Company Intelligence: Researching Employers Like a Pro
WEEK 103 :: 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: "Company Intelligence — Researching Employers Like a Pro."
This is Week 4 of an eight-week series on running a job search with AI, and it is the series' information-asymmetry showcase — the job-search version of the car series' dealer-research week. An employer entering an interview knows the reader's history, salary expectations, and references. The reader knows the employer's careers-page marketing. This week closes that gap: building a ranked target-company list, and screening out bad employers before investing application effort in them.
The territory is rich because the failure modes are real and documented: job listings that stay up with no one hiring behind them (the "ghost listing" — a direct parallel to the ghost cars of the last series), suspiciously coordinated bursts of five-star employer reviews, serial layoff patterns, and the culture warning signs that only show up when you know to look — leadership churn, vague answers about why the role is open, review complaints that cluster on the same theme across years.
The deliverable the reader should walk away holding: a ranked target-company dossier — this series' "Dealer Intelligence Matrix" moment — with each company scored against the Week 2 spec and screened for red flags.
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:
- Build the company snapshot brief. A repeatable research checklist for one company: what it does, how it makes money, how it is doing, what current and former employees say — organized as questions with named places to look (filings and annual reports for public companies, funding announcements for startups, employer-review sites read with dates in mind), so the reader assembles the evidence.
- Run the red-flag audit. A structured pass over one company for warning signs: layoff history, leadership turnover, funding runway for startups, and review forensics that weight recency and pattern over any single angry post — each flag framed as something to verify, with the audit distinguishing "confirmed," "concerning," and "rumor."
- Build the full dossier matrix. The multi-company system: a research workflow the reader runs per company, feeding a matrix that scores each against the Week 2 must-haves and deal-breakers plus the red-flag audit, producing a ranked list of where to actually spend application effort — and a screened-out list with reasons.
At the advanced tier, the strongest version of this week is the dossier as a living system — a research routine organized around the areas that matter (financial health, review patterns, listing legitimacy, pay transparency, leadership signals, growth trajectory, interview-process reputation, and which companies hire by referral before ever posting), feeding one composite-scored matrix. That architecture is worth reaching for; it is the week readers will bookmark.
The constraint that defines this week. AI models cannot see live listings, current filings, this week's layoffs, or yesterday's reviews — and several posts in the last series were marked down for letting the AI assert facts it could not know. No prompt may ask the AI to state a specific company's current facts — layoffs, funding, leadership changes, whether a posting is real — as settled fact. The prompts should have the AI build the research structure: the questions, the named source types, the scoring framework, the red-flag taxonomy. The reader gathers the evidence; the AI organizes it and helps score it. A prompt that has the AI "investigate" a named company and report findings should expect to be marked down on Content Accuracy — the honest version has the reader paste in what they found.
Series dependency chain, for the Metadata block: Week 4 consumes Week 2's target-role spec sheet (companies are scored against its must-haves and deal-breakers). Week 4 produces the ranked target-company dossier — consumed by Week 5 (applications go to the top of the ranking), Week 6 (interview prep draws on the dossier), and Week 7 (the negotiation leans on what the reader knows about the company's position).
Because readers may arrive at this post without having read the earlier weeks, the prompts should work for someone with a shortlist scribbled on a napkin, while making clear the matrix bites harder when it scores against a real Week 2 spec.
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 vetting a fast-growing startup's runway, another weighing a big company's layoff pattern against its brand, and a third trying to tell a real posting from a ghost 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 — and given the constraint above, this is the worst possible week to invent one. Ghost-listing prevalence numbers circulate widely and vary wildly; write around them.)
## 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: 4` 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 report a named company's current facts — layoffs, funding, leadership, listing legitimacy — as findings. The AI builds the research structure and scores evidence the reader gathered; the reader does the investigating.
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.
