In today's competitive ecommerce environment, understanding how your product range compares to competitors is critical to driving growth. Yet category analysis is often underutilised — largely due to the time and effort required to manually review competitor ranges, pricing structures and product depth.
Tools such as Claude AI are fundamentally changing this. By enabling fast, structured analysis of product datasets, AI allows ecommerce and trading teams to identify gaps, pricing opportunities and areas of competitive advantage in minutes rather than days. The role of the team then shifts from data gathering to decision-making — where the real commercial value lies.
The 5-Step Process
Start with a Clean, Comparable Dataset
Assemble a simple but structured dataset that includes your product range alongside one to three key competitors. Focus on consistency rather than complexity, ensuring the data can be easily compared. At a minimum, include: product name, price, category and subcategory, and key attributes (e.g. brand, size, features). This data can typically be exported from your ecommerce platform and supplemented with competitor data collected manually or via scraping tools.
Use a Clear, Commercial Prompt
The quality of insight generated by Claude AI is directly linked to how the task is framed. A structured, commercially focused prompt ensures the output is actionable rather than generic. Ask the AI to: compare product range depth and coverage, identify gaps in categories or price points, highlight over- or under-representation in key areas, and recommend opportunities to improve performance.
"Analyse the following product datasets comparing my range vs competitors. Identify gaps in product range, pricing differences, over/under representation in categories, and key opportunities to improve commercial performance. Summarise findings into clear insights and prioritised actions."
Interpret Through a Commercial Lens
Once processed, the AI returns a structured summary of insights — often highlighting where your range is misaligned with the market. Common themes include: missing subcategories or insufficient product depth, overexposure in low-performing or low-margin areas, gaps in entry-level or premium price bands, and competitor advantages in product variation or attributes. The role of the ecommerce leader is to interpret and prioritise these findings based on business context.
Translate Insight into Action
The real value lies in execution. Insights can be directly translated into commercial actions: expanding the range in high-demand categories, adjusting pricing architecture to improve competitiveness or margin, refining onsite merchandising to prioritise high-performing products, and enhancing product content and filtering to better match customer intent. In many cases, relatively small changes can unlock significant improvements in conversion and revenue.
Embed into Ongoing Trading Strategy
Rather than treating this as a one-off exercise, leading ecommerce teams are embedding AI-driven analysis into their regular trading rhythm. Over time, this approach can be used to review multiple categories on a rolling basis, combine external analysis with internal performance data, build a prioritised roadmap of growth opportunities, and support more agile, data-driven decision making.
- AI tools can compress days of manual category analysis into minutes
- The quality of your prompt determines the quality of the output — be specific and commercial
- Interpretation and prioritisation remain human jobs — AI generates the insight, you make the call
- Embed this into regular trading rhythm rather than treating it as a one-off exercise
- Small changes identified through AI analysis can unlock significant revenue improvements
AI tools like Claude AI are not simply about efficiency — they represent a step change in how ecommerce teams approach analysis and decision-making. For digital and ecommerce leaders, those who integrate AI into their workflows will be better positioned to identify opportunities, act decisively and outperform competitors in an increasingly data-driven market.