Decisions Affinity makes

Affinity builds and optimizes journeys through two types of intelligence: design-time intelligence builds the initial journey, and run-time intelligence optimizes it after launch.

Design-time intelligence

When you provide a prompt, Affinity consults a knowledge base to ensure your journey is founded on proven best practices.

Learning from annotated journeys

At the core of Affinity's intelligence are annotated datasets—thousands of high-performing journeys executed within Bloomreach Engagement that teams have systematically analyzed and labeled.

Annotation means each journey component—audience definitions, trigger events, timing delays, and content structure—has been tagged with information about what it does and how it performs. This structured knowledge helps Affinity understand not only individual elements but also how they work together to drive results.

Context-specific insights

Affinity combines large language model (LLM) knowledge with insights tailored to your context:

• Industry: Fashion retailers send reactivation journeys with discount offers, while B2B software focuses on feature updates and usage tips.
• Region: European journeys typically send during business hours (9 AM-5 PM local time) with formal messaging, while US journeys favor evening sends with casual tone.
• Use case: Abandoned Cart journeys can repeat multiple times per week, while newsletters are sent on a fixed schedule.

Learn more about how to provide effective context in your prompts. For details on design-time intelligence boundaries, see the AI optimization section in Affinity limitations.

Run-time intelligence

Journey launch starts the learning process. Run-time intelligence automatically refines journeys based on real-time customer behavior.

Self-optimization and learning

Affinity continuously improves performance after launch. It experiments with strategies—like adjusting send times—to learn what drives clicks and purchases. Journeys automatically adapt to what works best for your audience.

Dynamic wait-time adjustment

Applied to Abandoned Cart and Browse Abandonment journeys, this feature replaces fixed delays with intelligent timing. Affinity analyzes each customer's context—cart value, purchase history, browsing behavior—to determine the optimal follow-up moment.

This optimization is enabled automatically during journey brief generation for supported use cases. To learn more about wait-time options, see Wait node in Affinity journey brief and generation.

Optimization cycle

Optimization operates in three steps:

1. Decide: Affinity chooses optimal wait time based on customer context.
2. Act: Affinity calculates the delay and sends the message.
3. Learn: Affinity analyzes the outcome and feeds results back into the model.

This makes journeys smarter with every interaction, without manual intervention.

For details on run-time intelligence scope and limitations, see the AI optimization section in Affinity limitations.

To see how optimization impacts performance metrics, learn about launching and monitoring journeys.