Memuat
Memuat
Want to go deeper?
Join one of our courses or ask us directly on WhatsApp.
Picked from the software, topic, and level of “Claude from Zero to Expert Class #65: Recruitment: Job Posts, Screening, and Interviews”.
Other ways we can help with Claude.
Learn with a mentor
Scheduled AI & Machine Learning courses with live guidance and a certificate.

Midjourney Course: Create Stunning AI Images from Text
★ 4.9

DALL-E Course: Creating Professional AI Images from Text
★ 4.9

Stable Diffusion Course: AI Art from Beginner to Professional
★ 4.9
Have it built for you
No time to learn Claude? Our team can do the project for you.

AI Image Creation with Stable Diffusion — Unlimited Custom Visual Production
★ 4.9

AI Image & Video Creation with Leonardo AI — All-in-One Visuals for Business
★ 4.9

AI Image Creation with Midjourney — Cinematic AI Art for Business
★ 4.9
Get notified about new Claude classes
At most one email a week. Unfollow anytime with one click.
The full narration of this video. The current sentence is highlighted while the video plays; click any sentence to jump there.
Hi, and welcome back to Claude from Zero to Expert. Sunset Coffee is getting busier, and Laras needs an extra pair of hands. In this episode we use Claude for recruitment: building a job profile, writing the job post, screening applicants fairly, and preparing the interview.
Laras once posted a job ad that said, staff wanted, hardworking and honest. Hundreds of people applied, but most of them didn't fit the job. The problem wasn't the applicants; it was the vague job post. So we start with a job profile: describe the job clearly first, then look for the person. Laras explains what she needs to Claude: a part-time barista, afternoon to evening, five days a week, whose tasks are making coffee, working the cashier, and replying to WhatsApp orders when Dimas is off. Claude builds a tidy job profile. Notice how it separates required skills from skills that can be trained. At the end, Claude asks whether barista experience is required. Laras's answer is very important: experience can be trained; what's required is being careful and friendly. This small decision opens the door to more applicants, such as fresh graduates who've never worked in a coffee shop.
From that profile, Laras asks for a job post for Instagram and WhatsApp. She deliberately says she'll fill in the pay range herself. The job post appears in the right panel. The title is clear, the hours come first, and there's a line that draws in new applicants: no experience needed, we'll train you from scratch. Look at the list below: tasks, requirements, what's offered, and how to apply. The pay is in square brackets. Pay and employment status are the owner's decisions and must follow employment regulations, not something Claude makes up. Laras also spots a maximum age of twenty-five, carried over from an old habit. She asks for it to be removed because it has nothing to do with the ability to do the job. That's our job as the final reader: making sure every requirement is truly needed for the work, not just a habit. Before publishing, check the job post with this list. First, the working hours and location are clearly stated, so applicants can judge for themselves whether it fits. Second, pay and employment status are set by the owner, in line with local regulations. If in doubt, ask your local labor office or an employment law expert. Third, every requirement must relate directly to the job. Avoid requirements like age, appearance, religion, or marital status. They shut out applicants who are perfectly capable, and they can cause legal problems. Also avoid uncertain promises, such as a guaranteed permanent position. An honest job post brings in employees who stay longer.
For fair screening, every applicant is scored with the same rubric. Claude built this rubric from the job profile. The first criterion is carefulness. A score of one means giving the wrong change in the simulation; a score of four means accurate and double-checking. Second, friendliness. From short answers without a smile, all the way to warm and offering help. Third, availability. This job needs afternoon shifts five days a week. Fourth, eagerness to learn, scored from the applicant's real story about learning something new. With a rubric, scoring is no longer based on first impressions or personal liking. Even two different interviewers will give similar scores. Applications start coming in. Laras copies the short stories of three applicants, but first removes their names, phone numbers, addresses, and photos. The applicants are simply called A, B, and C. She asks Claude to summarize them against the rubric, and makes it clear: don't make a decision, just notes and follow-up questions. The result is a short table of things to ask in the interview. Why shouldn't Claude decide? Because AI can carry biases from the data it learned from, and applicants deserve to be judged by an accountable person. Claude organizes the information; Laras does the judging.
To prepare the interview, Laras uses this prompt. Claude's role is an experienced interviewer for small businesses. The data is the job profile and rubric we already made, so the questions connect to the scoring criteria. The task is clear: one question for each criterion, one short work simulation, and an example of a good answer as a benchmark. The constraints matter just as much. Don't ask about age, religion, marital status, plans to have children, or other personal matters. Questions like these don't measure job ability, and they make applicants uncomfortable. For the interview, Claude prepares the same questions for every applicant, each linked to one rubric criterion. The first is about experience: tell me about a time you served someone who was upset. Second, a situation question that really happens at Sunset Coffee: orders arrive at the cashier and on WhatsApp at the same time. What do you do? Third, a short simulation. The total is one hundred twenty-one thousand rupiah, and the customer pays one hundred fifty thousand. How much change? The answer is twenty-nine thousand, and a careful applicant will double-check. Fourth, what's the last new thing you taught yourself? The answer shows eagerness to learn, which matters more than experience. Laras also asks Claude to write an example of a good answer for each question, as a benchmark for scoring. After screening the applications, Laras sends two kinds of emails drafted by Claude: an interview invitation for those who passed, and a thank-you note for those who didn't. The interview invitation states the day, time, length, and what will happen. The line you don't need to bring anything helps applicants feel at ease. Applicants who didn't pass still get a polite message. This small habit protects the business's reputation, because today's applicant can be tomorrow's customer.
Let's be clear about who does what. For documents, Claude helps write the profile, job post, and emails. Pay and employment status are still yours to decide, in line with regulations. For screening, Claude builds the rubric and anonymous summaries. Who passes is your decision, based on the rubric scores. For the employment contract, Claude can help list questions before you consult a legal expert or the labor office. The agreement itself must follow local regulations. Claude isn't a legal advisor. Employment rules can change and differ from place to place. The app screens in this video are simulations, and menu names may differ slightly because Claude is updated often. Once the new barista is hired, the first day starts with introductions: the team, the shop, and the basic rules. Then reading the SOPs we already made, such as the WhatsApp order SOP and the opening and closing SOP. This is where SOPs really pay off. Next, practice brewing and working the cashier, with Laras alongside. At the end of the day, ask what's still confusing. The answers can improve the SOPs, so the next employee learns even faster. For your business, start with the one position you need most urgently. Keep the profile, job post, rubric, and interview questions in one Project, so your next hire is just an update, not a fresh start.
We've built a job profile, written an honest job post, created a screening rubric, prepared a structured interview, and sent polite emails. With this episode, the Claude for Business session is complete. In the next episode we start a new session, Claude for Education and Content, beginning with building teaching materials and modules with Mr. Hendra. See you there!
Try these on your own after watching to lock in what you learned.
Type a question or keyword; we find the part of this episode that explains it and jump the video there.
Notes are saved with the current video time and are only visible to you.
Stuck on a step? Ask here; the instructor and other learners can answer.
No questions yet.

Cerdas Inovasi Digital Team
Software developers, BIM & 3D engineers, and AI practitioners
We build software, BIM models, games and AI automations for clients every day, and turn that hands-on work into step-by-step classes: every step is shown on screen and comes with a PDF guide you can keep.
See our clients →