Week 4 Deep Research Prompt: Should You Really Buy a Car Right Now?

Written By Richard Ketelsen

  • Topic: Should I Buy a Car Right Now?

    Week: Week 1

    Rubric version: v1.0

    Platforms compared: ChatGPT, Gemini, Claude

    Winner: Claude (98.0 / 100)

    Runner-up: ChatGPT (85.0 / 100)

    Third place: Gemini (62.0 / 100)

    Margin of victory: 13.0 points

    Tags: ai-comparison, prompt-engineering, chatgpt-vs-claude-vs-gemini, weekly-showdown, ai-quality, rubric, week-1, car-buying, should-i-buy-a-car

    Categories: AI Comparison, Prompt Engineering

    Estimated reading time: 12 minutes

    SEO title: Week 1 AI Showdown: Claude vs. ChatGPT vs. Gemini — Who Wrote the Best Car-Buying Prompt Post?

    SEO description: We gave ChatGPT, Claude, and Gemini the same car-buying prompt topic and scored them across 7 dimensions. See which AI wrote the most useful, detailed, and actionable blog post.

Week 1 Deep Research Prompt: Should You Really Buy a Car Right Now?

A $52,600+ decision deserves more than a casual conversation with an AI. It deserves Deep Research — a mode available in ChatGPT, Claude, and Gemini that lets AI search across hundreds of sources, synthesize findings, and produce a professional research report instead of a quick answer. This post contains the complete Deep Research prompt that will guide your AI platform through an exhaustive investigation of your personal car-buying readiness, market timing, affordability analysis, and the opportunity cost of buying now versus waiting. You'll get a 15–30 page research report (depending on platform) instead of a few paragraphs.

Why Deep Research?

Deep Research mode is fundamentally different from a regular chat. Instead of answering from training data, the AI actively searches current sources, reads across multiple perspectives, cross-references data, and builds a synthesized argument supported by citations. For a car-buying decision, this matters because market conditions change week-to-week: interest rates shift, inventory levels fluctuate, tariff impacts emerge, incentive structures evolve, and depreciation patterns adjust. A Deep Research report on "Should I Buy a Car Right Now?" will pull recent data on average MSRPs, current financing rates by credit tier, real-time depreciation benchmarks, and emerging market trends you can't predict from 2024 knowledge. The result is a decision framework grounded in current evidence, not outdated assumptions.

Deep Research also forces structured thinking. Instead of giving you opinions, the AI breaks the question into 6–8 independent research threads, investigates each one thoroughly, and synthesizes the findings into an executive summary and actionable decision framework. You're not just getting an answer; you're getting the investigation itself — which means you can see exactly what evidence shaped the conclusion and judge the quality of that evidence yourself.

