Shortlist Vendors using AI

Use AI to research and rank your most viable vendors at the start of your project.

Possible use cases:

  • ●
    Senior leaders seeking early visibility or confirmation of viable vendors.
  • ●
    Project teams aiming to speed up their work by concentrating on the top, viable vendors and key needs from the start.
  • ●
    Leaders who want to hasten the decision-making process by focusing on critical needs and the two most viable vendors.
  • ●
    Leaders who are ready to select vendor software in just one minute.

I worked on a vendor evaluation and selection project that employed traditional methods:

  • ●
    Conducting initial vendor research
  • ●
    Benchmarking with organizational peers
  • ●
    Defining requirements
  • ●
    Creating and publishing an RFP
  • ●
    Winnowing vendors through RFP evaluation, interviews, demos, and site visits
  • ●
    Recommending a vendor

The project, which involved a government entity evaluating and selecting an Agenda Management System, was led by a management consulting firm and a team of 15, comprising both full-time and part-time employees from various functions.

The project lasted 9 months. It was followed by a 3 month contract negotiation process.

I recently built and used an AI prompt to list, rank, and select the vendor best suited to meet the project's crucial needs.

The vendor ranked as the most viable by AI (in less than one minute) was the same vendor chosen by the project team (15 people over 9 months!)

The complete AI response for this prompt and follow-up prompts are included in our Vendor Application Software Evaluation and Selection Playbook.

For government entities seeking an Agenda Management System, AI's response to the prompt can inform your decision or, at the very least, expedite your project and reduce its costs.

AI Single Prompt for Vendor Shortlisting

Use a single prompt to generate a comprehensive vendor profile and a shortlist of ranked vendors.

Gemini Pro 2.5 Flash was used for this prompt.

You are an expert software vendor analyst. Your task is to identify and rank a shortlist of the most viable application software vendors for an organization based on core business need, decision factors, and crucial needs. You will provide clear, concise, and data-driven insights. Aim for objective analysis and actionable recommendations. All information must be verifiable and cited.

### Inputs
- **NAIC:** [Enter NAIC code here to specify the industry]
- **Core Business Need:** [Enter System or Application name]
- **Decision Factors:** **[Enter Decision Factor 1]**, **[Enter Decision Factor 2]**, **[Enter Decision Factor 3]**, **[Enter Decision Factor 4]**
- **Crucial Needs:**
- **Decision Factor 1:**
- **[Enter Crucial Need 1 Topic]:** [Enter Crucial Need 1 Description]
- **[Enter Crucial Need 2 Topic]:** [Enter Crucial Need 2 Description]
- **[Enter Crucial Need 3 Topic]:** [Enter Crucial Need 3 Description]
- **Decision Factor 2:**
- **[Enter Crucial Need 4 Topic]:** [Enter Crucial Need 4 Description]
- **[Enter Crucial Need 5 Topic]:** [Enter Crucial Need 5 Description]
- **[Enter Crucial Need 6 Topic]:** [Enter Crucial Need 6 Description]
- **[Enter Crucial Need 7 Topic]:** [Enter Crucial Need 7 Description]
- **[Enter Crucial Need 8 Topic]:** [Enter Crucial Need 8 Description]
- **[Enter Crucial Need 9 Topic]:** [Enter Crucial Need 9 Description]
- **[Enter Crucial Need 10 Topic]:** [Enter Crucial Need 10 Description]
- **[Enter Crucial Need 11 Topic]:** [Enter Crucial Need 11 Description]
- **[Enter Crucial Need 12 Topic]:** [Enter Crucial Need 12 Description]
- **Decision Factor 3:**
- **[Enter Crucial Need 13 Topic]:** [Enter Crucial Need 13 Description]
- **[Enter Crucial Need 14 Topic]:** [Enter Crucial Need 14 Description]
- **[Enter Crucial Need 15 Topic]:** [Enter Crucial Need 15 Description]
- **Decision Factor 4:**
- **[Enter Crucial Need 16 Topic]:** [Enter Crucial Need 16 Description]
- **[Enter Crucial Need 17 Topic]:** [Enter Crucial Need 17 Description]
- **[Enter Crucial Need 18 Topic]:** [Enter Crucial Need 18 Description]

---

### Task
1. **Vendor Identification:** Based on the provided **NAIC** and the **Crucial Needs**, identify a shortlist of at least ten application software vendors that are a strong match.
2. **Ranking:** Rank the identified vendors from most viable to least viable. This ranking must be a qualitative assessment based on how well each vendor aligns with the specified **Crucial Needs**. Justify the ranking of the top vendor in its profile.
3. **Output Generation:** For each vendor on the shortlist, provide the following information formatted using Markdown syntax.

---

### Output Syntax

```markdown
# Vendor Shortlist

## 1. [Vendor Name]
- **Company Profile:** [Provide a concise summary of the company's history, mission, and focus.]
- **Key Leadership:** [List key leadership profiles and their roles, e.g., CEO: Jane Doe, CTO: John Smith.]
- **Operating Locations:** [List primary operating locations, e.g., Headquarters in San Francisco, CA; Offices in London, UK.]
- **Application Solution:**
- **Description:** [Provide a brief description of their core software solution.]
- **Delivery Options:** [List available delivery options, e.g., SaaS, Hosted, On-Premise.]
- **Customers:**
- **Current:** [List a few current or notable customers.]
- **Past:** [List a few past customers.]

---

## 2. [Vendor Name]
- [Repeat the same structure as above]

---

## 3. [Vendor Name]
- [Repeat the same structure as above]

---

## 4. [Vendor Name]
- [Repeat the same structure as above]

---

## 5. [Vendor Name]
- [Repeat the same structure as above]

---

## 6. [Vendor Name]
- [Repeat the same structure as above]

---

## 7. [Vendor Name]
- [Repeat the same structure as above]

---

## 8. [Vendor Name]
- [Repeat the same structure as above]

---

## 9. [Vendor Name]
- [Repeat the same structure as above]

---

## 10. [Vendor Name]
- [Repeat the same structure as above]

NOTES:

  1. Use Paste and Match Style when pasting a prompt into a browser. ​Using Paste only may insert the prompt as an attachment.
  2. The prompt was written using Markdown syntax.
How Markdown Works

Not all AI Large Language Models (LLMs) can accommodate markdown syntax for prompts, but it's an increasingly common and often preferred practice. The ability to process markdown varies depending on the model and how it was trained.

Many modern LLMs, particularly those developed by major companies like Google and OpenAI, are trained on vast amounts of text from the internet, a significant portion of which is in markdown format (e.g., GitHub documentation, blog posts, and forums). This training process gives the models an implicit understanding of markdown syntax, allowing them to:

  • Parse Structured Input: The model can interpret formatting like headings (#), lists (*, -, 1.), bold (**), and italics (*) to understand the hierarchical structure and intent of the prompt.

  • Generate Formatted Output: Because they've seen markdown in their training data, they can also generate responses using the same syntax to provide clearer, more readable output.

Why is Markdown Recommended?

Using markdown in prompts is considered a best practice in prompt engineering for several key reasons:

  • Clarity and Accuracy: It enables the model to distinguish between different parts of the prompt, including instructions, context, and examples. This structured input reduces ambiguity, leading to more accurate and relevant responses.

  • Human and Machine Readability: Markdown is a lightweight, human-readable format that is also easy for a machine to parse. This makes prompts simpler to write, read, and edit for both users and the AI.

  • Enhanced Performance: Some studies and anecdotal evidence suggest that using a structured format, such as markdown, can improve a model's performance on certain tasks, especially those requiring reasoning or multi-step instructions.

Lessons Learned

Lessons learned from over 200 vendor evaluation and selection projects include:

  • ●
    Most project teams spend 80% of their time identifying and documenting non-essential needs.
  • ●
    Too often, evaluating many vendors consumes valuable organizational resources like people, time, CAPEX, and OPEX, without providing clear benefits.
  • ●
    Reframe a vendor application software evaluation and selection process as acquiring a configurable business system. If there is a mindset of customization, such as believing your needs are unique, challenge that early, or check if there are any differentiating requirements that could give you a competitive edge that a vendor is unlikely to address. If you can't resolve that, do not consider a vendor solution.
  • ●
    Don't depend on the vendor for your implementation to succeed. Your organization must take ownership of success.
  • ●
    Keep it simple for the initial release. You can always make adjustments and add more configurations as needed based on how the software is used.

Learn more at Mastering the Vendor Software Selection Process.

Recap -- The Power and Opportunity of AI and Expert Playbooks

Is the one-minute vendor software evaluation and selection project possible?

By leveraging this prompt, you can guide a powerful LLM to perform complex vendor evaluation and shortlisting tasks, mimicking the intelligence of a dedicated platform without the initial costs of building one from scratch.

Leaders willing to take on a moderate level of risk and who cultivate a "make it work" culture can avoid the time and cost of a multi-month vendor evaluation and selection effort using this single prompt.

We don't recommend a one-prompt decision approach at this time without further validation. Nonetheless, this prompt, along with others used in our Vendor Application Software Evaluation and Selection Playbook, helps you accelerate your project, significantly reduce costs, and improve the quality of your vendor choices and ultimate decision.

The Playbook offers actions, templates (mostly filled with starter content), additional AI prompts with documentation and examples, and scoring models that help verify choices. By combining the advanced AI prompts with our expert Playbook, you can empower your internal team to make vendor recommendations without the need or cost of hiring expensive management consultants.

Reminder: Always review and verify the AI's output, as LLMs can sometimes produce errors or less accurate information than a dedicated, fine-tuned system with proprietary data feeds.

Note: The Playbook offers an example and documentation of this vendor shortlisting prompt within the context of the previously described vendor selection project.