2025 HR Lunch and Learn on AI

PROMPT 1

Convert the "Level 5" column to a table.

PROMPT 2

Show the pay scale for each level as a table

PROMPT 3

I have a Drafter I want to hire. What is the level and pay range?

PROMPT 4

Create a **clean, professional infographic** titled *"The Five Hourly Pay Scales"*.

**Design Requirements**
- Use a **neutral background** (light gray, beige, or soft white).
- Apply **modern, legible typography** (e.g., sans-serif like Helvetica, Lato, or Open Sans).
- Ensure the **layout is symmetrical and visually balanced**, with even spacing and alignment.
- Maintain a **minimalist aesthetic** with clear visual hierarchy and consistent style.

PROMPT

You are an expert data extractor. Extract the following information for each person in their biographies (delimited by ###):

- Name
- State of residence
- Age
- Years of education
- Highest degree earned
- Current degree being pursued (if any)
- Degree level of current program (undergraduate, graduate, other)
- Years of work experience
- Current company/employer
- Current job title
- Salary (exactly as written in text)
- Main career/subject interests (comma separated)

Print the results as a table with one row per person and one column per extracted field.

###
1. Emily has completed 17 years of education, holds a Bachelor’s in Engineering, and has 2 years of work experience. At 22 years old, she is pursuing her Master’s in Civil Engineering while working at Pacific Infrastructure Group, where she earns $72K/year. Growing up in California, she developed a passion for science and technology, which she now hopes to use to improve infrastructure in developing countries.

2. A Policy Associate at Global Outreach Network, Michael earns $55,000/year while finishing his graduate degree in Social Work. He is 24 years old, has 3 years of work experience, and completed 18 years of education with a Bachelor’s in Sociology and Political Science. Raised in Texas, he has long been passionate about helping those in need and dreams of one day joining the United Nations.

3. At 21 years old, Sarah works as a Junior HR Analyst at Metro Finance Corp with a salary of $48K/year. She has 16 years of education, a Bachelor’s degree in Business and Economics, and 1 year of work experience. Initially starting college as an undeclared major, she found her direction after two years and now aims to become a successful business leader.

4. David, now 23 years old, began his journey in photography during high school in Colorado. With 16 years of education and a Bachelor’s degree, he has 3 years of experience and works as a Lead Event Photographer at Rocky Mountain Events Photography. His role, which pays $65,000/year, allows him to specialize in documenting weddings, reunions, and corporate events.

5. Jessica’s early passion for creativity in Florida led her to a Bachelor’s degree in Fine Arts and a career as a freelance artist. She operates under Jessica Rivera Studios, bringing in $40K/year from commissioned work. At 25 years old, she has 4 years of professional experience and 16 years of education, along with extensive travel to study diverse art styles.

6. With 17 years of education and a Bachelor’s in Computer Science, Daniel has spent 2 years in the tech industry. He is 22 years old and works as a Junior Machine Learning Engineer at NextGen AI Systems, earning $85K/year. Raised in Washington, his strong background in mathematics and problem solving led him to focus his graduate studies on artificial intelligence and machine learning.

7. Olivia, a member of Southern Stages Touring Company, earns $32,000/year from performances and workshops. She has completed 14 years of education, holds an Associate’s degree, and has 1 year of work experience. At 20 years old, her passion for theater—nurtured in Georgia through school productions and scholarships—continues to grow.

8. Earning $58K/year, Matthew serves as a Conservation Project Coordinator at Green Horizons Initiative. He is 23 years old with 3 years of work experience, a Bachelor’s in Environmental Science, and 16 years of education. His interest in sustainability stems from a childhood spent exploring the outdoors in Oregon and learning about environmental issues.

9. Sophia, a Research Associate at MedTech Innovations, earns $90,000/year while pursuing her Master’s degree in Biomedical Engineering. At 24 years old, she has 18 years of education, a Bachelor’s degree, and 2 years of work experience. Growing up in Virginia, she cultivated her interest in medical technology through internships and research assistant roles.

10. At 22 years old, Andrew is a Fashion Designer at Chic Threads Apparel making $70K/year. He has 1 year of work experience, 16 years of education, and a Bachelor’s in Fashion Design. Originally from Illinois, his international travels to study trends and cultures have helped shape his innovative and stylish approach to design.

PROMPT 1

You are an expert HR analyst tasked with comparing multiple job descriptions (JDs) for the Cook I position at BYU. Begin with a concise checklist (3-7 bullets) of your planned analysis steps; keep items conceptual. Analyze and compare the JDs by:

- Identifying sections or elements that are identical or highly similar (provide the section title and a summary of the similarity).
- Highlighting unique differences (specify the JD, section, and a brief description of the difference).
- Listing any missing sections in one JD that are present in another (list by JD and section name; if all JDs are complete, leave this empty).

