The Application Engine: Applying Smart, Not Wide
WEEK 104 :: POST 1 :: GOOGLE GEMINI
Directions Given To The A.I. This Week+
Instructions Given to each A.I. — Please provide 3 prompt variations that share this objective:
Each A.I. also received two static attachments: the blog post template (structure) and the authoring instructions (voice and standards). The text below is the week-specific assignment as sent — reflowed for the web; wording unchanged.
I'd like you to write this week's Ketelsen.ai post. Two files are attached: the blog post template (the structure to follow) and the authoring instructions (context, voice, and standards). Please read both before you begin, then produce the complete post in a single response.
This week's theme: "The Application Engine — Applying Smart, Not Wide."
This is Week 5 of an eight-week series on running a job search with AI. The reader now has assets (Week 3) and a ranked company list (Week 4). This week they go live — and the trap waiting for them is spray-and-pray: hundreds of applications, a trickle of responses, and morale falling with every silent rejection.
There is a delicious irony at the center of this week, and the post should lean into it — plainly, and without gloating, because some readers will have already sent the two hundred generic letters and this post is their way out, not their scolding: AI-generated application slop is now something recruiters actively watch for. An AI prompt blog is exactly the place to say this plainly: the losing move is using AI to mass-produce two hundred generic cover letters; the winning move is using AI for tailoring intelligence — reading one posting deeply, matching it against the reader's real record, and producing an application that could not have been written for any other job. Same tool, opposite outcomes, and the difference is the prompting — which is the thesis of this whole series, and this is the week to argue it in full rather than just assert it. This is the series' thesis week. The post should say, in as many words, what the series contract promises readers: use AI like an analyst, not a ghostwriter — because employers restrict AI in their own hiring for real legal and compliance reasons, because recruiters discard what reads machine-made, and because an application the reader cannot stand behind in the interview was never an asset to begin with.
By this point the reader is also juggling artifacts from four earlier weeks — a spec sheet, a master résumé, a dossier — and keeping that context straight across sessions is itself becoming work. The strongest posts can acknowledge that honestly: structured, reusable prompting is what keeps a multi-week project coherent.
The deliverable the reader should walk away holding: a working application pipeline — a tracked set of live, tailored applications aimed at the top of the Week 4 ranking, with outreach running alongside.
THE SERIES CONTRACT — identical every week; it binds every prompt you design. This series' tagline is its editorial contract: "Use AI like an analyst, not a ghostwriter." It is written for a reader in a market unsettled by AI itself — some readers are searching precisely because AI eliminated their last role. Write with that reader at the table: no AI-efficiency cheerleading, no automation jokes, no promises that AI will "do it for you" anywhere a human hiring decision is involved. And hold one line in every prompt: the AI is the reader's private analyst, coach, and sparring partner — it structures, researches, rehearses, and questions. It does not ghostwrite. Anything a hiring human will read or hear — résumé lines, cover letters, outreach messages, interview answers, negotiation emails, resignation letters — must end in the reader's own words and be true. Prompts should drive toward drafts the reader rewrites and owns, and should say so explicitly. Employers increasingly restrict how AI may be used in their own hiring decisions for legal and compliance reasons, and recruiters increasingly recognize — and discard — material that reads machine-written. A prompt that makes a reader look AI-generated hurts them twice. Posts that ignore this contract should expect to lose the week. Two practical notes. First: a standing “About this series” notice covering these same points is added to every published post automatically at publication — acknowledge the frame in your own voice where your week's prompt calls for it, but do not write a formal disclaimer block of your own, and do not open every post with the same acknowledgment paragraph: outside the weeks whose prompts explicitly carry the series frame, this contract lives in your tone and your prompt design. Second, the framing is POSITIVE: used this way — analyst backstage, reader on the page — AI is an advantage no hiring human will ever hold against your reader. Write like that is true, because it is.
The three prompts should help a reader:
- Decode the job description. What the posting actually says versus what it means: the must-haves versus the wish list, the responsibilities hiding behind buzzwords, the signals about level and team — so the reader decides in minutes whether this posting deserves a tailored application at all.
- Build one tailored application package. A résumé variant cut from the Week 3 master against this specific posting, and a cover letter grounded in the reader's actual specifics — concrete, short, and impossible to mistake for a template. The reader supplies the posting and their real materials; nothing gets invented.