The Deep Research Prompt

RESEARCH BRIEF: Should I Buy a Car Right Now? A 2026 Market Timing & Affordability Analysis RESEARCH CONTEXT I'm considering buying a car in 2026 but uncertain about market timing and personal financial readiness. I need you to conduct a comprehensive research investigation across current market conditions, affordability models, depreciation trends, and personal financial frameworks to produce a professional research report that answers: Is NOW a good time for ME to buy a car, or would waiting change the outcome? Your research should synthesize evidence-based findings across multiple data sources and produce a report structure that separates findings from my personal decision process. RESEARCH THREADS TO INVESTIGATE Conduct independent research on each of the following threads. For each thread, search for current data, cite specific sources, and include numerical evidence where available. THREAD 1: Market Timing & Macroeconomic Conditions Research the current (2026) car market across these dimensions: - MSRP trends: What are average new-vehicle MSRPs in 2026? How has pricing evolved since 2025? Are MSRPs still elevated or normalizing? - Inventory levels: Are new vehicles in short supply, balanced, or over-supplied? How does inventory vary by vehicle type (sedan, SUV, truck, EV)? - Interest rates & financing landscape: What are current APR ranges by credit tier (prime, near-prime, subprime, deep subprime)? How have Fed rates influenced consumer lending in 2026? - Tariff impacts: Are tariffs affecting pricing? Are 2025 tariff fears (which drove acceleration buying) still relevant, or have prices already adjusted? - Incentive landscape: What manufacturer incentives are currently available? Are rebates, cashback, or 0% financing offers more or less generous than 2025? - Regional variation: How do market conditions vary geographically? (Urban vs. rural, coastal vs. interior, high cost-of-living vs. affordable markets) THREAD 2: Depreciation & Value Retention Research depreciation patterns and value retention: - New vehicle depreciation: What percentage of value do new vehicles lose in years 1, 3, and 5? How does depreciation vary by vehicle type (sedan vs. truck vs. EV)? - Used vehicle market: What are current prices for 3–5-year-old vehicles in the same class? How quickly is the used market absorbing new inventory? - EV depreciation: How does EV depreciation compare to traditional vehicles? What battery replacement costs should buyers anticipate? - Certified pre-owned (CPO) value: How much less do CPO vehicles cost compared to equivalent new vehicles? What warranty coverage do CPO vehicles offer? - Model-specific trends: Do certain brands or models retain value better than others? Are there "depreciation risks" in specific segments? THREAD 3: Total Cost of Ownership (TCO) Analysis Research the complete cost picture across vehicle ownership lifecycle: - Financing costs: Calculate 5-year financing costs at different down payment levels (10%, 20%, 30%) and credit tier APRs. - Insurance costs: What are 2026 insurance premiums for new vehicles? How do insurance rates vary by vehicle type, age, and driver profile? Are new vehicles more expensive to insure than used? - Fuel/energy costs: What is 2026 gasoline pricing? What is the cost difference between fuel efficiency categories (15 MPG vs. 25 MPG vs. 40 MPG EV equivalent)? - Maintenance & repair costs: What are annual maintenance costs for new vehicles vs. 5-year-old used vehicles? What is the cost impact of out-of-warranty repairs? - Registration, taxes, and fees: What are state/local registration costs and sales tax impacts on a $40K–$60K purchase? - Ownership timeline comparison: What does a 3-year ownership TCO look like? 5-year? 7-year? At what ownership length does buying become financially advantageous over leasing? THREAD 4: Personal Affordability Framework Research guidelines and frameworks for personal car affordability: - Income-based rules: What do financial advisors recommend for car-payment-to-income ratio? What percentage of gross/take-home income should monthly car payments consume? - Emergency fund impact: What emergency fund reserves should someone maintain after a car purchase? How should a down payment affect liquid savings? - Opportunity cost analysis: What is the real cost of tying $40K–$60K in a depreciating asset? What alternative investments could that capital generate over 5–7 years? - Debt integration: How should an existing auto loan, mortgage, or other debt affect a new car purchase decision? - Lifecycle factors: How do age, family situation, job stability, and life phase affect affordability decisions? (E.g., recent grad vs. established professional vs. near-retirement) - Credit score impact: How does a new car purchase affect credit scores? What should someone expect in terms of rate impact if they wait 6–12 months? THREAD 5: Opportunity Cost & Waiting Analysis Research the scenario analysis of buying now vs. waiting: - What is the cost of waiting 6 months? (Interest rate changes, depreciation of used inventory, potential price increases vs. decreases, incentive changes) - What is the cost of waiting 12 months? (Model year changes, potential interest rate reductions, technology updates, market conditions shifts) - Depreciation arbitrage: If you buy a new car now and sell it in 3 years, how much value will you lose? Would waiting to buy used (letting someone else absorb depreciation) save money? - Incentive timing: Are incentives typically higher or lower at specific times of year (quarters, model year transitions, holiday season)? - Technology obsolescence: Are upcoming model year changes (new platforms, safety features, infotainment systems) significant enough to justify waiting? - Tax law changes: Are there upcoming tax credits, incentives, or law changes (EV credits, etc.) that would make waiting advantageous? THREAD 6: Emerging Trends & Disruptors Research market-moving trends that could affect your decision: - EV transition acceleration: How quickly is the EV market growing? What is the current EV adoption rate? Are ICE (internal combustion) vehicles becoming harder to finance or insure? - Subscription services & alternatives: Are vehicle subscription services (Carvana, Zipcar alternatives, etc.) becoming competitive with traditional ownership? - Autonomous vehicle timeline: How close are fully autonomous vehicles to consumer availability? Would this create a technology cliff for new car purchases? - Supply chain recovery: Are semiconductor shortages, logistics delays, or manufacturing constraints still affecting availability? Are these improving or worsening? - Insurance rate trends: How are insurance companies adjusting rates for new vehicles, EVs, and autonomous features? Are insurance costs accelerating or stabilizing? - Second-hand EV market: Is the used EV market developing maturity, or is it still too new and risky for buyers concerned about battery health? THREAD 7: Psychological & Behavioral Factors Research decision-making psychology around car purchases: - FOMO vs. regret: What behavioral economics research exists on car-buying decisions? When do people regret buying now vs. wishing they'd bought sooner? - Anchoring effects: How does the MSRP anchor affect negotiation outcomes? Are buyers who focus on "payment" vs. "total price" systematically worse off? - Timing pressure: What creates artificial urgency in car buying? (End-of-quarter sales, model year transitions, dealer lot pressure) - Information asymmetry: How much should a buyer worry about not knowing "true" market conditions? Does more research improve decision quality or just increase anxiety? - Post-purchase satisfaction: What predicts satisfaction with a car purchase decision? Is it the car itself, the deal quality, or the decision process? THREAD 8: Decision Framework Integration Research and synthesize a decision model that integrates findings: - Decision trees: What frameworks help buyers weigh timing, affordability, and market factors? - Breakeven analysis: At what monthly payment, down payment, or ownership timeline does buying become clearly preferable to waiting or leasing? - Scenario analysis: Create 3–5 decision scenarios (conservative buyer, aggressive buyer, budget-constrained buyer, luxury-focused buyer, sustainability-focused buyer) and how the research applies to each. REQUIRED OUTPUT STRUCTURE Produce a research report with the following structure: A. EXECUTIVE SUMMARY (2–3 pages) - Thesis: Given 2026 market conditions and your personal context, is now a good time to buy? - Key findings summary: 1–2 sentences per research thread - Critical data points: 5–7 most important numbers from the research - Recommendation framework: 3–4 scenarios where buying NOW is clearly right, and 3–4 scenarios where waiting is clearly better B. PER-THREAD DETAILED FINDINGS (2–3 pages per thread) - For each research thread above, provide: * Current state: What does the 2026 market actually look like? * Key data points: 5–10 specific numbers with sources * Trends: What's improving vs. worsening since 2025? * Implications: What does this thread suggest about your decision? C. DATA TABLES & VISUALIZATION GUIDANCE (2–3 pages) - Table 1: Average financing costs by credit tier, down payment %, and loan term - Table 2: TCO comparison (new vs. 3-year-old used vs. 5-year-old used) across ownership periods - Table 3: Regional MSRP variation and incentive availability - Visualization guidance: Describe what graphs/charts would best represent TCO breakeven, depreciation curves, and APR by credit tier D. DECISION FRAMEWORK (2–3 pages) - Framework 1: If your household income is X, car payment rule suggests Y maximum payment - Framework 2: If you have Z in emergency reserves, what down payment is safe? - Framework 3: Based on depreciation + financing + opportunity cost, what ownership length breaks even? - Scenario analysis: Apply the framework to 5 distinct buyer personas and recommended actions for each E. CITATIONS & SOURCES (1–2 pages) - Full citation list with URLs for all sources cited in the report - Indicate data freshness: Is the data from 2026, late 2025, or earlier? - Note any sources that conflict and explain how you resolved conflicts - Flag any data gaps where current information wasn't available QUALITY REQUIREMENTS - Cite every numerical claim with a source - Distinguish between data-driven findings and expert opinion - Flag uncertainty: Use language like "current estimates suggest" or "according to [source]" rather than definitive claims - Avoid generic advice: All recommendations should be grounded in specific 2026 market data - Prioritize recency: Prefer 2026 data, then late 2025, then earlier data only if explicitly noted - Address complexity: Acknowledge trade-offs and admit when the evidence points in conflicting directions RESEARCHER BEHAVIOR - You are conducting research as a professional analyst, not a chatbot - Search broadly across at least 10 different sources per thread - When data sources conflict, investigate why and explain the discrepancy to the reader - Prioritize authoritative sources (government data, industry research firms like Cox Automotive, J.D. Power, Edmunds, Kelley Blue Book) but also include consumer forums and regional market analysis - Build the report incrementally: Start with Thread 1 (Market Timing), then proceed through Threads 2–7, then synthesize into the Decision Framework - Use footnotes or endnotes for citations; make it clear where your claims come from - Take your time: Quality research matters more than speed; a 5-minute thorough report beats a 2-minute surface report

