# Strategies specifications
{% hint style="info" %}
Discover FairChic example at the end of the article. 
{% endhint %}
When you have provided AB Tasty with all the required access to create your environment, it is your dedicated time to list your specifications.
1. **Define recommendation strategies**
* Work with AB Tasty to specify which recommendation strategies to implement (e.g., “Most Popular,” “Recently Viewed,” “Similar Items”).
2. **Specify design preferences**
* Share your design requirements or brand guidelines for recommendation widgets.
{% hint style="info" %}
By treating the strategy specification step as a “mini project” in itself (not just selecting recommendation types, but defining *who*, *when*, *why*, *how*, and *how we’ll measure it)* you give yourself a much better shot at launching with clarity. Launching blind without those definitions would mean slower results and more guesswork.
{% endhint %}
#### Kim's fictional example for FairChic
> When we moved into the ‘Strategy Specifications’ phase with AB Tasty’s Recommendations & Merchandising, I treated it as the moment to decide *why* we were doing each recommendation block, *how* we would use it, and *what success* would look like. Here is how I worked this at FairChic.
> #### Goal and use-case
> **Goal**: Increase average order value (AOV) and conversion rate by surfacing highly relevant product recommendations and merchandising slots throughout the shopping journey.\
> **Use-case**: On product pages, we’ll show a “Complete the look” recommendation group (fashion-specific) and in our post-purchase email, show “You might also like” based on recent buys.
> For example: when a customer views a dress, our recommendation block would show complimentary items (shoes, accessories) instead of generic “similar dresses”. In the email after purchase, we’ll use the feed + user behaviour to suggest “customers who bought this also bought…” to drive a second purchase.
> #### Best practices applied
> From the AB Tasty Resources hub I pulled scope ideas for [e-commerce and fashion](https://www.abtasty.com/resources/). \
> Here are the best practices I built into our specification:
> * Define each recommendation slot with a **clear business objective** (e.g., increase cross-sell, reduce bounce, lift email clicks)—this aligns with “what you want to achieve” step.
> * Choose use-cases that map to real customer journeys (e.g., browse → product page → cart → post-purchase email) rather than random placements.
> * For each slot, specify **targeting logic**: who sees it (first-time visitor / returning customer / VIP), when (on view, on scroll, in cart), and what product feed or algorithm (similar items, best-sellers, high margin).
> * Make sure we set measurable **KPIs** for every slot: e.g., recommendation click-through rate, incremental revenue per visitor, AOV lift.
> * Ensure our product feed contains the required attributes (category, price, margin, availability, images) since good data underpins effective recommendations.
> * Plan for continuous monitoring and refinement: we built in a cadence for reviewing performance and adjusting logic, rather than “set and forget”.
> #### What I actually did
> * Sent a spreadsheet to my marketing and analytics leads listing all planned recommendation slots (homepage, category page, product page, cart abandonment email) plus objective + audience + feed logic.
> * Created a mapping for each slot to our product feed: identified which feed fields matter (e.g., “isAccessory”, “high\_margin”, “season”), cleaned the data accordingly.
> * Defined the KPIs with our analytics lead and controller: for example our target was a 10 % lift in cross-sell revenue within 90 days for the “Complete the look” slot.
> * Shared AB Tasty’s “Getting Started” doc with the team so everyone understood the capabilities and constraints.
> * Scheduled weekly check-ins with the AB Tasty CSM for the first month after go-live to capture early learnings and make tweaks.