Information asymmetry is a defining reality of the job hunt: employers enter the interview knowing your history, your references, and your salary expectations, while you are left guessing based on their curated careers page. This week solves that imbalance by giving you the tools to build a ranked target-company dossier and screen out bad employers before you waste time applying. By mastering three specific prompts—the Company Snapshot Brief, the Red-Flag Audit, and the Dossier Matrix System—you will transform your AI from a passive writing tool into a rigorous private research analyst. Take the next 16 minutes to learn how to vet companies aggressively, ensuring you only invest your effort where the opportunity is real.
The Company Snapshot Brief
Build a repeatable research checklist to uncover a company's true reality.
You would never make a major financial investment without looking under the hood, and you shouldn't accept an interview without knowing how a company actually operates. Most job seekers rely entirely on a company's own marketing, missing critical context about financial health, revenue models, and employee satisfaction. This beginner variation flips the script, giving you a structured way to ask the right questions and find the real answers before you ever submit a resume.
Why this matters now
Ghost listings and suspiciously timed five-star reviews are everywhere right now. This prompt matters today because it forces you to look past the surface and gather hard facts—like funding announcements and actual employee sentiment—protecting you from investing hours in a company that isn't actually hiring or isn't worth your time.
Act as a professional career research analyst. My goal is to build a company snapshot brief for an employer I am considering applying to. I will provide the raw data and findings I gather from their website, recent news, and employee review sites. Do not invent any facts about the company. Instead, provide me with a structured questionnaire containing exactly 10 critical questions I need to answer to understand their revenue model, financial health, and employee satisfaction trends. Tell me exactly where I should look to find this information. Once I paste my findings back to you, organize them into a clean, one-page snapshot.
How the AI reads this prompt
Practical examples from different industries
Healthcare Specialty Centers: A professional seeking an Endoscopy Technician role uses this prompt to research a specialty center. By answering the AI's structural questions and gathering the data themselves, they uncover that the center recently lost accreditation for a key procedure, allowing them to dodge an unstable workplace. Startup Marketing: A freelance consultant uses the checklist to evaluate a tech startup. They follow the AI's guide to check funding runways and press releases, discovering the company hasn't raised capital in three years—signalling high risk for independent contractors.
Creative use case ideas
- Evaluating a non-profit organization's financials before volunteering for their board of directors.
- Researching a university department's turnover rate before committing to a master's program.
- Vetting a local general contractor's history and sub-contractor reviews before hiring them for a major home renovation.
Adaptability tips
Adjust the prompt to focus specifically on remote-work culture or environmental, social, and governance (ESG) commitments if those are your primary concerns, asking the AI to tailor its 10 questions to those topics.
Pro tips
Ask the AI to weight certain questions heavier than others (e.g., prioritize recent leadership turnover over 5-year revenue growth) depending on your specific career stage and risk tolerance.
Prerequisites
Have a target company in mind and a blank document ready to save your findings.
Required tools
Claude Desktop (leveraging local files to securely store your running research documents), or any standard LLM.
Frequently asked questions
What if I can't find the answers to the AI's questions? If a company's financial or cultural data is entirely hidden, that itself is a valuable signal. Private companies are inherently opaque, but a complete lack of employee reviews or news often indicates a very early-stage startup or strict non-disclosure practices that you should weigh carefully. Can I use this for multiple companies at once? It is best to use this beginner prompt for one company at a time to ensure the snapshot remains focused and accurate. For multi-company comparisons, refer to the Advanced prompt below. Why can't the AI just search the web for me? AI models often rely on outdated training data and cannot reliably verify if a job posting is a ghost listing or if a recent layoff occurred. You must be the investigator who gathers the facts; the AI is simply your analyst.
Recommended follow-up prompts
"Target Role Spec Sheet Generator" (Week 2), "Interview Persona Sparring Partner".
Tags and categories
Tags: research, checklist, vetting, snapshot. Categories: Job Search, Foundation.
