This resource library brings together Claremont AI's guides for business leaders, practitioners, and teams exploring artificial intelligence. Each page focuses on a particular topic, with explanations and considerations to help you connect AI capabilities to real organizational needs. Start with the subject most relevant to your work, or use the library as a learning path from prompting fundamentals to implementation and governance.
Retrieval-Augmented Generation (RAG)
RAG connects a language model to relevant information retrieved from external sources. This guide explains the full workflow: document ingestion, parsing, chunking, embeddings, indexing, retrieval, ranking, and grounded answer generation. It compares basic RAG with hybrid, adaptive, corrective, graph based, multimodal, and agentic approaches. You will also find practical guidance on freshness, latency, reliability, access control, prompt injection, evaluation, and observability. Metrics such as Precision at k, Recall at k, MRR, NDCG, faithfulness, and citation quality are introduced. Start with a measured baseline, diagnose failures, and add complexity only when evidence supports it in practice. Explore architectures and production practices...
Read the RAG Guide
RICECAR AI Prompt Builder
The RICECAR Prompt Builder turns a request into structured instructions for an AI assistant. RICECAR means Role, Instruction, Context, Examples, Constraints, Ask Me, and Reflection. Each element clarifies the assistant's role, desired outcome, background, examples, boundaries, needed questions, or review criteria. Fill out the relevant fields, generate a prompt, then copy it into your preferred AI tool. Examples show how the framework can be adapted for marketing and software development. Not every task needs every field, and a structured prompt does not guarantee correctness. Review results, protect sensitive information, and refine instructions for the task and model. Build clearer prompts...
Open the Prompt Builder
AI Prompting Guide
This guide teaches practical ways to communicate goals, context, and expectations to AI systems. It explains why vague requests often produce generic answers, and how specific directions improve relevance and evaluation. Learn the RICECAR framework, including role, instruction, context, examples, constraints, clarification, and reflection. Compare weak and stronger prompts, and consider how audience, tone, format, and success criteria shape responses. The guide presents prompting as an iterative skill: inspect outputs, provide feedback, and refine requests. It recommends limiting sensitive data and checking factual or high impact results. Apply these habits to writing, summaries, research, brainstorming, and coding. Practice prompt design...
Read the Prompting Guide
Agentic AI Guide
Agentic AI systems pursue goals through sequences of decisions and actions. This guide explains planning, tool use, observing results, adapting, and deciding when to stop. It explores applications and implementation, emphasizing that autonomy should match task value and risk. Define allowed tools, action limits, error handling, and when human approval is required. Agent workflows can support multi step work but may add latency, cost, variability, and complexity. Compare agents with chatbots, scripted automation, and fixed workflows; deterministic rules may be enough. Start with a narrow use case, test fallbacks, and expand permissions when results justify it. Explore bounded agentic systems...
Read the Agentic AI Guide
Generative AI Guide
Generative AI models create text, code, images, and other content from learned patterns and user instructions. This guide introduces common capabilities and applications, distinguishing content generation from predictive systems. It also explains limitations: outputs may be inaccurate, biased, inconsistent, or unsupported, so fluent language is not proof. Organizational adoption requires useful task selection, data boundaries, review practices, governance, and user understanding. Learn how to frame a responsible pilot, define measurable outcomes, and determine when human review is needed. It connects generative AI with prompting, RAG, and agentic systems, helping readers assess value and risk before deployment. Build an adoption approach...
Read the Generative AI Guide
Predictive AI Guide
Predictive AI uses historical data to estimate outcomes, trends, or behavior. It distinguishes prediction, such as demand forecasting or churn risk, from generative AI. It introduces forecasting, classification, anomaly detection, and risk estimation, while explaining that data quality matters and patterns can change. Predictions are estimates, not certainties or explanations of cause. Responsible implementation needs success measures, suitable data, validation, and monitoring. Consider what decision a model will inform and how people will use its output. Communicate uncertainty, examine impacts across groups, and retain human oversight for consequential decisions. Choose a focused use case and measure both benefits and risks...
Read the Predictive AI Guide
AI Leadership Guide
This guide helps executives set direction for AI adoption. It covers connecting initiatives to business priorities, establishing governance, allocating resources, and building organizational capability. AI success depends on data readiness, workforce skills, executive alignment, risk management, and realistic expectations, not technology alone. Learn success factors for building an AI ready organization, supporting experimentation, and measuring progress. It helps leaders distinguish valuable opportunities from technology led projects without clear outcomes. Use it to frame discussions, clarify ownership, coordinate teams, and sponsor a path from pilots to sustainable adoption. Treat governance as a foundation for trust and learning. Lead AI with accountability...
Read the AI Leadership Guide
AI Maturity Model
The AI Maturity Model helps organizations assess AI capabilities and identify strategic next steps. Its framework considers technology alongside data readiness, governance, workforce skills, and operating practices. Use the assessment to discuss established capabilities, identify gaps, align expectations, and connect maturity levels to improvement actions. The model supports planning and leadership conversations, but does not replace evaluation of use cases; maturity can vary across teams and domains. Establish a baseline, prioritize improvements that support business goals, and revisit progress as capabilities evolve. Advancement is a sequence of deliberate steps, not a race to adopt new tools. Plan the next stage...
Explore the AI Maturity Model
AI Roadmap Guide
Plan your organization's AI adoption with guidance on use cases, implementation, governance, and measuring progress.
Explore the AI Roadmap
RICECAR Corporate Training
Explore a one-day, instructor-led program for building structured AI prompts and applying human judgment to the results.
Explore RICECAR Training