- Run the full pipeline system. The operating rhythm: an application tracker with stages and dates, referral-outreach messages that respect the person being asked, informational-interview requests that are not stealth applications, and a follow-up cadence that is persistent without being unhinged.
At the advanced tier, the strongest version of this week is the pipeline as an operating system — decode, tailor, send, track, follow up, learn — where the tracker feeds back into targeting (which kinds of postings respond?) and outreach runs as a parallel lane rather than an afterthought. That loop is worth reaching for.
A constraint for this week. Response rates, referral-conversion multipliers, and "applications per hire" figures circulate everywhere and verify almost nowhere. No prompt may ask the AI to state response or conversion statistics as fact, and no outreach prompt may have the AI fabricate a relationship, a mutual contact, or credentials the reader does not have. Honest outreach written from the reader's real situation is both more effective and the only kind this blog will teach.
Design the prompts so the AI does what it is genuinely good at: deep reading of one document, precise matching against another, drafting from supplied specifics, and imposing system on a chaotic process. The reader supplies the postings, the master assets, and the truth; the AI supplies the decode, the tailoring, and the discipline.
Series dependency chain, for the Metadata block: Week 5 consumes Week 3's master résumé and positioning narrative (variants are cut from them) and Week 4's ranked dossier (effort goes to the top of the list). Week 5 produces the live application pipeline — consumed by Week 6 (interviews come out of the pipeline) and Week 7 (multiple live processes become negotiation leverage).
Because readers may arrive at this post without having read the earlier weeks, the prompts should work for someone with a résumé and a posting in hand, while making clear the engine runs far better fed by a real Week 3 master and a Week 4 ranking.
Three difficulty tiers as always — Beginner, Intermediate, Advanced — each a genuinely different approach to the same problem, not the same prompt at three lengths.
On examples: this is a career topic that touches every industry. The template lists tech startup / retail / freelance as suggested industry examples — those are marked MAY, and adapting them is expected here. A reader tailoring one application to a dream posting, another asking a former colleague for a referral without making it weird, and a third rescuing a pipeline that is all silence are the right kinds of contexts. Choosing them over the suggested business examples is correct behaviour and will not be scored against you.
A note on supplied figures. Anything marked `[SUPPLIED — use as given]` above came from Ketelsen.ai's own research brief. Use it freely — you are not fabricating by repeating it, and you will not be marked down for leaving it uncited. Do not attach an invented source to it. (No supplied figures this week — response-rate and referral-conversion numbers especially. If the sentence needs a statistic to land, rewrite the sentence.)
## BEFORE YOU SUBMIT — STRUCTURAL CHECK
(This block is identical every week. It exists because these specific items are the ones posts drop, and a dropped structural item costs compliance points for something that takes one minute to add.)
Your post is parsed by a script before any human reads it. Confirm all seven:
1. ☐ Response begins with `PLATFORM: <your name>` and `WEEK: 5` 2. ☐ `## Lead` present once, at the very top, before Variation 1 3. ☐ `## In one line` present in all three variations 4. ☐ `## What this prompt gives you` present in all three variations 5. ☐ `## The Prompt` present in all three variations, with the prompt in double quotes beneath it 6. ☐ `## Introductory Hook` and `## Current Use` present in all three variations (three of each — not one) 7. ☐ Every template heading written as `##`, none bolded instead; prompt breakdown is running text split on ` : `, with no `###` headings inside it
A complete post has 57 `##` headings. If your count is well short, a section is missing or was bolded instead of hashed.
One extra check this week: confirm no prompt asks the AI to state response or conversion statistics as fact, and no outreach prompt invites the AI to invent a relationship, mutual contact, or credential the reader does not actually have. Also confirm every prompt that produces a cover letter, outreach message, or any other text a hiring human will read ends with the reader rewriting and owning the final words (the series contract's final-pass rule) — this is the week that produces exactly the material recruiters screen for AI slop.
About this series. AI is reshaping work — for some readers, it's part of why you're searching at all. We don't pretend otherwise. And the hiring world is wary of AI-written material: many employers restrict how AI may be used in their own hiring decisions, and recruiters increasingly recognize — and discard — machine-written applications. So this series teaches a different approach: use AI as your private research analyst, interview coach, and thinking partner, while every word an employer sees or hears from you stays genuinely, verifiably yours. AI behind the scenes. You on the page.
