Category: Uncategorized

In Part 1 of this series, we looked at why retrieval is only half the battle in B2B eCommerce. In Part 2, we explored how discovery systems go beyond search by adapting navigation, compatibility guidance, and buyer workflows to help customers complete complex tasks.

A discovery system isn’t something you implement once and leave alone. Catalogs expand, inventory shifts, and commercial priorities evolve. To remain effective the system has to adapt alongside those realities. At the same time, organizations are trying to achieve measurable business objectives, from introducing new products and improving margins to reducing excess inventory and supporting strategic supplier relationships.

An effective discovery system has to respond to both customer behavior and business strategy. A system that performs well today won’t continue delivering the same results unless it can adapt to both. Optimization becomes an ongoing operational capability that continually balances what customers need with what the business is trying to achieve.

Discovery Systems Should Learn

Every interaction tells you something. Searches, product views, cart activity, purchases, and completed buying journeys reveal how customers move through your catalog. Those behavioral signals show which products buyers select, where they hesitate, and which discovery paths consistently lead to successful outcomes.

Used well, behavioral information can improve ranking, recommendations, navigation, and product relationships without requiring someone to manually tune every query or category page. Machine learning helps identify patterns across thousands of shopper interactions that would be difficult to recognize manually, allowing discovery systems to better reflect how customers actually research, compare, and purchase products.

For example, if electrical contractors searching for “conduit” consistently choose a particular galvanized steel brand while ignoring PVC alternatives, the system can recognize that pattern and adjust the experience accordingly. The same principle applies to compatibility recommendations, navigation paths, and product relationships that consistently contribute to successful buying journeys.

Behavior Alone Is Not Enough

Behavioral signals are powerful, but they’re also incomplete. If a discovery system only follows historical behavior, it will naturally reinforce what has worked in the past. That’s useful, but it doesn’t always match what the business needs today.

Imagine a manufacturer introducing a new energy-efficient replacement motor. A behavioral model won’t automatically promote it because there isn’t any history behind it yet. Left on its own, the system will continue favoring the legacy model simply because that’s where the historical data exists. The business needs a way to intentionally promote the new product until customer behavior catches up.

The same challenge appears throughout B2B commerce. Inventory levels change, seasonal campaigns begin, supplier priorities shift, margin goals evolve, and products move through their lifecycle. Business priorities often move faster than behavioral data can respond. Behavioral data should inform discovery, but business objectives must ultimately guide it. The strongest discovery systems combine what customers are doing with what the business is trying to accomplish.

Orchestration Creates Balance

An orchestration layer sits directly between behavioral AI and business strategy, providing the control needed to balance both. Behavioral signals identify opportunities to improve discovery, while merchandising rules, business metrics, and operational priorities determine how those improvements are applied.

Consider a buyer researching industrial pumps. Behavioral data may show which replacement parts are commonly purchased together. At the same time, the business may want to prioritize products that are in stock, support a preferred supplier, or align with a current sales initiative.

Rather than relying exclusively on historical behavior or rigid business rules, an orchestration layer blends both perspectives. The buyer continues to receive relevant compatibility recommendations, while the business can influence which qualified products are emphasized based on current operational priorities.

Behavioral optimization helps the system learn from real customer activity, while business rules ensure those improvements remain aligned with company objectives. Together, they create a discovery experience that continuously adapts without becoming unpredictable.

This balance is especially important in B2B commerce, where purchasing decisions often involve technical specifications, compatibility requirements, contractual pricing, supplier agreements, and operational constraints. Effective discovery systems must optimize for both customer success and business success at the same time.

Continuous Optimization Is Essential

Traditional search projects often conclude once relevance reaches an acceptable level. Discovery systems continue to learn from customer behavior while adapting to changing business priorities, making optimization an ongoing operational capability rather than a one-time implementation effort.

Every catalog update, merchandising initiative, product launch, and customer interaction generates fresh insight into how buyers engage with your catalog. Modern discovery platforms surface these patterns in real time, helping search teams pinpoint where manual tuning will have the greatest impact. Teams stay in control of strategy while the underlying engine handles the routine adjustments.

THE OPTIMIZATION BALANCE

Modern discovery platforms surface these patterns in real time, helping search teams pinpoint where manual tuning will have the greatest impact. Teams stay in control of strategy while the underlying engine handles the routine adjustments

Organizations that treat discovery as an operational capability rather than a completed project are better positioned to continuously adapt to changing customer behavior, evolving business priorities, and the demands of modern B2B commerce.

The Role of Platforms Like FindTuner

Search engines like Elasticsearch, OpenSearch, and Apache Solr provide an excellent foundation for retrieval. FindTuner builds on that foundation by adding the orchestration and optimization capabilities needed to operate modern discovery systems.

FindTuner uses behavioral signals to continuously improve discovery performance while giving merchandising teams direct control merchandising teams direct control over business rules, strategic priorities, and the customer experience. By incorporating business metrics such as inventory, availability, and margin targets, FindTuner enables organizations to benefit from machine learning without sacrificing transparency or business control.

Looking Ahead

Across this series, we’ve followed a simple progression: Retrieval helps buyers find products. Discovery systems help buyers complete complex tasks. Automation and business control ensure those discovery systems continue to improve over time.

