Proactive AI visualization

Proactive AI

Surfacing What You Need Before You Ask

Nick Brandt June 2025 12 min read

Abstract

Every AI assistant today works reactively: user asks question, AI processes, AI responds. But the most valuable information is often what you didn't know you needed. Proactive AI monitors context—calendar, screen, location—and surfaces relevant information before users ask. This paper presents an architecture for anticipatory AI that feels intelligent rather than merely responsive.

Two-panel comparison: Reactive AI shows user initiating question then receiving answer; Proactive AI shows context triggering AI to surface information to user
Reactive AI waits for questions. Proactive AI anticipates needs based on context.

1. The Reactive AI Problem

Every AI assistant today works the same way:

  1. User asks question
  2. AI processes
  3. AI responds

This is fundamentally reactive. The AI waits for you to know what to ask.

But the most valuable information is often what you didn't know you needed.

Reactive AI

User initiates:

"Hey Siri, what's on my calendar today?"

AI responds:

"You have a meeting with John at 2pm."

Proactive AI

[No prompt required]

"You're meeting John at 2pm. Last time you discussed the Henderson project. He mentioned concerns about timeline. Here's what you promised to follow up on."

The AI anticipates the question and surfaces relevant context before you ask.

2. Context Triggers

Proactive surfacing is triggered by context changes:

Radial diagram showing AI in center surrounded by context triggers: Calendar, Email, Document, Clock, Screen
Multiple context sources trigger proactive information surfacing.
Trigger What to Surface
Calendar event approaching Related facts, previous interactions, commitments made
Email from contact Relationship history, pending items, shared context
Document opened Related documents, previous versions, collaborator notes
Location change Location-relevant information, nearby contacts
Time-based Daily review, upcoming deadlines, expiring commitments
Screen content Information related to what you're currently viewing

3. The Meeting Prep Example

Traditional Workflow

  1. See meeting on calendar
  2. Wonder what it's about
  3. Search email for context
  4. Search notes for background
  5. Try to remember what was discussed last time
  6. Go into meeting unprepared anyway

Proactive Workflow

  1. 15 minutes before meeting, notification appears
  2. "Meeting with John (Henderson Project)"
  3. Summary of last interaction
  4. Commitments you made ("send updated timeline")
  5. His recent concerns (from your notes)
  6. Documents you both referenced

The Key Insight

No search. No recall effort. Context is ready. The AI knew what you'd need because it understood the relationship between calendar events, contacts, and your knowledge base.

4. The Commitment Tracker

People make commitments constantly:

Most are forgotten. A proactive system:

  1. Detects commitment language in conversations
  2. Extracts deadline (explicit or implied)
  3. Tracks status (pending, completed, overdue)
  4. Surfaces at relevant moments

Proactive Notification

"You told Sarah you'd send the proposal by Friday. It's Thursday and you haven't sent it."

5. The Knowledge Graph Foundation

Proactive surfacing requires understanding relationships:

Knowledge graph visualization showing nodes and edges: Email mentions John, John works_on Henderson Project, Project has_deadline March 15, You committed_to John to send timeline
Knowledge graph traversal finds relevant information based on entity relationships.

When you have a meeting with John, the graph traversal finds:

6. Privacy Implications

Proactive AI requires deep context awareness:

This is precisely why on-device processing matters:

All Analysis Local

Processing happens on your device, not in the cloud

No Screen Content Transmitted

What you're viewing stays on your machine

No Email Content Sent

Your communications remain private

Context Stays Private

Your knowledge graph never leaves your device

Proactive AI without privacy guarantees is surveillance. With on-device, it's assistance.

7. The Interruption Balance

Proactive doesn't mean intrusive. Design principles:

Do Surface:

Don't Surface:

8. Implementation Architecture

Vertical architecture diagram showing four layers: Context Monitor (inputs), Relevance Engine (graph/decay/importance), Surfacing Decision (threshold/timing), Output (notification/sidebar)
Four-layer architecture for proactive AI: monitor, evaluate, decide, surface.
┌─────────────────────────────────────────┐ │ CONTEXT MONITOR │ │ ├── Screen capture (OCR) │ │ ├── Calendar events │ │ ├── Active application │ │ └── Time/location │ └─────────────────┬───────────────────────┘ │ ▼ ┌─────────────────────────────────────────┐ │ RELEVANCE ENGINE │ │ ├── Graph traversal │ │ ├── Temporal relevance (decay) │ │ ├── Importance scoring │ │ └── User preference weighting │ └─────────────────┬───────────────────────┘ │ ▼ ┌─────────────────────────────────────────┐ │ SURFACING DECISION │ │ ├── Threshold check │ │ ├── Interruption budget │ │ ├── Deduplication │ │ └── Timing optimization │ └─────────────────┬───────────────────────┘ │ ▼ Notification / Sidebar

9. Measuring Proactive Value

Metric What It Measures
Surfacing precision % of surfaced items user found useful
Information discovery Items surfaced user didn't search for
Time saved Avoided searches due to proactive surfacing
Commitment tracking Reminders that prevented missed items
Dismissal rate Items surfaced but ignored (too aggressive?)

10. The Shift in AI Interaction

Generation 1: Keyword search

Generation 2: Natural language query

Generation 3: Proactive surfacing

Each generation reduces the burden on the user to know what to ask.

11. Conclusion

Proactive AI is the realization that the best interface is no interface—information appears when relevant.

By combining context monitoring, knowledge graphs, temporal relevance, and on-device privacy, we can build AI assistants that don't just answer questions but anticipate needs.

The goal isn't an AI that responds better. It's an AI that makes asking unnecessary.

Further Reading

Want to know more about proactive AI? Contact me, I'm always happy to chat!

Back to White Papers