AI Fields use the prompt you write to evaluate each candidate’s CV, application answers, and job description, then return a result.
The most effective prompts say exactly what you’re looking for, define what counts and what doesn’t, and ask for one thing at a time.
Yes/No Fields
Prompting Practices
To write a good Yes/No prompt:
say exactly what you’re looking for
specify the context (e.g. professional vs. academic)
make it something that can clearly be answered Yes or No
Avoid:
single words with no context
vague terms like "strong", "good", "solid"
multiple questions in one prompt (e.g. "Has management experience and knows React?")
✅ Tip
Read your prompt as if you were the AI. If you only had this prompt and the candidate’s CV, application answers, and job description, how would you interpret it?
Look for anything you could misread, then make it more specific.
Prompting Comparison
Quality | Prompt | Explanation |
Weak | JavaScript | It’s unclear what counts. The AI could accept any mention on the CV, backend or frontend work, or a single weekend project. |
Better | The candidate has professional experience using JavaScript. | It’s clearer, but it doesn’t define what "professional" means. |
Great | The candidate has professional experience using JavaScript. This means they have used it in a paid role. For example, a university project would not count, but an internship where they used JavaScript would count. | It defines what counts (paid work, including internships) and what doesn’t (university and personal projects), so it can be answered Yes or No for every candidate. |
Prompt Examples
Use these example prompts as a starting point for your own prompts:
Requirement | Example prompt |
People management | The candidate has experience managing people. This means they have had direct reports in a paid role (for example, line management of at least one person), not just mentoring or coaching informally. |
B2B sales | The candidate has experience selling B2B SaaS products. This means they have sold software-as-a-service to other businesses as part of their core role, not just used SaaS tools. |
Startup experience | The candidate has experience working in a startup environment. This means they have worked for a company with fewer than 100 employees, not just collaborated with startups as clients. |
SQL | The candidate has experience writing production SQL queries. This means they have used SQL regularly in a job to query live or reporting databases, not just completed a single course or one-off project. |
Integer (Number) Fields
Integer fields return a whole number for each candidate. You can use them to measure things like:
years of experience
number of previous roles
length of tenure
Prompting Practices
To write a good Integer prompt:
ask for a single number
state the unit, such as years
tell the AI what to return if the information isn’t available
Prompt Examples
Use these example prompts as a starting point for your own prompts:
Measure | Example prompt |
Years of experience | How many years of experience does this candidate have in software development? Return only the number of years. |
Management experience | How many direct reports has this candidate managed? If not mentioned, return 0. |
Tenure | What is the longest tenure (in years) the candidate has held at a single company? |
Certifications | How many relevant professional certifications does this candidate hold? If not mentioned, return 0. |