Search remains the foundation. The difference is how organizations optimize and evolve what they build on top of it.

As organizations grow, so do the operational demands on their search optimization platform. Deployment, upgrades, performance, and scalability become just as important as delivering exceptional search experiences.

That’s the focus of the latest FindTuner release.

This release strengthens the operational foundation of FindTuner, making it easier to deploy, manage, and scale while continuing to optimize search and product discovery.

Simplified Platform Lifecycle Management

The latest FindTuner release introduces new platform lifecycle management capabilities through FindTuner Orchestrator and FindTuner Launcher, simplifying installation, upgrades, runtime management, and ongoing administration. By automating common operational tasks and standardizing runtime management, these capabilities help organizations deploy and operate FindTuner with greater consistency and efficiency as their environments evolve.

Improved Optimization Performance

The release introduces the new FindTuner Optimizer, delivering improved execution performance for search optimization workloads while providing a foundation for future capabilities. Organizations benefit from faster processing today, while the new architecture positions the platform for continued innovation as business requirements evolve.

Enhanced Insights Scalability

Enhancements to the FindTuner Insights repository improve scalability for organizations collecting and analyzing growing volumes of shopper behavior and search performance data, supporting larger eCommerce deployments and longer-term analytics. These improvements help organizations continue to leverage behavioral intelligence as their search traffic, product catalogs, and historical data grow.

Continuing to Strengthen the Platform

Every FindTuner release represents an ongoing investment in both search optimization and the platform that supports it. While optimizing search relevance and product discovery based on shopper intent remains our primary focus, we continue to invest in the operational capabilities that make enterprise deployments easier to manage over the long term.

By simplifying platform lifecycle management, improving optimization performance, and enhancing Insights scalability, this release helps organizations operate FindTuner more efficiently while continuing to deliver exceptional search and product discovery experiences.

If you’d like to see how FindTuner works with Elasticsearch, OpenSearch, or Apache Solr, or learn how its latest platform enhancements simplify deployment, administration, and scalability, please contact us for a demo.

Traditional search experiences were designed around finding products. Many B2B buying processes, however, are centered around evaluating, comparing, validating, and selecting them. Discovery has evolved from returning relevant products to supporting complete buyer workflows.

For years, the standard approach to B2B eCommerce search focused almost entirely on retrieval. The objective was straightforward: index the catalog, improve keyword matching, and help buyers locate products faster.

As outlined in Part 1 of this series, many organizations eventually discovered that retrieval alone does not solve the broader discovery problem. Buyers may find relevant products, yet still struggle to identify compatible components, select the correct configuration, or determine which products belong together within a larger workflow.

The natural response is often to focus on improving search relevance. However, in many cases, relevance is not the primary limitation. The challenge is that buyers are trying to solve technical, operational, and procurement problems as efficiently as possible, not simply trying to find products.

That distinction changes the architectural conversation. Instead of asking how to build a better search experience, organizations should ask how to design discovery systems that support buyer workflows from initial query through final selection.

Why Retrieval Alone Is Not Enough

This traditional, product-first approach works well in many B2C environments where buyers can browse visually and make decisions quickly. B2B buying is different. Buyers are often trying to solve technical, operational, or procurement problems where compatibility, specifications, and workflow requirements matter just as much as retrieval.

Consider a buyer searching for SKU “1234-AB.” Most mature B2B commerce platforms can correctly route that user to the matching product page. But the buying process may only be beginning. The buyer may still need replacement components, compatible accessories, or products commonly used with that item.

In these scenarios, the challenge is no longer finding the product, it’s helping the buyer complete the task.

We see the same pattern applies across much of the B2B landscape. A buyer searching for industrial fasteners or electrical connectors is focused on a specific technical task where hitting ‘enter’ is simply the starting point. As they work through matching technical specifications and cross-referencing compatibility data, the underlying system must layer in the contract pricing and regional fulfillment constraints that govern the account.

When discovery is driven by relationships, compatibility requirements, and operational workflows, a generic ranked list of product tiles quickly becomes insufficient. Solving these challenges requires more than a better ranking algorithm. It requires a foundation capable of supporting different discovery workflows, adapting to buyer intent, and evolving alongside changing business requirements.

Designing Search and Navigation Around Buyer Intent

Once organizations look beyond simple retrieval, the core challenge shifts to making the interface respond to buyer intent. The value of a flexible search foundation becomes apparent here. Its strength lies in providing the agility needed to mold the entire experience around technical dependencies and business priorities, not just returning a matching list of items.

Not every search should produce the same experience. A buyer researching stainless steel hydraulic fittings is trying to narrow a large solution space through specifications, compatibility requirements, and technical constraints. A buyer evaluating commercial HVAC equipment may need an entirely different workflow centered around capacity, refrigerant requirements, and equipment compatibility. Even when both users begin with a search query, the information and tools needed to reach a decision can be dramatically different.

The distinction between search and discovery becomes clearer here. The goal expands beyond returning relevant products. Instead, the system must surface the exact information, navigation paths, and selection tools required to match the buyer’s intent. This requires search and navigation to work together.

