What stores actually use the agents for
Not abstract capabilities — specific jobs. Each use case describes a problem merchants recognise, how the agents divide the work, and what done looks like.
The pages in this section each cover one recurring job in running a store: recovering abandoned carts, keeping a large catalogue findable, getting lifecycle email past the welcome flow, preparing for peak season. Every page explains which agents take the work, how they split it, and — just as important — what the honest limits are. If you recognise the problem, the page will tell you what handing it to the team looks like.
Abandoned cart recovery
Recover the orders that got to checkout and stopped, with timing built from your own buying cycle.
Learn more →Product page optimisation
Rebuild the pages that decide whether a visit becomes an order, ranked by revenue at stake.
Learn more →Conversion rate optimisation
Find where the funnel leaks, fix the cause, and measure whether it actually moved.
Learn more →E-commerce SEO at scale
Metadata, structured data, and content across a whole catalogue — not just the top twenty pages.
Learn more →AI search visibility
Get mentioned and cited when shoppers ask ChatGPT, Perplexity, or Google AI Overviews what to buy.
Learn more →Product description writing
Descriptions written per product from real attributes and reviews — not manufacturer boilerplate.
Learn more →Collection page SEO
Turn empty category grids into pages that can rank for the terms with real purchase intent.
Learn more →New product launch
Launch a product across page, email, and search on the same day instead of over three weeks.
Learn more →Peak season readiness
Get the store, the infrastructure, and the campaigns ready before the traffic arrives.
Learn more →Email flow automation
Complete lifecycle coverage, built once and then actually maintained.
Learn more →Win-back campaigns
Re-engage lapsed customers using your real churn window instead of a round number.
Learn more →Customer segmentation
Segments built from purchase behaviour, not from generic engagement windows.
Learn more →Post-purchase upsell
Raise repeat rate and order value in the window after purchase, without souring the experience.
Learn more →Site speed optimisation
Find what actually slows real users down, fix it, and stop the regressions that undo it.
Learn more →A/B testing
Test the genuinely uncertain decisions, sized honestly, instead of testing everything badly.
Learn more →Merchandising automation
Collection order, featured products, and promotions driven by stock and performance, not by memory.
Learn more →Store localisation
Sell properly in more than one language — localised pages, correct hreflang, per-market SEO.
Learn more →B2B quote requests
Turn a wholesale site into a pipeline: qualified RFQs in, fast structured follow-up out.
Learn more →Marketplace listing optimisation
Keep listings competitive on marketplace search, consistent with your store, and honest to spec.
Learn more →Paid ads landing pages
Stop sending paid clicks to generic pages. Build and iterate landing pages that match the ad.
Learn more →Analytics reporting
A weekly report that says what changed, why, and what was done about it — without a dashboard.
Learn more →Subscription retention
Reduce subscriber churn with intervention before the cancel, not a survey after it.
Learn more →Review & UGC management
Collect more reviews, answer them properly, and put them to work on pages and in search.
Learn more →Competitor monitoring
Know when competitors change pricing, positioning, or start winning the searches you care about.
Learn more →How to read these pages
Each use case names the agents involved and links to their pages, describes the working loop step by step, and closes with the questions merchants actually ask. The use cases also link to the step-by-step playbooks where one exists for the same job.
Where to start
Start from the job that costs you most today. For most stores that is one of three: cart and checkout leakage, catalogue pages that are invisible in search, or a lifecycle email programme that stopped at the welcome flow. Fixing any one of them typically pays for the exploration of the rest.
Frequently asked questions
Do these use cases require all five agents?
No. Each page names the agents actually involved — usually two or three. You can run a single use case with a smaller plan and expand from there.
Are these hypothetical scenarios?
They are the recurring jobs the product is built around — the descriptions are of how the agents divide and execute the work, not aspirational marketing scenarios.
What if my use case is not listed?
The agents are goal-driven rather than template-driven, so uncovered jobs are often still achievable. Contact us with the job and we will tell you honestly whether the team can run it.
How is a use case different from a playbook?
A use case describes a problem and how the agents work it. A playbook is a step-by-step programme for one specific outcome, with the sequence spelled out. Use cases link to their matching playbooks where one exists.
Put the team to work on your store
Connect your storefront, analytics, and email stack, set a goal, and let the agents run the work end to end. Start on the free plan with your own model key.