Prompt Breakdown — How AI Reads the Deep Research Prompt

This prompt is much longer and more structured than a typical "should I buy a car?" question. Let's break down why each section matters and what principle you can carry forward to any complex decision.

RESEARCH CONTEXT (The Setup)

The prompt opens with a clear context statement: "I'm considering buying a car in 2026 but uncertain about market timing and personal financial readiness." This tells the AI exactly what decision is on the table. It then immediately states the output constraint: "produce a professional research report that answers: Is NOW a good time for ME to buy a car, or would waiting change the outcome?" This prevents the AI from delivering generic advice or surface-level opinions. You're explicitly asking for research, not conversation.

Transferable Principle: When asking for research or analysis, explicitly state the decision question first, then state that you want a report, not casual advice. This sets behavioral expectations.

RESEARCH THREADS (The Skeleton)

Instead of asking the AI to figure out what to research, the prompt breaks the decision into 8 independent research threads: Market Timing, Depreciation, TCO, Affordability, Opportunity Cost, Trends, Psychology, and Decision Framework. Each thread has 3–5 specific sub-questions. Why? Because without this, the AI might research only price and ignore insurance; it might look at average affordability rules and ignore your personal situation; it might find data but fail to compare buying-now vs. waiting. By breaking the decision into threads, you force comprehensive coverage.

