Create Your First Optimization

Define design factors, choose a model type, and link a reward metric to create a live optimization.

An optimization is the core unit in Levered. It defines what you are testing (design factors and their levels), how you measure success (a reward metric), and what model allocates traffic (MAB or CMAB).

Key concepts

Design factor -- A variable you want to optimize. Examples: headline, cta_text, hero_image.
Level -- A possible value for a design factor. Example: the headline factor might have levels "Ship faster", "Save time", and "Build better".
Variant -- A specific combination of levels across all design factors. With 3 headlines and 2 CTA texts, you have 6 variants.

Levered explores these variants automatically and shifts traffic toward the ones that produce the most reward.

Model types

Model	Best for	How it works
MAB (Multi-Armed Bandit)	Simple optimizations, small variant spaces	Treats each variant independently. Learns which variant wins overall.
CMAB (Contextual Multi-Armed Bandit)	Personalization, larger variant spaces	Uses context factors (device, location, user segment) to learn which variant works best for each type of user.

Start with MAB if you are new to Levered. Switch to CMAB when you want to personalize variant selection based on user attributes.

Create an optimization

Navigate to Optimizations and click Create Optimization.
Enter a name (e.g., "Landing Page Hero").
Add design factors:
- Factor name: headline
- Type: String
- Levels: Ship faster, Save time, Build better
- Click Add Factor and repeat for cta_text with levels Start free and Try it now.
Select the model type: MAB or CMAB.
Link a reward metric -- select the metric you created in the previous step (e.g., "Signup Conversion").
Click Create.

The optimization is now live. Once you integrate the SDK and start logging exposures and rewards to your warehouse, Levered will begin training on the next scheduled cycle.

What happens after creation

Once the optimization is live:

You integrate the SDK (next step) to request variants and log exposures.
Users see variants based on the bandit's current allocation.
Exposure and reward events land in your warehouse.
Levered trains on a recurring schedule, reads new data from your warehouse, and updates the model.
Traffic shifts toward variants with higher reward rates.

There is no manual "launch" or "stop" step. The optimization starts learning as soon as data flows.

Next step

Your optimization is created. Now integrate the SDK to start serving variants and logging exposures.