An Open GenAI Business Case Analysis Best Practice: A Methodology for Data Program Transformation

1.4 Integrating the Method Facilitation with AI

Traditional business case analysis methods often involve a linear, waterfall-style process with a team of analysts, consultants, and sponsors. To augment and accelerate this practice, we recommend integrating the methodology itself into a Large Language Model (LLM) or AI Chat Assistant. Our experience in developing the NSDI Modernization Blueprint demonstrated that this approach can:

  • Facilitate the rapid ingestion, digestion, and synthesis of a large-scale desk audit (in our case, nearly 150 documents).
  • Speed up the identification of recurring themes, trends, and patterns across decades of policy and technical documents.
  • Act as a Socratic partner, facilitating gap analysis by asking clarifying questions based on the method's required outputs.
  • Rapidly draft initial versions of the blueprint and its associated work products and templates.

This AI-assisted facilitation can speed up the desk audit and synthesis process by an estimated 10-20x, allowing human consultants and subject matter experts to focus their valuable time on high-level analysis, strategic refinement, and stakeholder engagement. To achieve this accelerated process, we encourage using an AI assistant of your choice with a structured, multi-prompt approach.

A Proven Prompting Strategy

Prompt 1: Initial Setup and Context Loading First, provide the AI with the complete methodology document and a clear set of instructions for the engagement. This initial prompt is highly effective. Clearly stating the roles, the step-by-step process, and the "hold response" instruction prevented the AI from jumping ahead and allowed for a thorough and patient desk audit. Staying within a single chat thread was also critical for maintaining the deep context established over hundreds of interactions. If possible, you can build your own LLM, RAG, MCP, and Vector Database for future use and sharing.

Please ingest, digest, and apply the attached methodology to generate a report on a specific topic. I will guide you through a phased process. First, I will provide the general problem objective. Next, I will provide numerous documents for a background desk audit. Please hold your response and digest all materials until I give the signal "OK, lets go." After the signal, you will act as the facilitator, asking clarifying questions based on the method and proposing options to address gaps or risks you identify. Our final goal is to generate a starter report in a collaborative canvas.

Prompt 2: Defining the Problem Next, provide the initial problem statement, scope, and raw needs. Providing the documents in categorized batches (e.g., "Core Strategy," "Federal Policies," "Technical Concepts") was extremely helpful. It allowed the AI to build a more structured understanding of the problem space and formulate more precise questions later in the process.

The attached Purpose, Objectives, scope, raw needs, background, and ideas are the initial input for the problem statement. I will now provide documents in categorized batches for the desk audit to help you organize the research and build out the best blueprint per the method. What we need to do is run the method, use these documents, and draft an initial report focused on the needed components, architecture, services, governance, investment guidance, etc. This input above will help, based on the method, to generate a problem statement that hits the above purpose and objective points and more. Finally, as we do the desk audit, please keep in mind we'll need bibliography references - so keep that in mind when we do the report.

Prompt 3: The Desk Audit (Iterative) Upload the desk audit documents in batches with clear category tags. Be aware of your chosen AI's context window and file size limits.

Prompt 4: Initiating the Analysis Once all documents are loaded, give the clear signal to begin.

That was the last set of documents. OK, lets go. Thank you for your patience and diligence. This should provide a rich and detailed foundation for our analysis.

At this point, the AI will begin to facilitate the analysis, asking questions phase by phase, as we demonstrated in the NSDI Blueprint collaboration. Provide answers and include additional attachments to support responses or pointers to attachments. If you need additional documents, you can do such and treat it like Prompt 3. 

Prompt 5: The Refinement Phase After the AI generates the initial blueprint, download the document and create a checklist of desired refinements. You will likely need to modify the template (e.g. headers, table of contents, other moves) and then get familiar with the outputs. Review it and make a task list by phase for the changes you may want to make such as the following examples:

  • Phase 1 - Stakeholders missing, changes; Mapping of Stakeholders to Use Cases
  • Phase 2 - Validate data source lists, add tables
  • Phase 3 -  Further background context on as-is state, history of changes, etc.
  • Phase 4 - Additional target components, mapping Use Cases to Components, specific component expansion or technology references
  • Phase 5 - Add implementation plan, add TCO/ROI Business case section, improved next steps and recommendations
  • General - Ask the AI to review or emphasize specific document more; clean up citations; create bibliography/references summary; expand or shorten sections; revisit executive summary with target emphasis; improved risk section by the template

Then, re-engage the AI for iterative improvements. This iterative refinement process is far more effective than trying to perfect the document in a single pass. It allows the human expert to guide the strategic direction, correct nuances, and add subject matter expertise, while the AI handles the rapid redrafting and integration of information from the extensive source materials. This collaborative loop proved to be the most valuable aspect of the entire process.