Summarize the key findings of your comparison in a short paragraph.

## Output Requirements

Return your analysis as a structured report. Your report should include clearly labeled sections:

- Identical Sections: List with section and summary.
- Unique Differences: List with JD, section, and difference.
- Missing Sections: List by JD and section name (leave blank if all JDs are complete).
- Summary: Short paragraph summarizing key takeaways.

Do not include any extra commentary or formatting beyond the specified structure. After preparing your output, quickly validate that all required sections are present and the text report matches the specification before returning the result.

PROMPT 1

PROMPT 1

Help me run some reports analyzing university salary survey data. Use the Excel file “AI Exploration - Job Eval.xlsx” (sheet “Survey Job Descriptions” with columns: Survey, Survey Job Code, Survey Job Title, Survey Median, Survey Average, # of Organizations Reporting Data, # of Incumbent Salaries Reported).

Please follow these steps:

"""

- Bar-chart: average Survey Median by Survey (BLS, CUPA, NACUFS, SLA, EduComp). Label each bar with the number of jobs (N) used.
- Scatter plot: Survey Average vs Survey Median for rows where both exist; add a simple trendline and a 45° reference line to show alignment.
- Bar-chart: count of job titles in four pay bands based on Survey Median: <$40k, $40–$55k, $55–$70k, >$70k. Label each bar with N.
- Side-by-side bar-charts: compare the mean Survey Median for two groups: Larger sample (≥10 orgs or ≥50 incumbents) vs Smaller/Unknown sample (otherwise). Include N for each group.
"""

Notes: Coerce pay fields to numeric; ignore rows missing Survey Median for steps that need it. Format currency as $#,### and keep titles/axes clear.

PROMPT 2

Heat map: rows = Survey, columns = Pay Band (the four bands above), cell value = count of job titles (N). Annotate each cell with N and show row/column totals. Add an “Unknown” column if a row is missing Survey Median.

PROMPT 3

Create an interactive prototype that allows me to select Survey represented in the spreadsheet. When I select a Survey, it shows a bar chart aggregated by Pay Band (based on Survey Median) for that Survey. Be sure to include total records per Survey.

PROMPT 1

Create an empty canvas

PROMPT 2 (Canvas Highlight)

Add a more clear, impactful opening

PROMPT 3 (Canvas Tooling)

Select: "Suggest Edits"

PROMPT 4

Create a new document. Turn this into an HTML email to use as as part an job opening awareness campaign. Simplify the email to generate excitement about the job. Add appropriate modern design elements for the email, but keep simple. Write the HTML.

PROMPT 5

Create an image I can drop on a LinkedIn post.

PROMPT 1

U: I love my car!
A: POSITIVE

U: I hated my last job
A: NEGATIVE

U: I went to the airport
A: NEUTRAL

U: I love spending time with my kids
A: POSITIVE

U: I love BYU sports
A:

PROMPT 2

Create a list of the items

User: dog, cat, fish
Assistant:
ANIMAL - DOG
ANIMAL - CAT
ANIMAL - FISH

User: apple, banana, orange
Assistant:
FRUIT - APPLE
FRUIT - BANANA
FRUIT - ORANGE

User: Santa Fe, Phoenix, Boston
Assistant:

PROMPT 3

AttitudeBot is a chatbot that thinks its funny and sometimes sarcastic

###

User: What is the capital of New Mexico?

AttitudeBot: Really? Did you attend primary school? The capital of New Mexico is Santa Fe, even though we might argue about the green chili capital.

###

User: What is Python?

AttitudeBot: Was Google too busy? Or maybe you lost your memory? Python is one of the most popular programming language in data science. But probably you don't even know what data science is

###

User: What GPT stands for?

AttitudeBot: So you are using me, but you don't even know who I am? GPT stands for generative pre-trained transformers, a model architecture introduced in 2017, while you were sleeping probably

###

User: Is AI going to take over my job?

AttitudeBot:

PROMPT 1

How many 'r' in the word "strawberry"?

PROMPT 2

blueberry

# Match a Job Description to Salary Survey Jobs (Description-Based)

**You are a compensation analyst.** Your task is to read a job description (JD), extract its true work content, and then match it to the most appropriate jobs across multiple salary surveys **based on duties/requirements**, not job title. You will rank matches, explain the rationale, and produce a short report.

---

## Inputs

1) **Job Description (JD)**

2) **Salary Survey Spreadsheet (tabular data)**

- File: `AI Exploration - Job Eval.xlsx`
- Use all relevant sheets/tabs within the workbook.
- Each row is a potential survey match with columns such as (examples; actual column names may differ):
- `survey_name`, `job_code`, `job_title`, `job_family/function`, `job_description`, `industry/sector`, `institution_type`, `size_band`, `FTE_scope`, `supervisory_level`, `education_req`, `experience_req`, `certifications/tools`, `work_context` (environment/physical), `FLSA/level`.
- If column names differ, infer equivalents by meaning (e.g., “Minimum Education” = `education_req`).

---

## What to Do

### 1) Parse & Normalize the JD

Extract and summarize:

- **Primary purpose / mission**
- **Core duties** (cluster similar duties; keep 6–12 bullets)
- **Scope** (setting/industry, unit size/complexity, menu/production scope, inventory or systems used, customer type)
- **Minimum requirements** (education, years of experience, certifications like ServSafe, tools/systems)
- **Supervision** (direct/indirect headcount, nature of oversight, training/mentoring)
- **Work context** (physical demands, environments such as hot line/freezer, hazards)

Create a keyword/synonym set from duties/requirements (e.g., institutional cooking, batch/volume production, standardized recipes, production sheets, allergen controls, cafeteria, HACCP, trayline, line cook, hot cook, cook II, ServSafe, food mgmt systems).

### 2) Candidate Retrieval from Surveys (don’t title-match only)

- Scan the **job_description** (and similar text columns) across all surveys.
- Use description-based retrieval with keyword/synonym expansion and phrase-weighting (e.g., “institutional cooking”, “cafeteria”, “volume production”, “standardized recipes”, “food safety/sanitation”, “train/mentor staff”).
- Prefer **sector/setting matches** (e.g., higher ed/food services) over generic hospitality when duties align.

### 3) Score Each Candidate (0–100)

Compute a weighted score per survey job:

- **Duties/Responsibilities match (40%)** – overlap with JD’s core duty clusters.
- **Setting/Scope (20%)** – institutional/education/cafeteria vs restaurant; volume/production complexity.
- **Qualifications (15%)** – education/years, required certs (e.g., ServSafe), tools/systems familiarity.
- **Supervisory scope (15%)** – direct/indirect headcount; training responsibilities.
- **Work context (5%)** – physical demands, hot/cold environments, hazards.
- **Other signals (5%)** – FLSA/level indicators, career level (I/II/III), union/non-union if present.

Also capture a brief **similarity rationale** quoting the phrases that matched.

### 4) Select and Explain the Top Matches

- Return the **Top 5** matches across all surveys, highest score first.
- For each, provide: **survey_name**, **job_code**, **job_title**, **Score (0–100)**, and a **2–4 sentence rationale**.
- If a strong tie exists, include both and explain the nuance (e.g., similar duties but slightly different supervisory scope).

### 5) Flag Mismatches & Leveling Cues

- Note any **gaps** (e.g., survey job requires a culinary degree but JD does not; survey role is “Cook III” while JD’s supervision suggests “Cook II”).
- Suggest whether the match should be **leveled up/down** within the survey family (I/II/III) and why.

-—

## Output Format (Concise)

**A. JD Snapshot (you extracted)**

- Purpose (1–2 sentences)
- Core duties (6–12 bullets)
- Minimum requirements (bullets)
- Supervision (bullets)
- Work context (bullets)

**B. Top Survey Matches (ranked)**

1. **[survey_name] [job_code] [job_title] — Score: XX**
*Why:* [2–4 sentence rationale referencing duties, setting, quals, supervision.]

2. **[...] — Score: XX**
*Why:* [...]

3. **[...] — Score: XX**
*Why:* [...]

4. **[...] — Score: XX**
*Why:* [...]

5. **[...] — Score: XX**
*Why:* [...]

**C. Notes & Leveling Guidance**
- Key differences/gaps
- Recommended level within each survey family (and why)
- Any data quality or mapping caveats

**D. Recommended Market Composite (optional)**
- If multiple strong matches from different surveys align, propose a composite market cut (e.g., average/median across the recommended matches), with a brief justification.

---

## Guardrails

- Never rely on job title alone—prioritize **work content**.
- Prefer survey rows whose **descriptions** explicitly mention institutional/cafeteria or volume production over restaurant/à la carte contexts.
- If the JD supervises or trains staff, avoid matching to purely individual-contributor cook roles unless supervision is incidental.
- If two survey jobs differ only by level, use **supervisory scope/complexity** to select the level.

---

## Matching Examples (for this kind of JD)

When the JD indicates institutional/higher-ed food service with batch cooking, standardized recipes, cafeteria/volume production, allergen controls, training/mentoring, and moderate physical demands, strong matches often include:

- **BLS 35-2012 — Cooks, Institution and Cafeteria**
- **CUPA 817020 — Line Cook**
- **Educomp 18436 — Cook**
- **NACUFS — NA-Cook II**
- **SLA 15061 — Hot Cook**

> Treat these as candidates to test via the scoring rules above—do **not** auto-select by title.