as their #1 use case. Every alternative requires either a paid SaaS subscription, a self-hosted n8n instance, or a developer-grade setup. None offer "click Deploy in a browser, sign in with Google, done."

User Signal

The current catalog has only label-consuming automations (gmail-to-drive-by-labels). There is a pre-existing assumption that the user already curates their labels manually. Closing the loop by generating the labels in the first place is the obvious next move and the natural pairing for the existing label-archive script. No specific issue requests this yet, but the gap is structurally visible: the catalog has a label consumer and no label producer.

Technical Opportunity

Every architectural piece is already in place:

• Catalog-native extensibility is documented in the PRD as a deliberate design ("the deploy page is architected as a script host, not a script-specific UI"). calendar-to-briefing-doc is already cited as proof that adding a new script inherits the deploy/configure flow for free.
• The dual-layer pattern (code.gs + src/index.js + injected GAS services) is the documented standard, and the new script would follow it exactly.
• Step 4's schema-driven config form already supports adding new field types — a multi-row (labelName, description) editor is a straightforward addition mirroring the existing label-to-folder UI from gmail-to-drive-by-labels.
• The Vertex AI Service handles the model call with no extra dependencies.
• A time-based trigger every N minutes mirrors the trigger pattern from existing scripts.

Assessment

Dimension	Score	Rationale
Feasibility	high	Pure composition of patterns the project already proves work — no new infrastructure, no new test patterns, no new OAuth scopes beyond what gmail.modify adds
Impact	high	Adds the most-requested AI workflow in the entire adjacent market to the catalog as the third script; pairs naturally with the existing label-archive script to form a complete inbox-management story
Urgency	high	AI Gmail triage is where the no-code automation market is investing in 2026; the open-source GAS catalog is currently absent from this conversation

Adversarial Review

Strongest objection: "Auto-labeling email is a destructive operation against the user's most personal inbox — one bad classification and the user loses trust forever. The blast radius is too high for an automation that runs on a trigger."

Rebuttal: Mitigate at the design level, not by abandoning the feature. (1) Default to dry-run: the first deploy runs in shadow mode for N days, writing what it would have labeled to a Drive Doc instead of touching Gmail. (2) Apply, don't move: only add labels, never remove them, never archive, never delete. (3) User-defined scope: restrict processing to a single source label (e.g. INBOX or a user-chosen filter) rather than the whole mailbox. (4) Explainability: optionally append the model's one-line reason to the email as a label like ai-triage/<reason> so the user can audit. The combination — additive-only labels + opt-in scope + dry-run default — keeps blast radius small while still delivering the feature.

Suggested Next Step

Create a product brief covering: trigger model and quota budget, dry-run mode design, the (labelName, description) schema for SCRIPT_CATALOG, the Vertex AI prompt template, and the test plan for mocking Gmail + Vertex services together. Validate the dry-run output on a real personal inbox before promoting to live mode.

---

Proposed by the BMAD Analyst (Mary) on 2026-04-07.
Workflow run

[github-actions[bot]]

Weekly Update

What Changed

Critical competitive landscape shift — repositioning needed:

• Gmail AI Inbox launched (2026): Gmail now natively filters unimportant emails using AI, directly competing with the core value proposition of a standalone AI triage script. This is available to paid Workspace users.
• Google Workspace Studio launched (Dec 2025): Users can now build custom email triage agents using natural language — no coding required. This is a direct competitor for the "custom classification" angle.
• Gemini API accessible from GAS: The Vertex AI advanced service makes Gemini calls from Apps Script straightforward (no API keys needed). For free-tier users, UrlFetchApp + Gemini API key from AI Studio (free tier available) is the alternative path.
• AI email add-on installs grew 200% in the Workspace Marketplace (2023–2025): The market demand is validated but Google is now capturing much of it with native features.
• Superhuman acquired by Grammarly (June 2025): The premium email AI market is consolidating, pushing users toward either Google's native features or expensive all-in-one solutions.
• SaneBox, Shortwave, alfred_ remain viable: Third-party AI email tools at $5–25/month prove the market exists, but all require subscriptions.

Updated Assessment

Dimension	Previous	Current	Delta
Feasibility	med	med	→ Gemini API access improved but classification design complexity remains
Impact	high	med	↓ Gmail AI Inbox and Workspace Studio cover the primary use case for paid users
Urgency	high	med	↓ Google's native features reduce the gap this script was designed to fill

Recommendation

Keep watching with repositioned targeting — The idea remains viable but must differentiate from Gmail's native AI:

1. Target free-tier Google account users who have NO access to AI Inbox or Workspace Studio — this is the underserved segment
2. Customizable classification with user-defined categories (e.g., "client emails," "newsletters," "action required") rather than Gmail's fixed categories
3. Action-oriented triage: Not just classification but automated actions (apply labels, forward to team, archive, create tasks) — going beyond what AI Inbox offers
4. Output flexibility: Triage results can go to a Google Sheet (for review/override), labels, or forwarding rules

The urgency has decreased, but the free-tier gap and action-oriented differentiation keep this alive. Recommend advancing only after the higher-priority ideas (drive-file-organizer, gmail-digest) are underway.

[github-actions[bot]]

Weekly Update — Retirement Recommendation

What Changed

PR #649 (feat(classifier): Gmail AI Semantic Classifier with Ontological Knowledge Graph & Drive Ingestion) shipped src/gmail-ai-classifier/. It is a Gemini-powered inbox classifier with 7 canonical domains, deterministic fast-path rules, auto-created Gmail filters, a daily audit and retention. PRs #652, #655, #657, #661 and #664 have extended it since. That is the capability this idea proposed.

Updated Assessment

Dimension	Previous	Current	Delta
Feasibility	—	Shipped	↑
Impact	—	Delivered by gmail-ai-classifier	→
Urgency	—	None (implemented)	↓

Recommendation

Retire / close as implemented. The open follow-ups now have their own threads: privacy-safe AI path (#672), correction-learning loop (#673), golden-set eval harness (#674) and deploy-page onboarding for the AI scripts (#675). Recommending closure only; this Discussion has not been closed.