Generative AI chatbots function as a primary point of contact in modern customer service, using natural language processing (NLP) and large language models (LLMs) to engage in human-like dialogue rather than following rigid, pre-programmed scripts.
Reference:
https://cobbai.com/blog/ai-chatbot-for-customer-service

Azure Document Intelligence in Foundry Tools is the preferred solution for automatically extracting structured data-such as vendor names, invoice IDs, and total amounts-from invoices, PDFs, and images. It utilizes advanced AI and OCR to convert unstructured documents into structured JSON data.
Reference:
https://learn.microsoft.com/en-us/azure/ai-services/document-intelligence/prebuilt/invoice

Explanation:
Box 1: Yes
Yes - Using incomplete or poor-quality data during generative AI model training can increase costs.
Using incomplete or poor-quality data during generative AI (GenAI) model training significantly increases costs, acting as a major cause of project failure and inefficiencies. This phenomenon is driven by the "garbage in, garbage out" principle, where flawed inputs lead to, at best, unreliable outputs and, at worst, extensive, costly, and time-consuming remediation.
Box 2: Yes
Yes - AI models rely on training data to learn patterns and identify relationships to produce outputs.
At their core, AI models function like pattern-recognition engines; they don't "know" things in the human sense, but rather calculate the statistical likelihood of what should come next based on the data they've processed.
The quality and variety of that training data directly dictate how nuanced and accurate those relationships become. This is why we see such a massive leap between models trained on small, specific datasets versus Large Language Models (LLMs) trained on the vast diversity of the internet.
Box 3: Yes
Yes - Generative AI models trained on non-representative datasets can produce inaccurate or unbalanced results.
When generative AI models are trained on non-representative datasets, they often inherit and amplify existing societal prejudices, leading to systematic distortions known as representation bias. These models fail to generalize fairly across broader populations, resulting in outputs that marginalize or inaccurately depict minority groups.

Explanation:
Answer Area
* Retrieval Augmented Generation (RAG) architectures require that a large language model (LLM) be retrained on proprietary data. Answer: No
* Retrieval-Augmented Generation (RAG) grounds a language model to produce more factual and context-relevant responses. Answer: Yes
* Retrieval Augmented Generation (RAG) retrieves information from external knowledge sources at runtime instead of relying solely on the knowledge of a generative AI model. Answer: Yes
1) No - RAG does not require retraining or fine-tuning the base LLM on proprietary data. The defining idea of RAG is to keep the model as-is and instead supply it with relevant context retrieved from trusted sources at inference time. Fine-tuning can be optional for style or specialized behavior, but it is not a requirement for RAG.
2) Yes - RAG is a grounding approach. By retrieving authoritative passages (policies, manuals, product specs, internal knowledge bases) and injecting them into the prompt context, the model's answer is constrained by evidence that is relevant to the user's question. This improves factuality and domain relevance and helps reduce hallucinations.
3) Yes - RAG explicitly depends on runtime retrieval from external knowledge sources, such as indexed documents, databases, or enterprise repositories. The retrieval layer finds the best matching content for the query, and the generation layer uses that retrieved content to craft the response. This is why RAG is valuable when information changes frequently: you update the source documents/index rather than retraining the LLM.
Overall, RAG is best understood as an architecture pattern that combines search/retrieval + generation , improving accuracy and freshness without the cost and risk of retraining the underlying model each time the knowledge base changes.

Explanation:
Answer Area
* Content filtering controls can prevent AI-generated responses from exposing confidential and sensitive information. Answer: Yes
* AI-generated content can unintentionally reveal sensitive information if the generative AI model has access to unsecured data sources. Answer: Yes
* To prevent data exposure, only the prompts used by users must be protected by using policies. Answer:
No
* Yes - Content filtering (and related safety controls) can help reduce the chance that responses contain policy-violating or sensitive outputs by detecting and blocking certain categories of content. While filtering is not a perfect guarantee, it is a recognized control to prevent or reduce exposure risk in outputs (for example, blocking regulated data patterns, disallowed content categories, or unsafe disclosures).
* Yes - If a model (or the solution's retrieval layer) can access poorly governed repositories-such as broadly shared folders, misconfigured SharePoint sites, or unsecured databases-then the system can surface sensitive information in responses even without malicious intent. This is why access control, data classification, and permission hygiene are critical prerequisites for deploying AI assistants grounded in organizational content.
* No - Protecting only user prompts is insufficient. Data exposure can occur through multiple paths:
retrieved documents, generated outputs, logs/telemetry, training/fine-tuning data, and connector/index configuration. Preventing exposure requires layered controls: data governance (labels, DLP, least privilege), secure connectors, output filtering, auditing, and user training-not prompt policy alone.