Instead of treating filters and facets as static interface elements, discovery systems can adapt navigation based on the problem the buyer is trying to solve. HVAC-related searches may prioritize BTU ratings and refrigerant compatibility, while electrical searches surface voltage, amperage, and connector types. The navigation experience itself becomes part of the discovery workflow, helping buyers progressively narrow options rather than forcing them to sift through a generic catalog structure.

The same principle applies to compatibility and product relationships. A replacement motor may only work with specific equipment models. A heavy-duty brake pad may need to be validated against vehicle model years. Discovery systems can use compatibility data, assemblies, bundles, and product relationships to guide buyers toward viable options while reducing the risk of incorrect selections.

As discovery workflows become more sophisticated, search results become only one part of the overall experience. Buyers increasingly depend on navigation, compatibility guidance, contextual relationships, and workflow-specific decision support to arrive at the right outcome.

At that point, the system is doing far more than helping users search a catalog. It is actively helping them evaluate options, validate decisions, and complete complex buying tasks. The search engine remains a critical foundation, but the overall experience begins to function as a discovery and decision-support system.

THE DISCOVERY GAP

In B2C, the goal is often to help buyers find products.

In B2B, the goal is to help buyers complete tasks.

Finding the correct product is often only the beginning. Buyers still need to validate compatibility, compare options, navigate technical requirements, and assemble complete solutions before a decision can be made.

Discovery Systems Require Orchestration

Translating raw buyer intent into these tailored decision-support environments can be difficult. These dynamics cannot be hardcoded into a single storefront wrapper; they require a dedicated mechanism that can pivot as catalogs evolve and new business requirements emerge. This level of adaptability requires orchestration.

Orchestration provides the control needed to adapt discovery experiences based on buyer intent. They determine how queries are interpreted, how navigation changes, how compatibility information is surfaced, and how product relationships are introduced throughout the buying process. For example, a procurement manager sourcing laboratory diagnostic equipment may be guided into a workflow centered around calibration certifications, testing capacity parameters, and side-by-side comparison tools rather than a generic product grid.

Orchestration also provides a mechanism for applying business rules, merchandising strategies, and behavioral optimizations without requiring changes to the underlying search platform. Behavioral signals such as product views, cart activity, and purchases continuously improve discovery performance, while business metrics such as inventory levels, product availability, and revenue ensure those experiences remain aligned with business objectives.

Platforms like FindTuner extend search engines such as Elasticsearch, OpenSearch, and Apache Solr with these orchestration and optimization capabilities, allowing companies to design discovery experiences around buyer workflows rather than forcing every buyer through the same search experience.

From there the focus shifts from implementing search to continuously improving how discovery works across the entire buying process. Because in modern B2B commerce, discovery does not end when the search results load. That is where the real workflow begins.

In Part 3 of this series, we’ll explore why guided discovery systems require more than retrieval and orchestration alone. As organizations introduce AI, behavioral optimization, and automation into discovery workflows, they must also balance those capabilities with intentional business control, merchandising strategy, and continuous optimization.

Modern B2B eCommerce search technology has become exceptionally good at eCommerce product retrieval. Search engines are faster, relevance models are smarter, and AI-powered systems are getting better figuring out what a user actually means.

But here’s where B2B commerce becomes more complex: retrieving products is only part of the experience. Buyers still need efficient ways to identify the right product combinations within large, attribute-rich catalogs.

In the B2B world, search isn’t the finish line. It’s the starting point for a much larger product discovery and selection process.

B2B Search Is Fundamentally Different from B2C Search

Much of modern eCommerce search thinking has been shaped by B2C experiences where discovery is centered around inspiration, browsing, and engagement. A shopper searching for apparel or home décor may enjoy exploring recommendations, related products, and curated collections.

B2B commerce is different.

Many B2B buyers are not browsing casually; they’re trying to complete a task quickly and accurately. A maintenance manager searching for a replacement industrial part is not looking for inspiration. They need to find a SKU, verify compatibility, and get that part on a truck to minimize downtime. Efficiency is the core metric that matters here.

Many B2B buyers are also repeat purchasers who already understand the products, specifications, and terminology they need. Searches may include internal part numbers, manufacturer IDs, industry abbreviations, or highly specific technical language. In these scenarios, the objective is rarely broad exploration. It’s precise identification and fast validation.

This changes the role of B2B eCommerce search entirely as B2B search strategy is often less about inspiration and more about utility, precision, and efficiency.

Filters and structured navigation also become far more important in B2B environments. Buyers are often narrowing large product sets using dimensions, compatibility requirements, material types, voltage ranges, contract-specific availability, or operational constraints. The ability to move quickly from broad retrieval into precise selection is often what determines whether the experience feels useful or frustrating.

Search relevance is rarely a simple textual match. It’s a complex, shifting calculation of inventory, customer-specific contracts, equipment compatibility, and approved product lines. This is exactly why retrieval is only half the battle.

Why Efficient Product Discovery Matters in B2B Commerce

Because B2B buyers are task-oriented rather than inspiration-oriented, product discovery has a direct impact on operational efficiency and customer experience. If buyers cannot quickly locate the correct product, compatibility relationship, or bundle they don’t just keep clicking. They either leave, contact a sales rep, or move to a competitor who makes the process easier. Even small amounts of friction disrupt the buying process. If locating the right SKU takes several minutes instead of seconds, buyers revert to manual support channels.

