{
  "$schema": "https://promptfoo.tech/schemas/workflow-template.json",
  "name": "AI Agent: Personal Inbox Triager",
  "slug": "ai-agent-personal-inbox-triager",
  "platform": "Agent",
  "category": "ai-agents",
  "difficulty": "Advanced",
  "tags": [
    "agents",
    "email",
    "productivity"
  ],
  "summary": "An agent that reads new email, drafts replies for low-stakes threads, files reference material, and escalates anything that needs a human in under an hour.",
  "overview": "Inbox zero via agent isn't magic — it's a small number of well-scoped tools and a strict policy about what the agent can send without approval. This design pattern uses read + classify + draft + file, with sending gated behind explicit human approval.",
  "variables": {},
  "steps": [
    {
      "order": 1,
      "name": "Define the policy",
      "description": "Write a one-page policy: what the agent can draft, what it must escalate, and forbidden actions (no sending, no calendar changes, no unsubscribes)."
    },
    {
      "order": 2,
      "name": "Pick your stack",
      "description": "OpenAI/Anthropic + a Gmail tool via MCP or Zapier + a Notion tool. Keep the toolset small."
    },
    {
      "order": 3,
      "name": "Build the classifier prompt",
      "description": "A single system prompt with your policy, example classifications, and a JSON output schema."
    },
    {
      "order": 4,
      "name": "Wire the actions",
      "description": "Each classification maps to one tool call. Drafts go to Gmail drafts; FYI applies a label; reference writes to Notion."
    },
    {
      "order": 5,
      "name": "Add the morning digest",
      "description": "A scheduled job posts a digest to Slack/email with counts, drafts to review, and any escalations."
    },
    {
      "order": 6,
      "name": "Run it in shadow mode first",
      "description": "For a week, log what it would have done without acting. Read the log daily and tune the policy before enabling actions."
    }
  ],
  "howItWorks": [
    "Trigger: every 15 minutes during work hours.",
    "The agent lists new mail with a Gmail tool, classifies each into: reply-needed, FYI, reference, spam.",
    "For reply-needed with low stakes (scheduling, thanks, confirmations), it drafts a reply into Drafts — never sends.",
    "FYI is archived with a label. Reference is filed to Notion with a summary. Spam is reported.",
    "A morning digest lists what was done and any drafts waiting for your review."
  ],
  "benefits": [
    "Recovers 30–60 minutes a day of shallow inbox work.",
    "Never sends without approval, so risk is bounded.",
    "Filed reference material becomes searchable in your knowledge base."
  ],
  "useCases": [
    "Founders drowning in intros and scheduling threads.",
    "Consultants juggling many low-context client emails.",
    "Anyone whose inbox is 80% noise and 20% signal."
  ],
  "example": null,
  "faqs": [
    {
      "q": "What model should I use?",
      "a": "A mid-tier model (GPT-4o-mini, Claude 3.5 Haiku) is fine for classification. Reserve larger models for drafting the trickier replies."
    },
    {
      "q": "How do I keep it from making things up?",
      "a": "Structured outputs plus refuse-when-unsure prompts. Never let the agent invent facts about the sender."
    },
    {
      "q": "Is this safe to point at a shared inbox?",
      "a": "Only after weeks of shadow-mode runs. Shared inboxes have higher stakes and more edge cases."
    }
  ],
  "source": "https://promptfoo.tech/workflows/ai-agent-personal-inbox-triager",
  "updated": "2025-05-08",
  "license": "CC-BY-4.0"
}