The losing move is using AI to mass-produce two hundred generic cover letters; the winning move is using AI for tailoring intelligence. In a market where employers restrict AI in their own hiring for real legal and compliance reasons, and AI-generated application slop is now something recruiters actively watch for, spraying and praying is a guaranteed path to silence. This week, we build an application engine that uses AI to read deeply and match precisely, ensuring you apply smart, not wide. You will find three prompts below: a Posting Decoder to separate real requirements from wish lists, a Tailored Application Builder to map your record to the role, and a Pipeline Manager to bring operational discipline to your outreach.
The Posting Decoder
Translate corporate buzzwords into actual job requirements before you apply.
Job descriptions are rarely written by the people doing the actual work. They are a negotiation between hiring managers, HR, and boilerplate templates, resulting in postings that ask for everything while saying very little. Before you invest an hour customizing your resume, you need to know what the job actually is. This prompt cuts through the noise, translating the posting into the unvarnished reality of the day-to-day work so you can decide if it deserves your attention.
Why this matters now
Right now, candidates are wasting massive amounts of time applying to "ghost jobs" or roles that are drastically misaligned with their seniority. By deploying an AI analyst to read between the lines, you can instantly disqualify bad fits and focus your limited energy strictly on roles where your specific background provides a genuine competitive advantage.
Act as an expert career analyst. I am pasting a job description below. Your task is to decode what the hiring manager is actually looking for.
> 1. Separate the true 'must-have' requirements from the 'nice-to-have' wish list.
> 2. Identify the likely hidden responsibilities hiding behind any corporate buzzwords.
> 3. Assess the role's actual seniority level and day-to-day reality based on the language used.
Do not write an application or cover letter. Provide an unvarnished analysis so I can decide if this posting deserves a tailored application.
Job Description:
\[PASTE JOB DESCRIPTION HERE\]
How the AI reads this prompt
Practical examples from different industries
A Senior Cybersecurity Incident Responder at a Fortune 100 company uses this prompt on a vague posting for a "Security Lead." The AI decodes the phrase "must wear many hats" and the list of twenty disjointed technical requirements, revealing that the role is actually a severely under-resourced solo position rather than a strategic leadership seat. This saves the candidate from applying to a toxic environment. An Endoscopy Technician at a specialty center feeds a posting for a "Clinical Floor Supervisor" into the prompt. The AI analysis highlights that despite the heavy emphasis on administrative duties in the text, the core "must-have" is actually deep patient-care protocol experience. The technician realizes they are highly qualified and proceeds with the application.
Creative use case ideas
- Analyzing a call for proposals for a competitive community art grant to understand what the selection committee truly values.
- Decoding a complex volunteer board position description to see if the time commitment aligns with your actual availability.
- Evaluating a freelance project brief to uncover hidden scope creep before drafting a proposal.
Adaptability tips
You can easily adapt this prompt by asking the AI to compare the decoded job description against a specific list of your dealbreakers (e.g., "Flag any language that suggests mandatory weekend shifts or lack of remote flexibility").
Pro tips
Ask the AI to generate three specific questions you should ask in the first interview to test its hypothesis about the hidden responsibilities.
Prerequisites
Have the full text of the job description ready, including the "About the Company" section, as that often holds cultural clues.
Required tools
Any modern LLM (Claude, ChatGPT, Gemini). A local text file to save your decoded insights is highly recommended.
Frequently asked questions
Can the AI really tell if a job is a bad fit just from the description?
The AI cannot know the hiring manager's mind, but it is excellent at pattern recognition. It has read millions of job descriptions and can accurately flag standard corporate euphemisms that usually indicate scope creep, under-resourcing, or misaligned seniority. What if the job description is only a few sentences long? If the posting is incredibly brief, the AI will likely flag that the role is poorly defined. You can then use the AI to generate a list of clarifying questions to ask a recruiter before you commit to the application process. Should I include the salary band in the paste? Yes. Including the salary data allows the AI to cross-reference the compensation against the listed responsibilities, which is one of the strongest indicators of the role's actual internal level.
Recommended follow-up prompts
"Based on your analysis of this job description, what are the three most critical objections a hiring manager might have about a candidate, and how can they be overcome?"
Tags and categories
Tags:
job search, analysis, decoding, time-saving Categories: Research & Preparation, Career Strategy
Citations
Ketelsen.ai Job Search Series Contract.
The Tailored Application Builder
Map your exact experience to the employer's specific problems without ghostwriting.
Once you have decided a job is worth your time, the trap is immediately reaching for an AI to write your cover letter. A recruiter can spot a machine-generated application instantly, and a letter you didn't write is not an asset. The true power of AI is acting as a precision matching engine—comparing the requirements of the role against the master inventory of your career, and highlighting exactly which of your achievements will resonate most. This prompt does the heavy analytical lifting so you can write a bespoke, compelling application in your own voice.
Why this matters now
As companies deploy AI to screen candidates, they are also discarding material that reads as machine-made. This prompt ensures you use AI like an analyst, not a ghostwriter. By mapping your genuine experiences to the company's stated needs, you create an application that is hyper-targeted, factually true, and impossible to mistake for a template.
Act as a ruthless and precise career coach. I am providing my master resume and a specific job description. Your job is to help me tailor my materials for this specific role, acting strictly as my analyst, not my ghostwriter.
> 1. Analyze the job description and identify the top 3-4 core business problems this role needs to solve.
> 2. Review my master resume and identify which of my specific experiences best prove I can solve those exact problems.
> 3. Suggest 4-5 tailored resume bullet points highlighting those specific experiences. Write these as drafts for me to refine.
> 4. Create a bulleted outline for a cover letter that connects my specific achievements to their core problems.
Do not write the cover letter itself. I will use your analysis to write the final materials in my own words.
Job Description:
\[PASTE JOB DESCRIPTION\]
My Master Resume:
\[PASTE RESUME\]
How the AI reads this prompt
Practical examples from different industries
An Identity Designer uses this prompt when applying to a senior brand architecture role. They paste in their ten-year master resume and the job description. The AI identifies that the company is struggling with brand consistency across acquisitions. It maps this to the designer's past project where they synchronized visual assets for a merged entity, outlining a cover letter focused entirely on post-merger identity integration. A project manager applying to a logistics firm uses this prompt. The AI spots that the posting emphasizes "supply chain resilience." It scans the manager's resume, pulls out an older, buried bullet point about rerouting shipments during a port strike, and elevates it to the top of the tailored resume suggestions, providing the perfect narrative hook for the cover letter.
Creative use case ideas
- Tailoring a pitch for a freelance consulting contract to precisely match the client's Request for Proposal (RFP).
- Drafting an outline for an internal promotion case, mapping your recent performance reviews to the requirements of the next pay grade.
- Organizing an application for an exclusive, specialized academic fellowship.
Adaptability tips
If you are a career switcher, add this line: "Specifically highlight the transferable skills from my previous industry that mitigate my lack of direct experience in this new field."
Pro tips
Run the prompt a second time, asking the AI: "Play devil's advocate. Based on my master resume, what is the weakest part of my application for this specific role, and how should I address it in the cover letter outline?"
Prerequisites
You must have your Week 3 master resume ready to paste, and you must commit to writing the final cover letter yourself.
Required tools
Claude desktop is excellent for this if you are using local files to store your master resume, keeping your data organized and secure.
Frequently asked questions
Why won't we just let the AI write the cover letter?
Because anything a hiring human will read must end in your own words and be true. An application you cannot stand behind in an interview was never an asset. Furthermore, AI prose is instantly recognizable to recruiters and is often immediately discarded. What if the AI hallucinates a skill I don't have? Because the prompt strictly constrains the AI to your supplied master resume, hallucinations are minimized. However, this is exactly why the prompt generates drafts and outlines. You are the final editor and the ultimate source of truth. Can I paste my LinkedIn profile instead of a master resume? You can, but a master resume is generally better. LinkedIn profiles are often public-facing and polished, whereas a true master resume (from Week 3\) contains raw, comprehensive details, metrics, and bullet points that give the AI more analytical material to work with.
Recommended follow-up prompts
"Review my finalized cover letter draft against the original job description. Does it sound distinctly human, and does it directly address the company's core problems?"
Tags and categories
Tags:
resume tailoring, cover letter, precise matching, authentic voice Categories: Application Materials, Career Strategy
Citations
Ketelsen.ai Job Search Series Contract.
The Pipeline Manager
Build and maintain the operational rhythm of a professional job search.
Applying is only the first step; the actual work of a job hunt happens in the follow-up. Managing multiple live applications, tracking dates, and conducting parallel outreach can quickly devolve into chaos. The strongest applicants run their search like a sales pipeline—they know exactly when to follow up, who they are talking to, and when to walk away. This advanced prompt uses AI to impose system and discipline on your process, ensuring no opportunity falls through the cracks and no outreach message comes across as desperate or fabricated.