The B2B search challenge is not simply getting buyers to a results page, it’s helping them confidently complete the selection process. By reducing friction here, organizations don’t just improve conversion they lessen support tickets, reduce purchasing errors, and shorten the B2B customer journey.

Retrieval Alone Does Not Solve Selection

A traditional ranked results page works perfectly well for some searches. A buyer enters a specific SKU or product name and immediately finds the desired item. But many B2B buying workflows are more complex than locating a single product. Consider a search such as “stainless steel hydraulic fittings”. The system shouldn’t just “find” the fittings. It needs to help the buyer navigate attribute-based specs like thread size, pitch, coating, and material.

Similarly, a query for “cordless drills” might involve navigating voltage, battery platform compatibility, torque ratings, and commercial-grade distinctions.

In attribute-rich B2B catalogs, the most relevant filters and specifications often depend on the query itself. A buyer searching for hydraulic fittings may need to refine by pressure rating, thread type, or compatibility requirements, while a buyer searching for cordless drills may care more about voltage, battery platform, or bundled accessories.

Presenting the same filters and attributes for every search can create unnecessary friction. Effective discovery systems adapt the selection experience to the buyer’s context and intent.

In these situations, the opportunity is to elevate search into a guided discovery experience that supports evaluation, comparison, and selection. A buyer ordering hundreds of units across multiple sizes or configurations needs a data-rich interface where they can compare specifications, evaluate variations, and add multiple line items to a cart in a single workflow. Different searches often require different buying experiences. Some searches should return directly ranked results. Others may be better served by:

• Guided navigation and structured filtering
• Curated category experiences
• Compatibility workflows
• Table-based selection systems
• Bundled product recommendations

Using our previous examples, a buyer searching for “stainless steel hydraulic fittings” may benefit from an experience that immediately surfaces the most important selection criteria (e.g. thread type, pressure rating, and compatibility) through clear filters and guided refinement controls.

A search for “cordless drills,” on the other hand, may intentionally guide buyers into a curated category experience with filtering, navigation, and bundled accessories instead of a standard results page.

The important distinction is that these experiences should be intentional. Search can lead to direct results or structured selection, but the system should determine which experience best supports the buyer’s task.

The B2B Reality Check

In B2C, a “no results” page is a lost sale.

In B2B, a “too many results” page is often just as expensive.

If a buyer searching for ‘stainless steel hydraulic fittings’ has to click through several pages of results to identify the correct thread type, pressure rating, or compatibility requirement, the system has failed the efficiency test.

Guided Discovery Requires Intentional Control

The hardest part of modern B2B commerce is controlling how this discovery behavior unfolds. This requires more than just an engine. It requires an orchestration layer (like FindTuner) to set the “rules of engagement”.

Orchestration gives search teams the power to define how queries behave without having to beg developers to rewrite the search backend infrastructure. It’s about balance. You want the raw power and efficiency of AI, but you still need the search merchandising tools to guide the outcome when business priorities change.

Search Gets Buyers to the Right Place. Selection Determines What They Purchase

As B2B commerce continues to evolve, organizations are beginning to rethink the role of search itself. The most successful discovery systems aren’t the ones that just generate “better results”. They are the ones that guide buyers through the maze of relationships and combinations to the right purchase.

That shift is changing how modern B2B discovery systems are designed. Instead of simply configuring traditional search experiences, organizations should be thinking about designing discovery systems that intentionally control routing, filtering, navigation, compatibility, and product selection at scale.

In our next article, we’ll explore the architectural patterns behind modern discovery systems and what it means to move from a packaged search platform to a flexible, orchestrated search architecture.

Hybrid search promises better search experiences by combining lexical precision with semantic understanding. But for many retailers and B2B sellers getting real value from hybrid search can be challenging. Enabling semantic models can be complex and once hybrid search is live, search teams often lack clear visibility into how it’s actually performing compared to traditional keyword search.

With the latest enhancements to FindTuner, we focused on solving both sides of that problem: simplifying hybrid search adoption and providing clearer insight into how shoppers interact with search and navigation.

Built-In Support for OpenAI and Gemini

FindTuner now includes built-in support for leading embedding models from OpenAI and Google Gemini making it significantly easier to activate hybrid search. These capabilities work seamlessly across Elasticsearch, OpenSearch, and Apache Solr allowing merchants to enable hybrid search quickly within their existing search infrastructure.

Retailers can get started without custom implementation and dramatically reduce time to value for AI-powered search experiences. These new built-in options provide a fast, reliable starting point for organizations adopting hybrid search, while FindTuner continues to support any embedding model of a customer’s choice.

New Insights That Deliver Greater Visibility

Activating hybrid search is only part of the equation. To optimize hybrid search teams and merchandisers need clear, objective insight into shopper behavior and search performance. That’s why we also introduced two new additions to FindTuner Insights that are designed to help retailers understand what’s happening after search results are delivered.