Citations
NOT APPLICABLE
The Red-Flag Audit
Scan employer reviews and leadership patterns for hidden warning signs.
It is incredibly easy to be swayed by a cluster of one-star reviews on an employer site, or conversely, a suspicious burst of five-star praise. The challenge isn't finding reviews; it's conducting proper forensics to separate a single disgruntled employee from a systemic, toxic culture. This intermediate prompt gives you an auditor's lens to evaluate company warning signs rationally.
Why this matters now
Serial layoff patterns and leadership churn are unfortunately common in today's job market. This prompt is critical because it forces you to look at the timeline and context of negative signals, protecting yourself from jumping onto a sinking ship or accepting a role where the previous three people quit in frustration.
Act as a forensic HR analyst. I am evaluating a potential employer and have gathered recent employee reviews, news about leadership changes, and layoff history. I will paste this raw text below. Review the information and conduct a red-flag audit. Categorize the warning signs into 'Confirmed Risks' (supported by multiple data points or official news), 'Concerning Patterns' (clustered complaints on the same theme), and 'Rumors' (isolated complaints). Provide a brief explanation for why each item was categorized this way. Do not invent any data; only analyze the text I provide.
How the AI reads this prompt
Practical examples from different industries
Cybersecurity Firm: A senior incident responder uses this audit to evaluate a tech firm. By pasting in external reviews and press releases, the AI highlights a "Concerning Pattern" of mid-level management turnover right after a recent acquisition, prompting the candidate to ask targeted questions during the interview. Retail Management: A retail manager pastes in three years of employee reviews. The AI successfully isolates a suspicious, coordinated burst of five-star reviews submitted in a single week, classifying them as a manipulated pattern and saving the candidate from a potentially toxic workplace.
Creative use case ideas
- Evaluating a prospective landlord by auditing tenant reviews and public property records.
- Auditing a software vendor's customer reviews before committing to a multi-year enterprise contract.
- Assessing a community theater group's reputation before dedicating a six-month season to their production.
Adaptability tips
You can easily adjust the taxonomy if you have specific deal-breakers, replacing "Rumors" with a category specifically tailored to "Remote Work Policy Reversals" or "Pay Transparency."
Pro tips
Gather reviews from multiple different platforms (not just one site) and always include the dates of the reviews when you paste the text. The AI can then spot chronological correlations, like a severe dip in morale exactly when a new CEO took over.
Prerequisites
A collection of copied-and-pasted reviews, news snippets, and exact dates regarding the target company.
Required tools
Claude Desktop (ideal for locally pasting and auditing large text files without exposing sensitive workflows to the web).
Frequently asked questions
What if a company has no reviews at all? A lack of reviews is common for stealth startups or very small businesses. In this case, the red flag isn't in the reviews, but in the lack of digital footprint, which you must weigh against your own personal risk tolerance. Will the AI know if a review is definitively fake? The AI cannot definitively prove a review is fake, but it is excellent at spotting linguistic patterns or suspicious timing—like twenty 5-star reviews all praising the "dynamic culture" on the exact same Tuesday. How much text can I paste? Most modern AI models can handle dozens of pages of text at once. The more chronological context you provide, the better the forensic analysis will be.
Recommended follow-up prompts
"The Dossier Matrix System" (this week's Advanced prompt).
Tags and categories
Tags: audit, red-flags, forensics, culture. Categories: Job Search, Analysis.
Citations
NOT APPLICABLE
The Dossier Matrix System
Build a composite scoring system to rank your job opportunities.
When you are looking at five different companies, scattered notes and gut feelings are not enough. You need a centralized system that objectively weighs a startup's growth trajectory against a legacy company's stability. This advanced prompt creates a living research routine, feeding a matrix that scores every potential employer against your personal must-haves and the red flags you've uncovered, producing a ranked list of where to actually spend your application effort.
Why this matters now
In a market unsettled by ghost listings and rapid shifts, your application effort is a precious resource. This prompt matters because it forces a strict go/no-go verdict based on data, ensuring you only spend your time applying to the companies that survive your rigorous screening.
Act as my private job-search analyst. I am building a ranked target-company dossier. First, review my 'Week 2 Target-Role Spec Sheet' (which I will paste below) to understand my must-haves and deal-breakers. Then, I will provide my research findings and red-flag audits for three different companies. Your task is to build a Dossier Matrix: a composite-scored table that evaluates each company on Financial Health, Leadership Signals, Pay Transparency, and Alignment with my Spec Sheet. Give each company a score out of 100, rank them, and provide a clear 'Go / No-Go' recommendation for where I should invest my application effort. Do not invent any company facts; rely strictly on the data I provide.
How the AI reads this prompt
Practical examples from different industries
Enterprise B2B Sales: An account executive feeds the AI data on three enterprise software companies. The matrix scores one company highly on compensation but flags a severe "No-Go" based on a recent red-flag audit showing massive sales leadership churn, redirecting the candidate's focus. Graphic Design & Identity: An experienced identity designer uses the matrix to compare an in-house corporate role with a boutique agency. The AI scores the in-house role higher on the "stability" must-have from their Week 2 spec, resulting in a clear "Go" verdict for the corporate position.
Creative use case ideas
- Ranking potential cities for relocation based on cost of living, healthcare access, and personal lifestyle must-haves.
- Evaluating different freelance client proposals against your desired hourly rate, project scope, and payment terms.
- Comparing different hospital systems when deciding where to request workplace coaching and support guidelines.
Adaptability tips
You can add specific custom columns to the matrix, such as "Commute Time" or "Interview Process Reputation", to make the scoring even more granular and tailored to your situation.
Pro tips
Maintain this matrix as a living system inside local files on your computer. Update the AI with new information after every interview round, allowing the scores to dynamically adjust as you learn more.
Prerequisites
Completion of the "Target-Role Spec Sheet" from Week 2, and completed research for at least two target companies.
Required tools
Claude Desktop (leveraging local files to maintain your Dossier Matrix as a living system without relying on cloud-based forum plugins).
Frequently asked questions
How does the AI calculate the score out of 100? The AI uses a weighted average based on the criteria you define. By default, it will weigh deal-breakers heavily, but you can explicitly instruct it to prioritize certain categories (like Pay Transparency) over others. What if I disagree with the AI's 'No-Go' verdict? The AI is your analyst, not your boss. If you disagree, use that friction to interrogate why. Perhaps your Week 2 spec sheet needs updating, or perhaps your gut instinct is overriding the data. Can the AI track companies that hire by referral before ever posting? The AI cannot browse private networks, but you can add a "Referral Potential" column to your matrix. If you find out a company heavily relies on referrals, input that fact yourself, and the AI will appropriately boost its score.
Recommended follow-up prompts
"Targeted Application Strategy" (Week 5).
Tags and categories
Tags: matrix, scoring, dossier, ranking. Categories: Job Search, Strategy.
Citations
NOT APPLICABLE
Which of the three should you use?
These three prompts work together to scale your research effort. The Beginner variation (The Company Snapshot Brief) is your starting point—a fundamental checklist to ensure you don't miss obvious warning signs when looking at a single company. It is best used early in the process when a recruiter reaches out and you need a quick temperature check. The Intermediate variation (The Red-Flag Audit) digs deeper into culture and stability, providing forensic analysis on reviews and news. It is essential when a company passes the initial snapshot but has a complicated public reputation or a history of leadership churn. The Advanced variation (The Dossier Matrix System) is the culmination of your research, built for the job seeker juggling multiple serious opportunities. Instead of evaluating companies in a vacuum, it ranks them against your explicit Week 2 standards. You should choose the level that matches where you are in the pipeline: use Beginner to screen, Intermediate to investigate, and Advanced to decide.
TAGS:
