📚 Build AI Assessments that Deliver Personalized Insights

Reading Time: 5 minutes

Hello AI Enthusiast,

Today, we're pulling back the curtain on how we built our AI Academy Skills Assessment Tool. We'll show you how we combined no-code tools and AI to create a system that analyzes a person's AI capabilities and provides personalized learning recommendations.

The Problem

Understanding where you stand in your AI journey can be challenging. Many professionals struggle to accurately assess their own capabilities and end up choosing educational paths that don't align with their actual needs. This leads to:

• Wasted time on courses that are either too basic or too advanced

• Frustration when skills learned don't translate to practical workplace applications

• Missed opportunities to leverage AI effectively in daily work

We wanted a solution that could scientifically evaluate both AI skills and usage habits, then recommend the right learning path based on our Skills-Habits Matrix (which positions users as Novices, Explorers, Pros, or Champions).

How We Did It

Here's how we built our workflow using entirely no-code solutions and AI:

1. Design assessment questions

We developed 8 questions based on our experience training over 12,000 individuals. Each question targets specific aspects of:

• Self-assessment (how crucial is AI to your weekly tasks)

• Usage patterns (specific AI applications in their workflow)

• Job context (responsibilities and performance metrics)

These questions serve as indicators for positioning users on both our Skills Pyramid and Habits Pyramid.

2. Set up the data collection form with Tally

We used Tally to create a clean, user-friendly form that collects assessment responses. Tally made it easy to design a professional-looking form to collect structured data through a frictionless user experience

3. Build the automation workflow with Make

Make is the platform we used to build our assessment tool. Our workflow follows these steps:

1. Collect form answers from the Tally submission

2. Transform some answer fields to make them easier to process

3. Evaluate answers to determine skill and habit levels

4. Put together answers and levels to suggest the most appropriate course

The workflow then proceeds through these next steps:

1. Add the data to a Google spreadsheet for record-keeping 5b. Data validation check that alerts us on Slack if anything is formatted incorrectly

2. Add user information to our email system for follow-up

The workflow concludes with these final steps:

1. Generate a personalized presentation based on assessment results and course recommendation

2. Create a shareable link for the presentation

3. Send the user an email with their assessment results

4. Set up AI-powered evaluation with the OpenAI API

The heart of our assessment tool is AI evaluation of user responses. We use two separate prompts for different parts of the process and to do that we use OpenAI's o3-mini model for its reasoning capabilities, speed, and cost-effectiveness.

The first prompt evaluates skills and habits by:

1. Analyzing the user's survey responses

2. Classifying their skill level (Knowledge, Understanding, Application, or Mastery)

3. Determining their habit level (Awareness, Occasional Use, Integration, or Advocacy)

4. Generating a personalized assessment report highlighting strengths and areas for improvement

5. Looking for contradictions between self-assessment and actual capabilities

For example, if someone claims high confidence but demonstrates limited usage patterns, the AI notes this discrepancy and provides more accurate positioning.

The second prompt provides course recommendations:

1. Takes the skill and habit levels from the first evaluation

2. Considers the user's job responsibilities and challenges

3. Recommends one of two learning paths: our comprehensive "AI Academy Membership" or our foundational "Practical Introduction to ChatGPT"

4. Provides actionable advice and next steps tailored to their specific situation

This dual-prompt approach ensures we deliver both an accurate assessment and relevant recommendations.

5. Deliver personalized results

The final steps of our workflow create a professional presentation with the user's position on the Skills and Habits pyramids, their overall profile (Novice, Explorer, Pro, or Champion), a personalized feedback and growth opportunities and finally custom learning recommendation.

This presentation is automatically emailed to the user, providing them with immediate, actionable insights.

Want to get even more practical? Explore hands-on AI learning with AI Academy:

• AI Academy Membership: Get 12 months of access to all our cohort-based programs, live webinars, on-demand courses, and tutorials.

• Generative AI Project Bootcamp: Accelerate processes and solve business problems by mastering prompts and building AI prototypes, without coding.

• Corporate Training: Equip your team with the skills they need to unlock the potential of AI in your business.

• Practical Introduction to ChatGPT: A free course on using ChatGPT confidently, understanding its workings, and exploring its potential.

We'll be back with more AI tips soon!