> For the complete documentation index, see [llms.txt](https://docs.abtasty.com/llms.txt). Markdown versions of documentation pages are available by appending `.md` to page URLs; this page is available as [Markdown](https://docs.abtasty.com/onboarding/recommendation-merchandising-and-search-quick-start-guide/strategies-specifications.md).
# 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.
---
# Agent Instructions
This documentation is published with GitBook. GitBook is the documentation platform designed so that both humans and AI agents can read, navigate, and reason over technical content effectively. Learn more at gitbook.com.
## Querying This Documentation
If you need additional information that is not directly available in this page, you can query the documentation dynamically by asking a question.
Perform an HTTP GET request on the current page URL with the `ask` query parameter, and the optional `goal` query parameter:
```
GET https://docs.abtasty.com/onboarding/recommendation-merchandising-and-search-quick-start-guide/strategies-specifications.md?ask=&goal=
```
`ask` is the immediate question: it should be specific, self-contained, and written in natural language.
`goal` is optional and describes the broader end goal you are ultimately trying to accomplish on behalf of the user. GitBook uses it to tailor the answer towards what is most useful for that goal.
The response will contain a direct answer to the question and relevant excerpts and sources from the documentation.
Use this mechanism when the answer is not explicitly present in the current page, you need clarification or additional context, or you want to retrieve related documentation sections.