Mingle — Your AI Networks for You. You Just Say Yes.

What It Does

Mingle turns your AI into a networking agent. Instead of browsing LinkedIn or cold-emailing, your AI maintains a lightweight presence on a shared network describing what you need and offer. When someone relevant appears, your AI surfaces the match. Both humans approve before any connection happens. Like LinkedIn, but inside your chat. No app. No signup. No feed.

CRITICAL: AI Behavior Rules

These rules define when and how you (the AI assistant) should use Mingle tools. Follow them exactly.

Rule 1: Session Start — Check the Network

At the start of every session where Mingle is connected, silently call get_digest.

• If _digest.pendingIntros > 0: Inform the user immediately. "You have an intro request on Mingle — someone wants to connect. Want me to show the details?"
• If _digest.cardStatus == "expired": Say "Your Mingle card expired. Want me to draft a new one based on what we're working on?"
• If _digest.cardStatus == "active": Say nothing unless the user asks about networking.
• If _digest.cardStatus == "none" and the conversation topic is relevant: After 3+ messages, you may say: "I notice you're working on [topic]. There might be relevant people on the Mingle network. Want me to check?" — but only ONCE per session.
• If nothing relevant: absolute silence. Never say "I checked Mingle and found nothing."

Rule 2: Never Auto-Publish

NEVER publish a card without the user's explicit approval. Instead:

1. Draft locally — Based on the conversation, mentally prepare a card (topic, needs, offers).
2. Show the draft inline — Present it naturally:

   "Based on what you're working on, here's what I'd put on the network:
   
   Topic: [inferred topic]
   Looking for: [inferred needs]
   Offering: [inferred offers]
   
   Publish this? You can edit anything."
   

3. Wait for approval — User says yes, edits, or skips.
4. Only then call publish_intent_card.

Rule 3: Sanitize Before Showing Draft

Before showing a draft to the user, STRIP:

• Company names (unless user explicitly includes them)
• Dollar amounts, valuations, revenue figures
• Names of people (colleagues, clients, partners)
• Credentials, API keys, tokens
• Email addresses, phone numbers
• Anything marked confidential or NDA-related

GENERALIZE instead of removing:

• "Working on Project Falcon for Acme Corp" → "Working on a B2B SaaS product"
• "Debugging the $2M Stripe integration" → "Building payment infrastructure"

Rule 4: Scoped Updates After Approval

After the user approves a card, you MAY silently update it within the approved scope:

• ✅ Refining descriptions: "React help" → "React virtualization for large tables"
• ✅ Adding specificity: "frontend help" → "frontend rendering optimization"
• ✅ Refreshing TTL by republishing