Domain 4: Integrate with watsonx

IBM Certified Specialist - watsonx Assistant · 37 questions

• A customer service team wants their watsonx Assistant to answer complex product questions by pulling information from a company documentation database. Answers should be synthesized into natural language rather than returning verbatim text chunks. Which approach should the engineer implement?
• An engineer needs to connect watsonx Assistant to IBM watsonx.ai so the assistant can invoke a foundation model for generating responses. Which configuration step is required inside the watsonx Assistant interface?
• An engineer wants to enable watsonx Assistant to answer unstructured questions by searching a connected Elasticsearch index of company documents. Which watsonx Assistant feature should the engineer configure?
• A developer has configured a custom extension for an external CRM API but the assistant always returns an error when the extension is invoked. The extension requires an OAuth 2.0 bearer token. Where in the watsonx Assistant UI should the developer supply the OAuth credentials?
• A healthcare organization stores clinical guidelines in an Elasticsearch cluster. They want watsonx Assistant to search those guidelines when answering clinician queries. Which search integration type should be configured?
• An engineer wants to add generative AI capabilities to watsonx Assistant without writing custom integration code. They want to use IBM-provided, pre-built connectors. Where should they look first?
• An engineer configuring conversational search wants to control how the LLM synthesizes its final response from retrieved document passages. Specifically, they need to add instructions about response tone and maximum length. Where should these instructions be placed?
• A financial services company needs their assistant's answers to be strictly based on internal policy documents, with no information fabricated by the LLM. Which watsonx Assistant capability best ensures this grounding?
• A user asks watsonx Assistant 'What are the onboarding requirements?' and then follows up with 'How long does the process take?' The assistant fails to connect the follow-up to the earlier topic and returns an unrelated answer. What should the engineer configure to resolve this?
• A legal firm's assistant is missing relevant contract clauses when users phrase questions differently from the exact terminology in the documents. For example, a search for 'termination rights' fails to surface passages about 'right to end the agreement.' Which configuration change addresses this?
• After deploying conversational search, an engineer notices the assistant occasionally returns AI-generated answers that are irrelevant to the user's question. They want the assistant to show a 'no answer found' message when retrieved passages are below a certain relevance score. Which setting should be adjusted?
• An organization has product documentation ingested into IBM Watson Discovery collections. They want watsonx Assistant to search those collections to answer customer questions. Which configuration is most appropriate?
• An engineer has set up a complete RAG pipeline: Elasticsearch is configured as the search integration, and the custom watsonx.ai extension is connected for LLM-powered response generation. Users report that answers within a single session are accurate for standalone questions but the assistant loses track of earlier questions when users ask follow-ups. What is the most likely missing configuration?
• Before connecting watsonx Assistant to a foundation model on watsonx.ai; what IBM Cloud resource must exist?
• Which LLM parameter in a watsonx.ai connection controls how random or deterministic the model output is?
• A developer wants to use a watsonx.ai foundation model to generate natural language summaries inside an action. What must be configured?
• Which watsonx.ai parameter controls the maximum number of new tokens the model will generate in a single call?
• A developer wants LLM responses to conform to a specific output format. Which approach in the Generative AI extension achieves this?
• What is prompt tuning in the context of watsonx.ai and watsonx Assistant?
• A developer wants an action step to call a watsonx.ai model for summarization. What extension type is used?
• What does the 'stop sequence' parameter do in a watsonx.ai LLM configuration?
• Which IBM Cloud service must be provisioned before using the Generative AI extension in watsonx Assistant?
• Which LLM parameter limits word selection at each generation step to the K most probable tokens?
• A developer wants to prevent the watsonx.ai model from repeating phrases. Which parameter should be adjusted?
• When connecting watsonx Assistant to a foundation model on watsonx.ai; which authentication credential is required?
• A developer wants to use the IBM granite-13b-instruct model. What must be verified first?
• In a Generative AI extension; what does the 'system prompt' field define?
• What is the practical effect of setting temperature to 0.0 for a watsonx.ai call?
• Which watsonx.ai feature should a developer use to test a foundation model interactively before integrating it into an assistant?
• Which watsonx.ai parameter seeds the random number generator to allow reproducible model outputs?
• In a Generative AI extension call; what does the 'input' field contain?
• A Generative AI extension system prompt says 'You are a helpful insurance agent. Only answer insurance coverage questions.' What is the effect?
• What is 'top K' sampling in the context of watsonx.ai foundation model parameters?
• A developer wants the model to stop generating after producing the phrase 'END OF ANSWER.' Which parameter controls this?
• What distinguishes prompt tuning from full fine-tuning of a foundation model?
• Where does the assistant inject the user message when calling a Generative AI extension?
• How does 'greedy' decoding differ from 'sampling' in watsonx.ai?