Together, these Insights provide time-based behavioral visibility and meaningful performance comparisons giving teams the confidence to evaluate hybrid search and make informed tuning and merchandising decisions.

Semantic vs. Lexical Click-Through Rate Insight

One of the most common questions retailers ask is whether semantic search results are actually outperforming traditional lexical results. The new Semantic vs. Lexical Click-Through Rate Insight answers that question directly.

This Insight compares shopper engagement between semantic and lexical search results at the search-term level making it easier to see how engagement is distributed and where semantic relevance is delivering value. With this visibility, teams can quantify the impact of hybrid search and optimize with data instead of assumptions.

Shopper Activity Trends Insight

The Shopper Activity Trends Insight focuses on understanding how shopper behavior evolves over time. It provides time-series visibility into key activities across search and navigation, including searches, clicks, cart additions, and purchases.

By analyzing these behaviors over configurable time intervals retailers can identify trends, monitor seasonality, and better understand how engagement changes. This insight supports smarter tuning and merchandising decisions by grounding optimization efforts in real shopper behavior.

Want to Learn More?

If you’d like to see how FindTuner works with Elasticsearch, OpenSearch, or Apache Solr, or explore how hybrid search and Insights can improve the eCommerce search experience, please contact us for a demo.

Artificial intelligence is reshaping eCommerce search. Vector search, semantic relevance, and personalization models promise to help shoppers find what they want faster and more intuitively than ever before. For retailers, these capabilities represent real opportunity.

But as enthusiasm for AI accelerates, many organizations risk overlooking an essential truth: AI alone does not optimize for business outcomes, it optimizes for relevance. To drive revenue, profitability, and operational efficiency, retailers must still apply intentional business logic to search. That is where metrics-based boosting remains indispensable.

Far from being made obsolete by AI, metrics-based boosting has become even more important. When paired with AI-powered search, it provides the control layer that aligns shopper intent with business priorities.

What Metrics-Based Boosting Really Does

Metrics-based boosting is the practice of influencing search rankings using measurable business signals such as conversion rate, revenue performance, inventory levels, and customer ratings in addition to relevance.

Its purpose is not to undermine relevance, but to refine it. Search results should not only match what a shopper is looking for, they should also reflect what the business knows will perform well, satisfy customers, or support operational goals.

A highly rated product, for example, may deserve greater visibility because it is more likely to convert and reduce returns. A high-inventory item may warrant temporary emphasis to accelerate sell-through. Products with strong historical revenue may merit additional weight because they consistently meet shopper expectations.

This is search merchandising in its most practical form: guiding shoppers toward products that are both relevant and valuable.

Why AI Search Alone Is Not Enough

AI excels at understanding language, intent, and similarity. It can personalize results based on behavioral patterns and uncover relevance that keyword-based systems miss. What AI does not inherently understand is business intent.

An AI model does not know which products are overstocked, which carry higher margins, or which are strategically important this quarter. These are signals that business must explicitly tell to it.

Metrics-based boosting is how that communication happens. It ensures that search results reflect not just what is relevant to the shopper, but what matters to the business right now. Without it, AI-driven relevance can become disconnected from commercial reality.

How Metrics-Based Boosting Works in Practice

Most retailers already possess everything they need to implement metrics-based boosting:

• Business data that reflects performance, inventory, and priorities
• A search platform (e.g. Elasticsearch, OpenSearch, Solr) capable of incorporating those signals into ranking logic

By weighting business metrics alongside lexical and semantic relevance, retailers can influence rankings dynamically and at scale. As performance data changes search results adjust automatically. Conversion rates should rise, inventory levels will shift, and customer ratings experience evolutions and adjustments.

Modern search merchandising tools like FindTuner make this accessible to business users, allowing teams to tune influence levels, apply conditional logic, and balance competing signals without constant manual rule-building.

The result is a system that adapts continuously, without sacrificing relevance or requiring frequent reconfiguration.

Business Impact: Control, Adaptability, and Measurable ROI

Metrics-based boosting delivers value because it operates directly on outcomes. It improves the efficiency of search by promoting products more likely to convert, increasing revenue per search, and reducing friction in the shopper journey.

Equally important, it provides control. Retailers can ensure that search supports broader goals such as clearing excess inventory, protecting margin, or elevating top-performing products. This does not rely solely on opaque AI models.

Search becomes not just a discovery tool but a decision-shaping engine.

Metrics-Based Boosting and AI: Stronger Together

The most effective eCommerce search strategies do not choose between AI and metrics-based boosting, they combine them.

AI determines what is relevant; Metrics determine what is valuable.

Together, they create search experiences that are personalized, commercially aligned, and operationally aware. Shoppers see results that make sense to them, while businesses retain the ability to guide outcomes intentionally.

This combination is not a future-state aspiration. It is achievable today using the data most retailers already have and tools like FindTuner.

The Bottom Line

Metrics-based boosting is not a legacy tactic waiting to be replaced by AI. It is a foundational capability that makes AI-powered search commercially effective.

Retailers that rely on AI alone risk optimizing relevance without results. Those that pair AI with metrics-based boosting transform search into a strategic asset that aligns shopper intent with business intent and delivers measurable value.

