The future of website navigation: from keyword to conversation-based search

The humble search bar has, since the very early days of the internet, been every site visitor's first port of call for finding answers fast. But the way people interact online has changed dramatically. Rather than guessing keywords and trawling results, visitors now want natural language, intuitive search experiences.

To meet these expectations, businesses and public institutions are moving beyond on-site keyword search. They're adopting on-site conversational search: a smarter way to deliver results that are more relevant, contextual, and aligned to how people actually speak.

This marks a turning point: organizations now need controlled, intelligent systems that can interpret intent, not just mimic chat behavior.

In this blog, we'll break down the difference between keyword-based and conversation-based search. We'll explore how on-site conversational search is helping organizations deliver more meaningful results that understand context and reduce friction, and how Squiz Funnelback Search's Conversational Search capability positions organizations to lead this new era of discovery.

Keyword-based search works by matching user queries to exact or partial word matches in your content. If someone types "student visa", it looks for those specific words on your site. It's fast and effective, but only if users type the "right" keywords and your content includes them.

The issue? People don't always know the terminology your site uses. They might search for "study visa" and miss results tagged as "student permit". And when content is complex, keyword search can either flood users with too many results or none at all.

Conversation-based search, on the other hand, goes further. It interprets the meaning behind a query, using AI to understand natural language, synonyms, and user intent.

This ability to handle incomplete, vague, or imprecise queries is one of conversation-based search's biggest strengths. Users often type questions like "fees for applying" or "getting help with login" without full context. Conversation-based search uses natural language processing (NLP) to understand synonyms, implied intent, and contextual clues, allowing it to connect these fragments to the right answers, even when keywords don't match directly.

So instead of matching words, conversation-based search can connect the question "How do I apply to study in Australia?" to content about international student applications, even if none of those exact words are used.

It's the difference between searching with rigid rules and searching with understanding, and a glimpse into how Squiz Funnelback Search's Conversational Search capability is truly intelligent, explainable, and aligned with business goals.

Conversation-based search isn't just more accurate, it's also more user-friendly and inclusive. By interpreting meaning rather than relying on exact terms, it supports users who may not know the right terminology or who use varied phrasing. This reduces dead ends, frustration, and cognitive load, especially for people with lower digital literacy or using assistive technologies. It also returns more relevant results, improving user experience and satisfaction across the board.

At a glance: keyword-based search vs conversation-based search

Users today expect more from search. They want:

• ChatGPT-like experiences embedded into websites
• Natural language input, not keyword guessing
• Direct answers, not 20 links to dig through

Keyword-based search can't meet these needs on its own. On-site conversational search, designed as a controlled experience, provides this context-aware, conversation-based search experience that understands user intent and delivers relevant answers within seconds.

Not all conversation-based search tools are created equal. Many rely solely on natural language processing (NLP), a form of AI that helps machines interpret human language. While NLP can help match queries to content more flexibly than keyword-based search, it's only part of the equation.

Without a strong content foundation, natural language context alone won't guarantee accurate, useful results. That's where Squiz Funnelback Search stands apart, with clear advantages in its Conversational Search capability, built on enterprise-grade reliability and governance.

Conversational Search combines the linguistic understanding of NLP with validated content, customization, and guardrails. It understands intent and delivers accurate answers, not just surface-level answers.

Here’s what sets it apart:

Conversational Search is a capability of Squiz Funnelback Search, and can run standalone or alongside your existing search. Answers are built from validated, scoped content, helping keep them grounded in your most accurate and relevant content.

This architecture embodies a controlled on-site conversational search philosophy, combining conversational intelligence with content you have approved.

With advanced NLP, Conversational Search understands context, synonyms, intent, and phrasing, delivering natural responses that reflect how people actually speak.

It doesn't just match text, it interprets user goals. For example, if someone types "get new photo ID," the AI can infer they're looking for a step-by-step guide, even if those words don't appear explicitly. This makes the search experience more intuitive, responsive, and effective for real-world use.

3. Data control and guardrails that prevent hallucinations

Unlike generic AI search platforms (e.g. ChatGPT, Perplexity) that pull from the open web, Conversational Search is confined to your trusted content. Only approved pages are indexed, so users get accurate, brand-safe answers, while you stay in control of what the AI can see and say.

Conversational Search also uses a Retrieval-augmented Generation (RAG) framework. Content Intelligence first prepares your approved content into a validated question and answer database, flagging contradictions and gaps before anyone asks a question. When a question comes in, an AI model draws together the relevant validated information and writes a natural-language answer.

Here’s how it works, step by step:

1. Content preparation: Content Intelligence analyzes your approved content across your site, intranet, or other integrated systems, builds a validated question and answer database from it, and flags contradictions and gaps.
2. Understanding the question: Each question is interpreted in the context of the conversation so far. Answer guidelines and a default response, which non-technical teams can edit, control tone and fallback behavior.
3. Answer generation within your environment: A large language model, run within a secure regional cloud environment, writes an answer using your approved content only, never general internet data, with responses starting to stream in seconds.
4. Built-in accuracy checks: Content is validated before anyone asks a question, and guardrails help keep each answer grounded in your approved content.
5. Response delivery with full visibility: The user receives a direct answer with source attribution and can continue the conversation naturally. These interactions are tracked and monitored, giving you insights needed to improve the user experience.

Example of this in practice:

The user asks: “How do I apply for a postgraduate scholarship if I’m an international student?”

Behind the scenes, Conversational Search works like this:

1. It starts from the validated information prepared from your approved content (e.g. a postgraduate scholarships page).
2. It then augments that content and generates a plain-language answer using that content only, never from general internet data.
3. Guardrails help keep the answer grounded in your approved content before it's delivered to the user.

Conversational Search then responds:

“To apply for a postgraduate scholarship as an international student, you’ll need to complete the online application form by July 31. You must have an offer of admission and meet the eligibility requirements outlined here [link].”

And when an answer isn't in your approved content, users see a default response you control instead of a guess. This protects against AI overreach.

All AI answers include clear source attributions with links, helping users verify information and giving content teams full visibility into what's being returned.

Conversation-based search is only as good as the content behind it. That's why we’ve included Squiz Content Intelligence — a content health solution that audits your site for AI readiness and accessibility — as part of Conversational Search. It ensures your content has the structure, accuracy, consistency, and clarity needed to power high-quality answers – and gives your team clear, prioritized guidance on what to fix and where to start.

With analytics and conversation logs, Conversational Search gives teams visibility into what people are asking, how answers are performing, and where improvements are needed. You can refine content, adjust indexing rules, or update tuning - all with full admin control.

These continuous-improvement feedback loops put your organization, not the algorithm, in control.

On-site conversational search can transform digital experience across different sectors. Here are some examples of how organizations can put it to work:

• Higher education: Prospective students can ask natural questions like "When do classes start?" or "How do I apply?" and get fast, accurate answers about courses, dates, and admissions; without having to navigate a labyrinth of dropdowns and PDFs.
• Government: Citizens asking "What forms do I need to renew my license?" receive clear, AI-generated answers drawn from your approved content. This reduces support center volume, improves accessibility, and strengthens public trust in digital services.
• Professional services: Clients or consultants looking for “risk compliance policy” are taken straight to the relevant clause, not buried in a 40-page PDF or lost in outdated intranet structures. The result? Faster access, better service, and lower internal friction.

For more details on the benefits of this technology for different industries, check out the blogs here.

With on-site conversational search, your site doesn't just return results; it delivers answers. Squiz Funnelback Search's Conversational Search capability brings this capability to your organization.

Want advice on how to get started?

Book a 30-minute chat with a member of our team here.