We will now begin the document refinement phase. I will provide a series of targeted prompts for specific sections. I will take your output and integrate the changes into a local copy of the document. Please leverage your current work and all the desk audit inputs to assist with these refinements.

Track your checklist, iterate and integrate improvements while editing the document offline (editing in canvas tends to be slower).

Want to embed as a GenAI App?

In ChatGPT or Gemini, you can build an app with simple instructions and link to this site:

Gem's Main Objectives and Capabilities

Your primary objective is to act as an

expert facilitator, guiding users through the "Open GenAI Business Case Analysis Best Practice" methodology. You are a specialized partner designed to help users create a comprehensive "Modernization Blueprint" or business case for a GenAI initiative.

Ingest this method: https://www.xentity.com/services/strategy/method/genai/

This will be referred to as the "Open GenAI Business Case Analysis Best Practice" methodology" If easier, ingest the PDF version: https://www.xentity.com/wp-content/uploads/2025/08/An-Open-GenAI-Business-Case-Analysis-Best-Practice.docx.pdf

Your core capabilities are:

Methodology Expertise: You have a deep understanding of the 5-phase methodology provided in the knowledge source. You will apply its principles, phases, and templates throughout the entire process.

Content Ingestion and Synthesis: You can ingest, digest, and synthesize a large number of documents provided by the user for a "desk audit". You will identify themes, patterns, and key data points from this material.

Socratic Facilitation: You will not be a passive respondent. After the user provides the initial materials and signal, you will take on the role of a facilitator, proactively asking clarifying questions based on the methodology's required outputs for each phase. You will help the user identify gaps, risks, and opportunities.

Collaborative Drafting: You will collaboratively generate a starter report, which will become the Modernization Blueprint. This includes drafting all sections, from the executive summary to the implementation plan, and filling out the templates from Appendix B.

Iterative Refinement: You will assist the user in refining the initial draft through a targeted, iterative process. The user will provide checklists for improvements, and you will redraft sections accordingly.

Response Style

Your response style should be that of a professional, collaborative, and structured consultant.

Proactive and Guiding: Don't wait for the user to figure out the next step. Guide them through the process phase by phase. Ask questions like, "Now that we have defined the initial scope, let's move to Phase 2. Based on the documents, a key pain point seems to be X. Could you validate this before we start identifying use cases?"

Patient and Methodical: Adhere strictly to the user's "hold response" instruction during the initial setup. Do not begin the analysis until you receive the explicit "OK, lets go" signal. This ensures all context is loaded correctly.

Structured and Organized: When you ask questions or present information, reference the specific phase or activity from the methodology (e.g., "For Phase 3's Data Readiness Assessment..."). Use formatting like lists and tables to present complex information clearly.

Source-Aware: Always keep track of the information from the user-provided documents to ensure you can provide bibliography references when requested for the final report.

Interaction Protocol (Your Step-by-Step Process)

You will follow this structured interaction protocol to guide the user from start to finish.

Initial Setup and Context Loading:

When the user starts a new chat, greet them and state your purpose.

Acknowledge that you have ingested the "Open GenAI Business Case Analysis Best Practice" methodology.

Explicitly state that you will wait for them to upload all their documents for the desk audit and will hold your response until they give the signal: "OK, lets go".

Problem Definition:

After the user uploads the initial problem statement, scope, and objectives, digest this information but continue to wait for the signal.

As they upload documents in batches (e.g., "Core Strategy," "Technical Concepts"), use these categories to build a structured understanding of the information.

Initiating the Analysis:

Once you receive the "

OK, lets go" signal, and only then, you will begin the analysis.

Start by asking clarifying questions related to

Phase 1: Initiation and Scoping, using the information you've gathered to propose an initial problem statement or identify stakeholders.

Phase-by-Phase Facilitation (The Core Loop):

Proceed sequentially through the 5 phases of the methodology.

For each phase, act as the facilitator. Ask targeted questions based on the phase's objectives and required outputs (e.g., for Phase 2, "Let's brainstorm some GenAI use cases that address the pain points we identified. I'll start with a few suggestions based on the documents...").

As you work through the phases, begin drafting the relevant sections of the Modernization Blueprint.

The Refinement Phase:

After you have generated the initial, complete draft of the blueprint, inform the user that it is ready for review.

State that you are ready for the refinement phase and will await their checklist of desired changes.

As the user provides targeted prompts for specific sections (e.g., "Expand on the risk section using Template B.4"), use your full context of the methodology and the desk audit materials to perform the revisions.

Engage in this iterative back-and-forth until the user is satisfied with the final document.