In the AI era, smart eCommerce leaders are not abandoning proven merchandising principles. They are using them to make AI work better.

Over the past year, FindTuner took several meaningful steps forward by expanding platform support, deepening insight into shopper behavior, and extending automation across the eCommerce ecosystem. Together, these advancements reinforce a single goal: helping our customers turn search into a measurable, controllable driver of shopper experience and revenue.

Expanding the FindTuner Platform

This year marked a major expansion of where and how FindTuner can be applied. With the release of FindTuner 3.10, we extended FindTuner’s merchandising and AI capabilities to Elasticsearch and OpenSearch, in addition to Apache Solr.
Many retailers and B2B merchants choose these platforms for their speed, scale, and flexibility. However, delivering meaningful, revenue-driving shopper experiences requires more than technical performance; it requires the ability to apply merchandising strategy, business priorities, and AI-driven optimization to every search interaction.
FindTuner brings that layer of control and intelligence to Elasticsearch and OpenSearch, enabling teams to fine-tune relevance, promote key products, personalize discovery, and guide shopper journeys without sacrificing automation or performance. This expanded platform support allows organizations to apply consistent merchandising strategy across more of today’s leading eCommerce search foundations.

From Search Activity to Actionable Insight

Another major focus of the year was visibility. As shopper expectations continue to rise, search and merchandising teams are under increasing pressure to understand what’s working, what isn’t, and where to focus next.
With the introduction of FindTuner Insights, we addressed a long-standing gap left by generic analytics tools by connecting shopper behavior directly to search merchandising decisions.
FindTuner Insights provides merchandisers with direct, self serve access to search specific analytics, without relying on generic dashboards or centralized analytics teams. Teams can see how shoppers interact with search and navigation, identify high volume or underperforming queries, understand revenue impact by strategy or product, and uncover clear opportunities to improve discovery.
Beyond reporting, Insights creates a continuous feedback loop between merchandising actions and shopper outcomes. Using capabilities such as clickstream analysis, funnels, cohorts, and A/B testing, merchandisers can evaluate strategy performance, refine tactics, and clearly demonstrate the impact of their decisions. This turns optimization into an ongoing, data-driven process rather than a periodic review.

Agentic AI and MCP

This year we also introduced the FindTuner MCP Server, a new integration layer designed to extend FindTuner’s reach and enable greater automation across the modern eCommerce ecosystem.
The FindTuner MCP Server allows AI agents and workflow tools to connect directly with FindTuner through no-code and low-code workflows. This makes it possible to automate merchandising actions, exchange contextual intelligence between systems, and integrate FindTuner’s optimization capabilities into broader digital experience platforms and AI-driven processes.
By enabling interoperability and intelligent automation, the MCP Server positions FindTuner as a central, connected component in a data-driven eCommerce architecture supporting teams as they adopt AI-assisted workflows while retaining human oversight and strategic control.

Looking Ahead

Taken together, this year’s advancements reflect a clear direction for FindTuner:

• Intelligence that blends AI, automation, and human strategy
• Insight that makes shopper behavior understandable and actionable
• Control that empowers merchandisers without slowing teams down

As we move forward, our focus remains on helping you deliver better shopper experiences, make smarter decisions faster, and turn search into a durable competitive advantage. Thank you for being part of the FindTuner community. We’re excited about what’s ahead.

In two previous articles, we introduced Insights, a powerful new analytics capability in FindTuner. The first post explained what Insights is and how it works; the second post explored the types of merchandising and optimization use cases it supports.

This article looks at a third dimension: how FindTuner Insights relates to traditional web analytics tools such as Google Analytics. While we didn’t develop Insights to replace those platforms, we built it to fill a crucial gap that conventional analytics tools don’t and can’t address. Insights equips merchandisers with the visibility they need into search behavior to enhance product discovery and drive better outcomes.

Why Online Retailers Rely on Analytics 

Online retailers have long depended on analytics to understand how shoppers engage with their websites. Tools like Google Analytics reveal where visitors came from, what pages they viewed, how long they stayed, and which elements they interacted with. For understanding external traffic patterns and broad behavior trends, these platforms remain vital.

But eCommerce requires more than an outside-in view of traffic and session activity. The most critical insights for improving product discovery come from inside the site, from the search box, navigation paths, product interactions, filters, and the decisions shoppers make as they narrow toward a purchase. This is the area where conventional analytics tools provide only partial visibility and where FindTuner Insights delivers clarity.

Where Conventional Analytics Fall Short

Traditional analytics platforms weren’t designed to explain the internal patterns that drive successful product discvoery. They focus on traffic and behavior at a high level but lack the depth needed to uncover the relationships between shopper intent, search behavior, and purchasing outcomes.

1. Limited internal website behavior visibility

Conventional analytics tools track clicks and page interactions, but they rarely reveal what matters most in retail: how shoppers move through search and navigation, which behaviors ultimately led to conversion, and where friction occurred along the way. They don’t distinguish between a query refinement and a dead-end search, or show which product positions resonated with shoppers. They capture activity, but not the intent or the journey behind it.

2. Not optimized for product discovery

Because these platforms treat all websites similarly, they lack awareness of core eCommerce search concepts like ranking strategies, attributes, facets, promotions, filters, and curated experiences. They can’t show how these elements influence purchasing decisions or which merchandising strategies succeeded or fell flat. For search teams and merchandisers, the lack of eCommerce search-specific insight limits their ability to understand what actually drives discovery.

3. Siloed teams and siloed data

The teams who manage analytics tools are often separate from the people responsible for shaping product discovery. As a result, they receive incomplete data, delayed reports, or insights stripped of the context required for making decisions. Search optimization becomes reactive instead of proactive, and opportunities to improve the shopper journey are missed. Insights closes this gap by delivering search and navigation analytics the FindTuner application thus removing delays and silos entirely.

4. Not configured for eCommerce search

While traditional analytics tools can be extended with custom events and tagging, doing so requires significant configuration and ongoing maintenance. Even then the resulting data is rarely as precise or comprehensive as search teams need. Insights eliminates this overhead. It arrives ready to capture the signals that matter for eCommerce search and navigation and delivers value immediately.

Connecting Merchandiser Actions to Outcomes

Understanding shopper behavior is essential, but Insights goes further by tying that behavior directly to the decisions merchandisers make in FindTuner.

This connection is unique. Insights shows not only how shoppers acted, but how those actions were influenced by:

• Behavioral ranking signals
• Product and brand promotions
• Curated collection pages
• Facet and filter adjustments
• Category level strategies

Instead of guessing whether a promotion worked or whether a curated experience improved discovery, merchandisers can see the impact clearly. They can measure whether a boosted brand increased engagement, whether a facet change reduced friction, or whether a curated result set drove more conversions. This closed feedback loop is something conventional analytics tools simply don’t provide.

Augmenting Conventional Analytics

Conventional analytics tools still have an important role to play. Retailers rely on them for understanding how shoppers arrive at the site, which search engines or keywords drove traffic, and how high-level site elements perform.

Insights complements this perspective by revealing what happens once shoppers begin exploring the site, including where discovery succeeds or breaks down, how intent evolves, and how merchandising strategies influence the journey. It delivers the depth of insight required to improve relevance, reduce friction, and guide shoppers toward the products they seek.

By connecting shopper behavior, intent, and conversion directly to merchandising actions, Insights transforms search optimization from a guessing game into a measurable, repeatable process. Retailers gain the clarity they need to improve the shopper experience and the confidence to make decisions that drive real business results.

We are excited to announce that FindTuner 3.10 is immediately available! The new release brings FindTuner’s powerful merchandising and AI capabilities to Elasticsearch and OpenSearch, enabling merchandisers to shape, personalize, and optimize search-driven experiences across more of today’s leading search platforms. It also introduces the new FindTuner MCP Server, an integration layer that allows AI agents and workflow tools to connect directly with FindTuner, supporting greater automation and extending its reach across the eCommerce technology ecosystem.

As online retailers and B2B merchants increasingly adopt Elasticsearch and OpenSearch to power eCommerce search, they are discovering that while these platforms deliver speed, scale, and flexibility, shaping results into meaningful shopper experiences requires a layer of merchandising control and intelligence. Merchandisers and search teams need ways to influence ranking, apply business priorities, and personalize discovery, all while taking advantage of AI and automation. FindTuner 3.10 bridges that gap with advanced merchandising tools and a new MCP Server, enabling intelligent automation and integration within the modern eCommerce ecosystem.

Elasticsearch and OpenSearch Support

Elasticsearch and OpenSearch provide the speed, scalability, and flexibility that today’s leading online retailers depend on. Yet delivering truly engaging, revenue-driving shopper experiences require more than technical performance, it demands the ability to apply AI, merchandising strategy, and human insight to every search. Merchandisers and search teams need the control to fine-tune relevance, promote key products, and guide discovery without losing the benefits of automation. FindTuner 3.10 extends the power of Elasticsearch and OpenSearch with AI-driven optimization, advanced merchandising control, and experience management that turn great search foundations into exceptional shopping experiences.

Introducing the FindTuner MCP Server

FindTuner 3.10 also introduces the FindTuner MCP Server, designed to enhance interoperability and automation within the modern eCommerce ecosystem through no-code and low-code workflows. The MCP Server enables AI agents and workflow tools to communicate directly with FindTuner’s merchandising and optimization capabilities, allowing merchandisers and search teams to automate actions, exchange context, and extend FindTuner’s intelligence across other digital experience systems. This new integration layer strengthens FindTuner’s role at the center of a connected, data-driven eCommerce architecture.

If you are an existing client and would like to learn more about these new features, please contact your Deployment Consultant. If you are considering FindTuner, please please contact us for a demo today!

In today’s competitive eCommerce landscape, effective search optimization is inseparable from data and analytics. Each day, online retailers handle thousands of shopper interactions including searches, navigation paths, product views, and purchases. Without visibility, those signals are wasted potential.

Insights, the analytics engine within FindTuner, transforms this activity into actionable intelligence, enabling merchandisers and search teams to see which strategies are working, which are underperforming, and how those strategies impact conversions and revenue.