Why this matters now
Keeping context straight across sessions is becoming work. By treating your job search as an operating system, you maintain control. This prompt helps you manage the administrative burden of follow-ups and networking, allowing you to focus your mental energy on interviews and negotiations. It ensures your outreach remains honest, rooted in your real situation, and highly effective.
Act as a strategic career operations manager. I am building a tracked application pipeline for my top target companies.
> 1. Based on the job description and my resume provided below, draft a 3-step follow-up cadence for this specific application (e.g., Day 1, Day 7, Day 14), including the specific actions I should take.
> 2. Draft a short, respectful request for an informational interview to send to a potential peer at this company. Do not invent any mutual connections or credentials. Keep it focused on learning about their team's current challenges.
> 3. Identify the key metrics I should track for this specific application in my pipeline system.
Job Description:
\[PASTE JOB DESCRIPTION\]
My Resume:
\[PASTE RESUME\]
How the AI reads this prompt
Practical examples from different industries
A senior executive transitioning out of a decade-long entrepreneurial stint uses this prompt to manage their re-entry into the corporate sector. The AI builds a 14-day follow-up cadence and drafts an informational interview request aimed at a VP of Strategy, focusing entirely on discussing market trends rather than asking for a job, ensuring the outreach is professional and grounded. A software engineer applying to five different startups uses this prompt to standardize their tracking. The AI recommends tracking "Time to First Response" and "Technical Screen Pass Rate," while drafting a polite Day-7 follow-up email that the engineer sends to the internal recruiters, keeping their pipeline moving without being unhinged.
Creative use case ideas
- Managing submissions and follow-ups for a series of freelance pitches or magazine article queries.
- Tracking applications to multiple graduate school programs, including managing recommendation letter requests.
- Organizing outreach to potential mentors in your local community, ensuring you follow up respectfully.
Adaptability tips
If you already have a referral for the role, modify the prompt: "In the follow-up cadence, include specific steps on how to keep my internal referral updated on my progress without overwhelming them."
Pro tips
Ask the AI to format the tracking metrics and follow-up cadence as a CSV or markdown table so you can instantly copy and paste it into your spreadsheet or workspace tool.
Prerequisites
You should have your target company list (from Week 4\) and a basic tracking system (like a spreadsheet or a Notion board) ready to populate.
Required tools
Any modern LLM. A spreadsheet tool (Excel, Google Sheets) or a dedicated database workspace.
Frequently asked questions
Why shouldn't I just ask for a job in the informational interview request?
Because informational interview requests that are actually stealth applications are transparent and often ignored. By keeping it focused on learning about their team's challenges, you lower the stakes and dramatically increase the likelihood of a response. How do I know who to send the informational interview request to? You will need to do your own research on LinkedIn to find a peer or a manager in the target department. The AI provides the framework for the message, but you must supply the human connection and the truth. What do I do if I get no response after the 3-step cadence? The pipeline manager enforces discipline, which includes knowing when to walk away. If you execute the 3-step follow-up and hear nothing, you log it as a closed opportunity in your tracker and reallocate that energy to the next target on your list.
Recommended follow-up prompts
"Generate a weekly review checklist I can use every Friday to evaluate the health of my application pipeline and decide where to focus my outreach next week."
Tags and categories
Tags:
pipeline, tracking, outreach, networking, operations Categories: Career Strategy, Workflow Automation
Citations
Ketelsen.ai Job Search Series Contract.
Which of the three should you use?
The Beginner variation is a defensive tool; it protects your time by decoding the reality of a job posting before you commit to applying. It is fast, requires zero setup, and instantly separates real opportunities from toxic or misaligned roles. It acts as the gatekeeper for your pipeline. The Intermediate variation is the core engine of the application process. It takes the insights from the decoder and your master resume, acting as a precision matching tool. It does the heavy analytical lifting required to tailor your materials without crossing the line into ghostwriting, ensuring your application remains authentic and avoids the AI-slop filters recruiters are actively monitoring. The Advanced variation scales your effort. Once you are applying and tailoring smartly, the Pipeline Manager provides the operational discipline required to run a multi-threaded job search. It structures your follow-ups, ensures your networking outreach is honest and respectful, and turns a chaotic process into a manageable, tracked system. Together, they form a complete, intelligent application engine.
TAGS:
