Overview Background Design Thinking Experiment Final Design

Subject Line Assist

Subject Line Assist Cover

I designed and introduced a proactive, inline AI interaction pattern for Subject Line Assistant that increased AI adoption by . I led the proactive vs. reactive AI experiment, focusing on improving adoption through interaction design.

Role
Product Designer (AI)
Company
Klaviyo
Focus
Interaction Design, Experimentation

Background

Marketers need to write subject lines that drive engagement and conversions without slowing down their workflow. However, Klaviyo's Subject Line Assistant was used in only ~1.7% of messages, indicating a disconnect between AI capability and usability.

Business Problem

User Problem

Constraints

Design Thinking

My goal was to redesign Subject Line Assist to meaningfully reduce cognitive load, improve relevance and brand alignment, and increase adoption toward a ~5% target of messages using AI-generated subject lines.

Concept Exploration

I started by exploring multiple design directions before converging on the final approach:

Keyword-Based Prompting

Keyword-Based Prompting

Allowed users to guide AI with keywords, but created uncertainty around intent, accuracy, and how outputs were generated.

Toolbar-Based AI Controls

Toolbar-Based AI Controls

Enabled actions like regenerate, refine tone, and A/B testing with fewer clicks. While more efficient, it still required explicit activation and added UI complexity.

Performance-Informed Suggestions

Performance-Informed Suggestions

Surfaced past subject lines with open rates, increasing trust but raising concerns around data clarity and echo-chamber effects.

Key Insight

Across concepts, a consistent pattern emerged: users wanted flexibility and relevance but were unwilling to take extra steps to access AI.

Guiding principle: Guidance without friction.

Experimentation

Experimentation and testing: To validate the direction, I designed and shipped a set of experiments. These experiments isolated the impact of proactive vs. reactive AI and inline vs. modal interactions, allowing us to directly measure how interaction patterns influenced discovery, adoption, and usage.

Experiment 1 → Control: Existing modal-based Subject Line Assistant

Control — Modal SLA

Experiment 2 → Variant B: Reactive AI accessed via a sparkle icon with regenerate controls

Reactive AI

Experiment 3 → Variant C: Proactive, inline AI that surfaced suggestions as users typed

Proactive Inline AI

Experimentation Takeaway

Proactive, inline AI clearly outperformed reactive and modal patterns—driving ~6× higher message-level adoption (1.5% → 8–9%) and ~8× higher account-level adoption (3% → 24%).

The core insight: interaction design, not AI capability, was the constraint. Surfacing in-context suggestions with low-friction regenerate unlocked sustained, meaningful usage and validated proactive inline AI as the default pattern for scaling adoption.

Final Design, Impact & Takeaways

The winning solution was proactive, adaptive autocomplete embedded directly into the subject line field.

Key Interactions

Impact

~1.5% → ~8–9%
Message-level adoption (≈6× increase)
~3% → ~24%
Account-level adoption (≈8× increase)

Additional impact included increased meaningful AI usage in live campaigns and flows, improved trust and repeat usage, and validation of proactive inline AI as a scalable pattern across Klaviyo.

Takeaways & Challenges

Designing Proactive AI Without Being Intrusive

  • Tuned suggestion timing to avoid disruption
  • Clear cancel and regenerate controls for user agency
  • AI never blocked or overrode manual input

Data Limitations

Limited historical data risked generic outputs, addressed through graceful degradation and clear expectation-setting.

Cross-Functional Alignment

Success required tight alignment with Product, Data Science, and Engineering on hypotheses, metrics, and experiment design.