The Solution

To address these challenges, the project team developed a proof-of-concept (POC) that leveraged advanced graph technology and a semantic RAG (Retrieval Augmented Generation) agentic workflow. 

The solution was built around several core workstreams:

Defining System Functionality

The initial phase focused on establishing a clear use case: enabling the foundation to query its data ecosystem with natural language questions and receive accurate, explainable answers. This involved mapping out a comprehensive taxonomy and ontology that could encapsulate the knowledge domain of investments, thereby standardizing how investment documents and data were interpreted and interrelated.

Processing Existing Data

With functionality defined, the next step was to ingest and transform various data types. Structured data from internal systems and unstructured investment documents were processed and aligned with the newly defined ontology. Advanced techniques, including semantic extraction and graph mapping, were employed to ensure that all data—regardless of source—was accessible within a unified graph database.

Building the Chatbot Model

Central to the solution was the development of an investment chatbot that could leverage the graph’s interconnected data. This was approached as a cross-document question-answering challenge. The model was designed to predict answers by linking query nodes with relevant data nodes across the graph, thereby addressing competency questions that a naive retrieval model would miss. An explainable AI component was integrated to transparently show which data points drove each answer, instilling confidence in the results.

Deploying the Whole System in a Containerized Web Application Stack

To ensure immediate usability, the POC was deployed, along with all of its dependencies, in a user-friendly, portable web application stack. This involved creating a dedicated API layer to interface between the chatbot and the graph database containers, alongside a custom front end that allowed executive users to interact with the system and view detailed explanations of the generated answers and the source documents upon which they were based. Early feedback highlighted the system’s ability to connect structured and unstructured content seamlessly, paving the way for broader adoption.

Providing a Roadmap for Further Development

Beyond the initial POC, the project laid out clear next steps. Recommendations included refining the chatbot’s response logic, optimizing performance (notably in embedding and document chunking), and enhancing user experience through additional ontology-driven query refinements. These steps are critical for evolving the system from a demonstrative tool to a fully integrated component of the foundation’s data management and access stack.

 

 

The EK Difference

A key differentiator of this project was its adoption of standards-based semantic graph technology and its highly generalizable technical architecture. 

The architecture comprises:

Investment Ontology and Data Mapping:

A rigorously defined ontology underpins the entire system, ensuring that all investment-related data—from structured datasets to narrative reports—is harmonized under a common language. This semantic backbone supports both precise data integration and flexible query interpretation.

Graph Instantiation Pipeline:

Investment data is transformed into RDF triples and instantiated within a robust graph database. This pipeline supports current data volumes and is scalable for future expansion. It includes custom tools to convert CSV files and other structured datasets into RDF and mechanisms to continually map new data into the graph.

Semantic RAG Agentic Workflow and API:

The solution utilizes a semantic RAG approach to navigate the complexities of cross-document query answering. This agentic workflow is designed to minimize unhelpful hallucinations, ensuring that each answer is traceable back to the underlying data. The integrated API provides a seamless bridge between the front-end chatbot and the back-end graph, enabling real-time, explainable responses.

Investment Chatbot Deployment:

Built as a central interface, the chatbot exemplifies how graph technology can be operationalized to address executive-level investment queries. It is fine-tuned to reflect the foundation’s language and domain knowledge, ensuring that every answer is accurate and contextually relevant.

 

The Results

The POC successfully demonstrated that GRAG could answer complex questions by:

• Delivering coherent and explainable recommendations that bridged structured and unstructured investment data.
• Significantly reducing query response time through a tightly integrated semantic RAG workflow.
• Providing a transparent AI mapping that allowed stakeholders to see exactly how each answer was derived.
• Establishing a scalable architecture that can be extended to support a broader range of use cases across the foundation’s data ecosystem.

This project underscores the transformative potential of graph technology in revolutionizing how investment health is assessed and how strategic decisions are informed. With a clear roadmap for future enhancements, the foundation now has a powerful, next-generation tool for deep, context-driven analysis of its investments.

 

Download Flyer

 

The post Humanitarian Foundation – SemanticRAG POC appeared first on Enterprise Knowledge.

As investment consultants, my parents were contacted by a variety of people looking for advice on how to handle their finances, from a small savings account to million dollar inheritances. These conversations with customers were usually over the phone, and it was my parents’ job to turn those quick calls into actual client leads. In order to answer difficult questions and sound like experts in the financial world, they depended on Charles Schwab’s intranet and internal help desk. This information database and direct access to human resources supplied employees with a wealth of knowledge in a time when the internet was brand new and most companies didn’t have websites to advertise their products and services.  

Knowledge Management, in its simplest terms, is about connecting the right information to the right people at the right time. This concept is especially important in organizations where contact centers and help desks are a significant business function and employees with less experience may be speaking directly with potential clients or customers. Every employee in an organization, regardless of age or experience, should be equipped with the knowledge and tools they need to become an expert in their field and successfully communicate their company’s breadth of information and services to people who call in. In addition to the KM tools that will be detailed later in this blog, company leadership should prioritize and foster a culture of knowledge sharing, where information is routinely organized and shared in the correct channels and systems for enterprise-wide use. 

Help desks are frequently the primary point of contact for customers who have questions about the company’s products or services. Given frequent turnover and a difficult hiring environment, companies struggle to hire and retain the most knowledgeable people for their help desks. This is a problem, but cannot be an excuse. If experts are not available to fill these positions, those employees who do receive the calls need direct access to use cases, platform permissions, step-by-step instructions, links, and everything else that would be required to resolve the customers’ problems. 

Contact centers often serve a much broader purpose and are essentially a customer service department that handles customer complaints, orders, inquiries, etc. In this case, callers may already be frustrated, upset, or dissatisfied, making seamless access to the right information at the right time even more critical to deliver quality customer service. 

Apart from the knowledge sharing culture and values that a strong KM foundation provides, there are several specific KM tools that we recommend for superior customer service in any of these business areas:

	Knowledge Base A knowledge base is a repository of enterprise-wide knowledge that should be the primary source for call agents to solve and respond to customer queries. Similar to the one that my parents described working with all those years ago, a functional knowledge base should have intuitive search capabilities and a user interface that allows for easy and rapid navigation. This will improve employees’ experience as well as customer satisfaction, as employees will feel confident and empowered when they have the necessary resources at their fingertips to excel in their jobs.
	Artifacts  Call agents should also have direct access to artifacts that can be sent directly to customers for more detailed information or future reference. These can be FAQs, articles, how-to guides, device instructions, videos, or any other simple visual guide that can act as a follow-up to a customer call.
	Intelligent Chatbots There is no denying that in many companies, contact centers and help desks have declined in usage as customers have more and more access to self-service channels. Tech-savvy customers expect a useful and streamlined self-service experience, especially when contacting a larger company. Artificial intelligence (AI) tools like chatbots can be extremely effective and dependable to solve customer problems and provide human-like resolutions using Natural Language Processing (NLP). When integrated with a knowledge base and visual guides, call agents can deflect calls directly to a chatbot with the confidence that those customers will get the answers they need as quickly as possible. This type of holistic support ensures that an organization provides assistance to every single customer while keeping employees from burnout and reducing support costs.

By establishing systematic and repetitive ways to deliver information to customers, an organization will possess consistent and positive customer experience as one of its key differentiators. Modern-day customers are used to digital self-service, but we all know how frustrating it can be to dial numbers over and over without ever finding a sufficient answer to a query. Until chatbots can entirely replicate human assistance, prioritizing Knowledge Management for contact centers and help desks will continue to improve customer service Key Performance Indicators (KPIs) and give service organizations a competitive advantage unlike any other. 

Measuring customer service KPIs is a great way to quantify the effectiveness of KM in these parts of an organization. These KPIs can vary depending on the organization, but they include metrics like agent training time, agent errors, repeat calls, mean call time, resolution time, etc. Effective KM can help your organization lower customer service costs by reducing the time and efforts agents spend responding to customer inquiries, thereby building a strong business case for continued KM transformations. Are customer issues usually resolved during first contact? Are customers experiencing faster resolution times? Are agents prioritizing proactive development of self-service content based on common issues faced by customers? These are questions that KM stakeholders should seek answers to in order to identify service gaps in these departments and measure Return on Investment (ROI) from the implementation of the tools described above. These tools can be highly effective in improving these KPIs, and organizations should develop reporting that shows hard progress against these metrics to garner buy-in and support for KM efforts.

Once implemented, these tools can immediately begin demonstrating the benefits of KM for contact centers and help desks:

• Findability: With consistent and intuitive tagging of all content within a knowledge base, a call agent will be able to find direct answers to customer queries faster, easier, and more completely. A clear and easy user interface within a self-service portal will allow customers to quickly find answers to their questions and understand what an organization has to offer them. 
• Consistency: Information governance is a key tenant of good KM. An organization should establish governance processes for its knowledge base to ensure content remains new, accurate, and complete for call agents’ reference, varying from content reviews to ownership to workflows. Here at EK, we have seen countless knowledge bases overrun with outdated and obsolete content, and good governance practices are the best way to counteract that trend. 
• Collaboration: As mentioned before, a culture of knowledge sharing is a powerful way to ensure call agents and support staff are equipped for any customer question, even without the implementation of actual KM tools. Agents can work confidently knowing that they are surrounded by others who are willing to help and distribute knowledge in whatever way they can, adding another resource for agents who cannot immediately find what they are looking for in a knowledge base.  
• Consumability: Structured content (that with predefined formats and organization) will be easy for agents to read, quickly understand, and then act upon. Good KM will ensure content is delivered to agents in the right format, scale, and scope for the situation, maximizing readability and minimizing cognitive load. 
• Flexibility: Most of the time, an agent will need a quick and concise answer for a customer. However, in times when deeper answers are needed or desired, agents will have opportunities and resources to explore related content that is tagged similarly in the knowledge base.
• Supportability: Good KM dictates clear job roles and organizational structure. In more serious situations, agents will know when and to whom the situation should be escalated.

EK has experience with many projects of this nature, utilizing KM best practices to improve the efficiency of contact centers and help desks. One example is the work we did with the principal revenue collection agency of a national government overseas. In this engagement, the agency was having difficulty standardizing and managing content in their internal tool designed to guide service agents towards the correct information they need to support their customers. To help these service agents more easily locate content and navigate complex regulations and concepts, EK provided comprehensive Content Transformation Services which included Content Strategy and Governance Design. As a result of these efforts, the agency was positioned to standardize the way information is captured and managed across the enterprise, enabling content to become more findable, scannable, and intuitive to follow for service agents. Service agents spent less time finding applicable content within their internal tool, translating to a decrease in mean-time-to-resolve (MTTR) customer inquiries. 

Overall, Knowledge Management in contact centers and help desks makes it smoother and more efficient for agents to find and use information. Customers expect and will often demand timely, personalized service; if these needs are not met, the organization will likely lose that customer. Every organization with a contact center or help desk must make sure their agents are equipped and empowered with the right knowledge and tools to correctly answer questions and provide relevant information. By investing in KM in these areas, your organization can ensure the satisfaction and longevity of both customers and employees. Here at EK, we offer many services to help organizations improve document management, content governance, search functionality, and so much more that can further the best practices detailed above. If you think your organization could benefit from Knowledge Management, contact us today to learn more about our services.

The post The Benefits of KM for Contact Centers and Help Desks appeared first on Enterprise Knowledge.

The Solution

To organize and typify the various categories of both the institution’s knowledge and that of its employees, EK enriched their business taxonomy, developed an ontology and a knowledge graph to create a semantic hub (colloquially referred to as “The Brain”) that, while leveraging the knowledge graph, collects organizational content, user context, and project activities. This solution uses AI to automatically deliver content to bank employees when and where they need it. The Brain was built on a graph database and a taxonomy management tool. Content from around the organization is auto-tagged (using the taxonomy management tool) and collected within the graph database. Together, these two tools, in which this aggregated information is managed and stored, power a recommendation engine that delivers contextualized recommendations via email, suggesting (in the form of links or attachments) relevant articles and information per the following scenarios:

• A user schedules a calendar event on a given topic, or 
• New content is introduced to the system that matches a user’s pre-defined interests.

Presently, the same strategy is being expanded to power a chatbot as part of the bank’s larger AI Strategy. These outputs are published to the bank’s website to help improve knowledge retention and to showcase the institution’s in-house expertise via Google recognition and search optimization for future reference.

The EK Difference

Leveraging our vast experience with taxonomy/ontology design and semantic technologies, we helped the bank model their domain through a series of workshops and stakeholder interviews. Once the domain was in place, we applied our expertise in Solutions Architecture and Big Data orchestration to develop an application that quickly and efficiently loads and tags content from multiple sources into a single repository – a Knowledge Graph – used to provide recommendations to bank staff.

We specifically applied our core competency in analysis, design, implementation, operations, and maintenance of information management systems and technical platforms for managing subject expert knowledge and topical information to ensure the bank had a solution that met their specific needs. Throughout the entire process, EK went beyond technical implementation, engaging with business users to ensure we were designing interfaces, workflows, security models, content cleanup practices, classification procedures, and governance guidelines to inform and define the long-term adoption and sustainability of the system.

EK further employed our data science and engineering experience to iteratively enable knowledge-oriented AI to train the recommendation algorithm and upstream applications to consume and “understand” the bank’s data in a manner similar to which their staff understands and uses it.

The Results

In addition to connecting people to information, the tool is providing timely content recommendations on three different web applications and in advance of important meetings, as well as via a Chatbot service.

Using knowledge graphs based on this linked data strategy enabled the bank to connect all of their knowledge assets in a meaningful way to:

• Increase the relevancy and personalization of the search experience;
• Enable employees to discover content across unstructured content types, such as webinars, classes, or other learning materials based on factors like location, interest, role, seniority level, etc.; and
• Further facilitate connections between people who share similar interests, expertise, or location.

Knowledge-AI_-Content-Recommender-and-Chatbot-Powered-Auto-Tagging-and-an-Enterprise-Knowledge-GraphDownload

The post Knowledge AI: Content Recommender and Chatbot Powered by Auto-Tagging and an Enterprise Knowledge Graph appeared first on Enterprise Knowledge.

Successfully building, implementing, and scaling an enterprise knowledge graph is a serious undertaking. Those who have been successful at it would emphasize that it takes a clear definition of need (use cases), an appetite to start small, and a few iterations to get it right. When done right, a knowledge graph provides valuable business outcomes, including a scalable organizational flexibility to enrich your data and information with institutional knowledge while aggregating content from numerous sources to enable your systems’ understanding of the context and the evolving nature of your business domain. 

Having worked on multiple knowledge graph implementation projects, the most common question I get is, “what does it take for an organization to maintain and update an enterprise knowledge graph?” Though many organizations have been successfully building knowledge graph pilots and prototypes that adequately demonstrate the potential of the technology, few have successfully deployed an enterprise knowledge graph that proves out the true business value and ROI this technology offers. Such forethought about governance from the get-go plays a key role in ensuring that the upfront investment in a tangible solution remains a long-term success. Here, I’ll share the key considerations and the approaches we have found effective when it comes to instituting successful approaches to grow and manage an enterprise knowledge graph to ensure it continues serving the upstream and downstream applications that rely on it.

First and foremost, building an effective knowledge graph begins with understanding and defining clear use cases and the business problems that it will be solving for your organization. Starting here will enable you to anticipate and tackle questions like: 

“Who will be the primary end-users or subject matter experts?” 

“What type of data do you need?”

“What data or systems will it be applied to?” 

“How often does your data change?” 

“Who will be updating and maintaining it?”

Addressing these questions early on will not only allow you to shape your development and implementation scope, but also define a repeatable process for managing change and future efforts. The section below provides specific areas of consideration when getting started.

1. Build it Right – Use Standards

As a natural integration framework, an enterprise knowledge graph is part of an architectural layer that consists of a wide array of solutions, ranging from the organizational data itself, to data models that support object or context oriented information models (taxonomy, ontology, and a knowledge graph), and user facing applications that allow you to interact with data and information directly (search, analytics dashboards, chatbots, etc). Thus, properly understanding and designing the architecture is one of the most fundamental aspects for making sure it doesn’t become stale or irrelevant. 

A practical knowledge graph needs to leverage common semantic information organization models such as metadata schemas, taxonomies, and ontologies. These serve as data models or schemas by representing your content in systems and placing constraints for what types of business entities are connected to a graph and related to one another. Building a knowledge graph through these layers that serve as “blueprints” of your business processes helps maintain the identity and structure for your knowledge graph to continue growing and evolving through time. A knowledge graph built on these logical models that are explicitly defined makes your business logic machine readable and allows for the understanding of the context and relationships of your data and your business entities. Using these unifying data models also enables you to integrate data in different formats (for example, unstructured PDF documents, relational databases, and structured text formats like XML and JSON), rendering your enterprise data interconnected and reusable across disparate and diverse technologies such as Content Management Systems (CMS) or Customer Management Systems (CRM). 

When building these information models (taxonomies and ontologies), leveraging semantic web standards such as the Resource Description Framework (RDF), the Simple Knowledge Organization System (SKOS), and the Web Ontology Language (OWL), offer many long term benefits by facilitating governance, interoperability, and scale. Specifically, leveraging these well-established standards when developing your knowledge graph allows you to: 

• Represent and transfer information across multiples systems, solutions, or types of data/content and avoid vendor lock to proprietary solutions; 
• Share your content internally across the organization or externally with other organizations;
• Support and integrate with publicly available taxonomies, ontologies, and linked open data sources to jump start your enterprise semantic models or to enrich your existing information architecture with industry standards; and
• Enable your systems to understand business vocabulary and design for its evolution.

2. Understand the Frequency of Change and the Volume of Your Data

A viable knowledge graph solution is closely linked to the business model and domain of the organization, which means it should always be relevant, up to date, accurate, and have a scalable coverage of all valuable sources of information. Frequent changes to your data model or knowledge graph means your organization’s domain is in constant shift and needs your knowledge and information to constantly keep up. 

These types of changes should not require the rebuilding or restructuring of your entire graph.  As such, depending on your industry and use cases, determining the frequency and update intervals as well as your governance model is a good way to effectively govern your enterprise knowledge graph.

For instance, for our clients in the accounting or tax domain, industry and organizational vocabulary/metadata and their underlying processes/content are relatively static. Therefore the knowledge, entities, and processes in their business domain don’t typically change that frequently. This means real-time updates and editing of their knowledge graph solution at a scale may not be a primary need or capability that needs focus right away. Such use cases allow these organizations to realize savings by shifting the focus from enterprise level metadata management tools or large scale data engineering solutions to effectively defining their data model and governance to address the immediate use cases or business requirements at hand.  

In other scenarios for our clients in the digital marketing and analytics industry, obtaining a 360-view of a consumer in real-time is their bread and butter. This means that marketing and analytics teams need to immediately know when, for example, a “marketable consumer” changes their address or contact information. It is imperative in this case that such rapidly changing business domains have the resources, capabilities, and automation necessary to update and govern their knowledge graphs at scale.

3. Develop Programmatic Access Points to Connect Your Applications:

Common enterprise knowledge graph solutions are constructed through data transformation pipelines. This renders a repeatable process for the mapping of structured sources and the extraction, disambiguation, classification, and tagging of unstructured sources. It also means that the main way to affect the data in the knowledge graph is to govern the input data (e.g. exports from taxonomy management systems, content management platforms, database systems, etc.). Otherwise, ad-hoc changes to the knowledge graph will be lost or erased every time new data is loaded from a connected application. 

Therefore, designing and implementing a repeatable data extraction and application model that is guided by the governance of the source systems is one of the fundamental architectures to build a reliable knowledge graph.  

4. Put validation checks and analytics processes in place

Apply checks to identify conflicting information within your knowledge graph. Even though it’s rather challenging to train a knowledge graph to automatically know the right way to organize new knowledge and information, the ability to track and check why certain attributes and values were applied to your data or content should be part of the design for all data that is aggregated in the solution. One technique we’ve used is to segment inferred or predicted data into a separate graph reserved for new and uncertain information. In this way, uncertain data can be isolated from observed or confirmed information, making it easier to trace the origins of inferred information, or to recompute inferences and predictions as your underlying data or artificial intelligence models change. Confidence scores or ratings in both entities and relationships can also be used to indicate graph accuracy. Additional effective practices that provide checks and processes for creating and updating a knowledge graph include instituting consistent naming conventions throughout the design and implementation (e.g., URIs) and establishing guidelines for version control and workflows, including a log of all changes and edits to the graph. Many enterprise knowledge graphs also support the SHACL Semantic Web standard, which can be used to validate your graph when adding new data and check for logical inconsistencies.

5. Develop a Governance Plan and Operating Model

An effective knowledge graph governance model addresses the common set of standards and processes to handle changes and requests to the knowledge graph and peripheral systems at all levels. Specifically, a good knowledge graph governance model will provide an approach or specification for the following: 

• Governance roles and responsibilities. Common governance roles include a governance group of taxonomists/ontologists, data engineers or scientists, database and application managers and administrators, and knowledge or business representatives or analysts;
• Governance around data sources that feed the knowledge graph. For instance when there’s unclean data coming in from a source system, specific roles and processes for correcting this data;
• Specific processes for updating the knowledge graph in the system it is managed (i.e., processes to ensure major and minor changes to the knowledge graph are accurately assessed and implemented). Including governance around adding new data sources — what does it look like, who needs to be involved, etc.;
• Approaches to handle changes to the underlying ontology data model. Common change requests include addition, modification or depreciation of an ontological class, attributes, synonyms or relationships; 
• Approaches to tackling common barriers to continue building and enhancing a successful ontology and knowledge graph. Common challenges include lack of effective text analytics and extraction tools to automate the organization of content and application of tags/relationships, and intuitive management and updates to Linked Data;  
• Guidance on communication to stakeholders and end users including sample messaging and communication best practices and methods; and 
• Review cadence. Identify common intervals for changes and adjustments to the knowledge graph solution by understanding the complexity and fluidity of your data and build in recurring review cycles and governance meetings accordingly 

Closing

As a representation of an organization’s knowledge, an enterprise knowledge graph allows for aggregation of a breadth of information across systems and departments. If left with no ownership and plan, it can easily grow out of sync and result in rework, redesign and a lot of wasted effort. 

Whether you are just beginning to design an enterprise knowledge graph and wish to understand the value and benefits, or you are looking for a proven approach for defining governance, maintenance, and plan to scale, check out our additional thought leadership and real world case studies to learn more. Our expert graph engineers and consultants are also on standby if you need any support. Contact us with any questions.

The post How Do I Update and Scale My Knowledge Graph? appeared first on Enterprise Knowledge.

Look to the concepts featured above to guide the initial phases of your chatbot ideation process and to ensure its design is future-ready from the start. Whether you’re ready to begin chatbot implementation or are more curious about the benefits a chatbot can bring to your organization, contact us to join you on your chatbot journey, no matter where you are.

The post Consider the User: A Chatbot UX Guide appeared first on Enterprise Knowledge.

In my last blog, I introduced the how of chatbots: how they work, how they’re implemented, and how they can help your organization, whether that’s through supporting your customer experience team, connecting users to information and research at the point of need, or request mapping. I also closed the blog with a line about the user experience that’s integral to successful chatbot implementation: “chatbots allow for a customized user experience, and not only allow users to get the information they need more quickly, but can be designed and oriented toward each user’s unique intent and interest.” This blog considers four key elements integral to creating a user-oriented chatbot experience. I’ve also included a selection of questions and considerations to ask yourself and your team before beginning the process of designing and developing the user experience of your chatbot. 

Define Your Purpose

At the outset of your chatbot design and development process, you’ll want to define the chatbot’s purpose. Is it going to be oriented towards supporting your CX team or to connecting users to relevant research and publications? Part of your purpose will be pre-defined by the type of organization you are and the services you provide. When deciding what the purpose of your chatbot will be, consider areas of weakness in your organization and if those areas could benefit from chatbot-oriented services. A strong purpose statement can serve as your ‘north star’ throughout the development process and guide decision-making so that the end product aligns with your initial goal. Having a clear ‘north star’ purpose will also be invaluable throughout the necessary content clean-up and tagging process that happens prior to chatbot development. Additionally, the iterations and use case validations that occur during development should consistently be matched against, and support, your purpose. 

Questions to consider:

• If you’re considering a phased approach to chatbot implementation, what do those phases look like? Does your purpose statement hold true during each of those phases of development?
• Some purpose statements include elements of both the emotional and the rational. Decide how you want your chatbot to make your users feel and consider not only what that looks like from a visual perspective, but the steps necessary to make that happen. What processes must your chatbot be able to carry out flawlessly? What is its main job? What is the use case for your chatbot?

AI & Chatbots

Artificial Intelligence (AI) chatbots have the ability to ‘learn’ in the sense that they’re designed to spot and track trends and patterns in data, like repeat user questions. The programming behind these chatbots is written in a way that not only tracks these patterns, but also applies those patterns where applicable, allowing the chatbot to most aptly service users’ needs without consistent human intervention. For example, consider a company that sells cell phones: user questions about a nonfunctioning power button or a cracked screen would both be routed to a physical repairs webpage.

Questions to consider:

• How ‘smart’ do you want your chatbot to be? Should it be able to notice and document patterns in user queries and adjust its responses in return or should it be designed to answer a set of  targeted, but common, questions?
• What are the more advanced features you envision your chatbot offering? If its main purpose is to connect users to customer service representatives through a series of Boolean questions, you can go light on AI and machine learning capabilities.
• How often and with what resources are you willing or able to dedicate to your chatbot? A chatbot oriented around Boolean questions requires considerably less investment than a chatbot designed to ‘learn.’

Natural Language Interface/Conversational User Interface (CUI)

Chatbots allow users to interact with a computer interface on their own terms and in their own language, regardless of whether the chatbot’s communication process is triggered through Boolean operators (‘Did you want to cancel your internet services?’) or actual queries (‘What publications do we have about bridge development in Paraguay?’). And while Boolean operators limit the questions a user can ask of the chatbot and, in turn, what the chatbot understands, implementing a Boolean-oriented chatbot is an excellent option for a Proof of Concept to prove out a larger, more complex chatbot project.

Questions to consider:

• Related to both the AI section above and the Purpose section below, consider how conversational you need your chatbot to be. Spend some time brainstorming the types of questions you expect your users to ask, and then consider what questions would ‘break’ your bot. Be prepared to spend some time reworking your bot’s logic to address these breaking points. For instance, should your users be able to escape a bot-guided and intent-specific process? In one of our projects, users were finding that they couldn’t request help while looking at publications (i.e. the intent here is ‘view publications’). The bot’s conversational structure had to be reformatted to guide the user through the required steps to complete an intent before returning them to a point where they can choose a new intent.
• When your bot breaks (and it will), how should it respond and prompt the user to try another query? Does it recommend alternative or popular queries submitted by other users?

Personalized Brand Experience

The visual interface of the chatbot should be aligned with your organization’s branding guidelines so that it doesn’t appear to be adversely operating as a separate function of your organization’s user experience strategy. And because chatbots leverage a natural language interface, you’ll want to spend some time crafting the tone and formality of your chatbot’s responses so it interacts with your users in a language akin to your company’s brand and ethos. Your decisions here dictate how your chatbot will look, ‘speak,’ and behave.

Questions to consider:

• Is your organization’s branding up-to-date? Do your design and development teams have access to this branding? While this may seem like an obvious place to start any design process, it’s always a good idea to ascertain that everyone has access to the same, and correct, materials.
• Have you defined the ‘voice’ of your brand? If your brand were a person, how would they talk? Consider the vibe and tone you want conveyed through your chatbot’s ‘speech.’

Conclusion

With some dedicated thought and draftwork, the prompts featured above should help kickstart your organization’s chatbot design process. And while the above points are integral to the chatbot implementation process and can inform your organization’s initial design and development decisions, there’s some necessary data mapping and ontology design work that needs to happen behind the scenes so that your chatbot is both relevant and helpful. Use the prompts above to get a head-start on your chatbot’s design, and contact us if you’re interested in better understanding the chatbot implementation process from an end-to-end perspective.

The post The UX Guide to Chatbots appeared first on Enterprise Knowledge.