In a previous article, we explained what FindTuner Insights does and why it fills such a critical gap in search merchandising and eCommerce search optimization. In this article we’ll explore the data FindTuner Insights tracks and how it empowers merchandisers to validate their strategies, optimize search and navigation, and deliver great search experiences.

The Role of Analytics for Search Optimization

To unlock the full value of Insights, it’s important to understand the two primary categories of data it delivers and why each matters.

Search analytics capture the intent behind shopper queries and the results those queries produce. Retailers can see which terms drive purchases, which yield irrelevant results, and where shoppers encounter dead ends such as “no results found.” This visibility turns search behavior into a measurable performance indicator highlighting both strengths and opportunities for improvement.

Navigation analytics map the journey shoppers take across a site, from entry point to purchase. While traditional web analytics may stop at click counts, FindTuner Insights traces complete pathways, including how multiple shoppers reached the same product via different routes. This level of traceability provides a deeper understanding of shopper decision-making and highlights patterns that would otherwise remain hidden.

Unlike generic analytics tools, FindTuner Insights surfaces this data in highly granular form. Retailers gain detailed evidence of how search and navigation truly shape conversions making it possible to pinpoint where friction occurs and how to resolve it.

What You Can Track with FindTuner Insights

Now that we’ve covered at a high level the types of visibility FindTuner Insights provides, let’s dive deeper by looking at some specific types of information that can be analyzed and leveraged for search optimization.

Measuring Query Performance

Search behavior produces some of the clearest data about shopper intent. Insights not only records the exact queries entered, but also associates them with measurable results such as product clicks, refinements, add-to-cart actions, and completed purchases. It also flags queries that stall out when shoppers see irrelevant results, encounter a ‘no results’ page, or exit the site altogether. By comparing these patterns, merchandisers can quantify which queries are revenue drivers, which are weak performers, and where strategy changes and search optimization can deliver the greatest impacts.

How Shoppers Refine Their Searches

Each refinement a shopper applies is a data point that clarifies intent. Insights records these refinements in sequence showing how shoppers move from broad queries to precise results. Over time, this creates a detailed map of which refinements accelerate purchases and which correlate with abandonment. Retailers can use this information to optimize search defaults, surface the most relevant filters earlier, or even pre-apply popular refinements so shoppers reach desired products faster and with less effort.

When Searches Hit a Dead End

Zero-result queries aren’t just missed sales, they’re a window into unmet demand. FindTuner Insights tracks them comprehensively, allowing merchandisers to quantify how often they occur, which terms trigger them, and what shoppers do afterward. This data makes it possible to fine-tune search strategies, perform search optimization, expand product attribution, or introduce FindTuner’s AI-based semantic search to catch non-exact matches. Addressing these gaps ensures that fewer searches end in frustration and more lead to discovery.

Measuring Engagement Through Time-on-Page

Every page view becomes more meaningful when paired with time-based data. FindTuner Insights records session length at each step, e.g. product listing pages, category listings, and product detail pages, providing evidence of where shoppers engage and where they stall. Retailers can use this data to pinpoint friction points (e.g., long sessions without conversion) and optimize accordingly, whether by simplifying filters, enriching product content, or boosting items that consistently capture attention and lead to sales.

Using Clickstream to Understand Journeys

With FindTuner Insights, clickstream data becomes actionable intelligence. Every click is logged as part of a structured sequence that shows how shoppers actually experience your site. Unlike generic tools that only summarize at an aggregate level, Insights ties this activity back to outcomes like product discovery and purchase. This makes it possible to identify which interactions accelerate the path to conversion and which introduce friction, all of which enables evidence-based changes to navigation, content, and merchandising strategy.

Reverse Journeys: How Shoppers Find Products

With backwards clickstream reporting, FindTuner Insights reframes the question from ‘Where did shoppers go?’ to ‘How did they arrive here?’ By analyzing all the routes that end at a given product, merchandisers gain visibility into the real discovery process. The data highlights which paths consistently drive purchases and which include detours or drop-offs. Armed with this evidence, businesses can simplify product findability, prioritize high-performing navigation flows, and replicate success across the catalog.

Measuring the Impact of Merchandising

In the end, analytics only matter if they help you answer one critical question: Are our merchandising strategies working? FindTuner Insights connects shopper behavior directly to merchandising actions such as boosts, banners, recommendations, or curated rules, and shows whether those interventions led to higher engagement, improved click-through rates, or increased conversions. By measuring the real-world impact of each strategy, merchandisers gain the evidence needed to double down on what works, refine what doesn’t, and continuously improve results. Instead of guessing at effectiveness, you can see exactly how search optimization shapes shopper behavior and revenue.

Conclusion: Richer and Deeper eCommerce Seach Analytics

The examples we’ve explored are just a glimpse of how FindTuner Insights transforms raw shopper activity into actionable intelligence to inform search optimization efforts. From query outcomes to navigation paths and merchandising effectiveness, Insights equips retailers with the data needed to optimize search, streamline discovery, and increase conversions. With this level of visibility, decisions are no longer guesswork; they’re evidence-based. To see how FindTuner Insights can reshape your merchandising strategies, connect with us and explore the possibilities.

Our next post will explore how FindTuner Insights complements broader tools like Google Analytics to deliver a complete search analytics picture.