Product Discovery for Ecommerce: Context, Personalisation and AI

Reasons to listen:

1. Learn how product context and knowledge graphs can improve search relevance.
2. Understand which shopper behaviours signal genuine intent and which may be noise.
3. Get practical ideas for testing merchandising choices and deciding where AI needs human oversight.

How can ecommerce websites help shoppers find the right products when they don’t know exactly what to search for?

In this episode, James Gurd talks with Max Etheridge, Voyado’s Director for the UK and Ireland, about improving product discovery through richer product data, customer context and thoughtful use of AI.

They discuss why conversational search alone can’t fix weak product data, and how ontology and knowledge graphs connect products to categories, occasions and shopper needs.

That context can help a site understand a search like “something to wear to a summer wedding” and surface relevant products, even without an exact product description match.

The conversation also explores how ecommerce teams can distinguish meaningful purchase intent from passing interest. Repeated behaviours, such as refining searches, revisiting products or adding items to a wishlist, can be more informative than a single page view.

Combining those signals with product knowledge helps make personalisation more relevant to what a shopper wants now, rather than simply repeating what converted before.

James and Max examine practical ways to test product discovery, from mobile-versus-desktop strategies and filter layouts to content and product placement on category pages.

They also discuss who should control those decisions: algorithms can handle high-volume, lower-risk tasks, while people should retain oversight of brand-sensitive choices. Transparent reasoning and A/B testing help teams learn what works instead of relying on opinion.

Finally, they consider agentic search, the role of human merchandisers, and whether AI will change how teams use ecommerce platforms. One point runs through the discussion: new AI features are only useful when they solve real customer problems and have strong data and context underneath.

Chapters:

• [00:30] Introduction: product discovery, customer context and AI
• [03:45] Why context matters in ecommerce product discovery
• [07:00] Ontology and knowledge graphs explained
• [12:30] Reading shopper intent from behaviour
• [14:10] Personalisation beyond repeating past purchases
• [17:00] Who controls product discovery?
• [22:40] A/B testing merchandising strategies
• [25:20] Testing mobile experiences, filters and PLPs
• [30:30] Where AI should and shouldn’t make decisions
• [33:20] Agentic search and conversational discovery
• [37:05] Bringing content into product discovery
• [39:05] AI, user interfaces and the future of merchandising
• [46:40] Product roadmap and AI-first workflows
• [50:35] AI costs, guardrails and practical value

tl;dr What you'll learn:

• Why transparent delivery promises can influence conversion, trust and loyalty.
• How delivery choices, pricing, customer value and returns affect profitability.
• What to consider when deciding whether to build or buy delivery capabilities—and where AI may help.

Delivery’s often treated as a cost to contain but it also shapes whether customers trust a brand, complete a purchase and come back. In this conversation, James Gurd and Fraser Trivett, CRO at Ingrid, explore how ecommerce businesses can rethink delivery as both a customer experience and a profit-centre opportunity.

The key is to make delivery promises clear, accurate and suited to customers’ needs. Hidden costs or missed promises can undermine trust, while well-chosen delivery options can help reduce checkout friction and support healthier margins.

The discussion covers using customer and product data to make more strategic decisions, weighing build-versus-buy choices and how AI can help businesses act on delivery insights faster.

Kibo: A unified, model-agnostic approach to agentic commerce For B2B and B2C

tl;dr

• Understand why unified data and one AI interface can outperform a fragmented collection of point agents.
• See how model-agnostic AI and “bring your own LLM” architecture reduce vendor lock-in and give commerce teams more control over cost and flexibility.
• Learn how Playbooks automate everyday commerce tasks while preserving human oversight, permissions and accountability.

Eric Rosado’s return to Kibo as Chief Product Officer comes at a pivotal moment for ecommerce technology. After previously serving as Kibo’s VP of Product and spending three years as CPO at Monetate, Eric returned to help shape Kibo’s next phase of product innovation, as AI accelerates software development and the way commerce teams operate.

The vendor market is evolving rapidly. AI is enabling companies to build faster but that creates new challenges: deciding what to build, keeping pace with constant model innovation and helping customers navigate a crowded market where vendors often promise similar capabilities.

Product teams must now design not only for customer experience, but also for “agent experience”, making their platforms easy for AI agents to understand and use.

That thinking is central to Kibo AI, Kibo Commerce’s newly available agentic layer. Rather than exposing customers to a growing collection of individual agents, Kibo AI brings nine specialised agents together behind one unified interface spanning commerce and order management.

Its unified data model and API-first architecture allow agents to work across catalogue, pricing, promotions, inventory, routing, fulfilment and orchestration without forcing users to understand the underlying complexity.

Kibo AI is also model agnostic. Through its “bring your own model” architecture, customers can use OpenAI, Anthropic, Gemini or open-weight models according to their existing technology strategy, performance requirements and budget.

This flexibility helps avoid vendor lock-in and gives businesses greater control as model capabilities and token costs continue to change.

Our conversation also explores Playbooks: plain-language automations that run on triggers or schedules. They can monitor new products for missing content, flag fulfillment risks, generate reports and connect with external services such as translation engines or Slack.

It's important that we emphasise human oversight. AI can analyse, explain and prepare actions, but permissions, audit trails and approval steps remain in place, helping commerce teams automate repetitive work without surrendering control.