Transferable Principle: Break complex decisions into independent research dimensions. For any major decision, identify 6–8 parallel threads you need to explore (financial, personal fit, market timing, alternatives, trends, psychology, framework, risk). Ask the AI to research each one separately, then synthesize.

SUB-QUESTION SPECIFICITY (The Granularity)

Each thread includes 3–5 specific sub-questions. For example, in Thread 1 (Market Timing), the prompt asks: "What are average new-vehicle MSRPs in 2026? How has pricing evolved since 2025?" Notice it doesn't just say "research pricing." It specifies what data point you need (MSRPs), the time period (2026), and the comparison baseline (vs. 2025). This prevents the AI from retreating to generic statements like "car prices are high." It forces specificity.

Transferable Principle: For each research thread, write 3–5 specific questions, not vague ones. Include time periods, comparison baselines, and measurable metrics. "What is X?" beats "research X," which beats "tell me about X."

REQUIRED OUTPUT STRUCTURE (The Blueprint)

The prompt specifies exactly what the output should look like: an executive summary, 2–3 pages per research thread with current state / key data / trends / implications, data tables, a decision framework, and citations. Without this, the AI might deliver a rambling narrative. With it, you're defining the architecture of the final report. You're saying, "I want an executive summary, then detailed findings, then actionable frameworks — in that order."

Transferable Principle: Always specify the output structure you want, section by section. This prevents AI from delivering unstructured walls of text and guarantees you get something you can actually use and reference.

QUALITY REQUIREMENTS (The Standards)

The prompt includes 6 explicit quality criteria: cite every number with a source, distinguish data from opinion, flag uncertainty, avoid generic advice, prioritize recency, and address complexity. These aren't suggestions; they're standards that shape what the AI considers "good research." Without them, the AI might cite a single source, present opinion as fact, or include 2024 data without noting that it's outdated. With them, you're defining what quality means.

Transferable Principle: Define quality criteria explicitly. When you care about citations, say so. When you want to distinguish research from opinion, say it. When recency matters, specify it. The AI will calibrate its work to meet your standards.

RESEARCHER BEHAVIOR (The Mindset)

The final section includes 5 behavioral instructions: treat this as professional analysis (not casual chat), search broadly across 10+ sources per thread, investigate when sources conflict, prioritize authoritative sources, and take your time. These instructions reframe what "good research" means. You're not asking for speed; you're asking for thoroughness. You're not asking for consensus; you're asking for the AI to investigate conflicting evidence. This changes how the AI approaches the entire task.

Transferable Principle: Tell the AI how to approach the work, not just what the output should look like. Specify breadth (10+ sources), prioritization (authorities first), and how to handle edge cases (conflicts, uncertainty, data gaps).

What to Expect

Output length: Depending on the platform, Deep Research reports typically run 15–30 pages (15K–25K words). Claude tends to produce longer, more detailed reports. ChatGPT's Deep Research generates 12–20 pages. Gemini's Deep Research is more concise but still comprehensive. You're not getting a 2-paragraph answer; you're getting a full research deliverable.

Completion time: Deep Research takes time. ChatGPT's Deep Research typically completes in 5–15 minutes. Claude's research mode may take 10–20 minutes depending on complexity. Gemini's Deep Research is fastest, often completing in 5–10 minutes. This is slower than a normal chat response, but the depth justifies the wait.

Structure of output: The report will follow the structure you specified: Executive Summary, Per-Thread Findings, Data Tables, Decision Framework, and Citations. Each section will be labeled and clearly separated so you can navigate and reference specific parts. If you want to drill into depreciation data, you'll know exactly where to find it.

Quality expectations: A well-executed Deep Research report on car buying will include current market data (MSRPs, interest rates, incentives), multiple perspectives (conservative vs. aggressive buyer), data tables with numbers, and explicit citations. You should see footnotes, source URLs, and clear language about data freshness ("This data is from March 2026" vs. "The most recent data available is from late 2025"). If the report includes vague claims without citations, it didn't meet the standard.

Adaptation to your personal situation: The report will be generalized (it can't know your exact income, credit score, or personal preferences), but the decision framework and scenarios should help you apply it. You'll read the "conservative buyer" scenario and think, "That's me," then apply that section to your decision. The research gives you the market foundation; the framework helps you plug in your personal context.

Key Research Questions the Prompt Investigates

1. Is the 2026 car market favorable to buyers, or does it still favor sellers? The research explores MSRP trends, inventory levels, and incentive availability to determine whether buyer or seller power has shifted since 2025.

2. How much value will a new car lose in the first 3–5 years? Depreciation research produces specific percentages for different vehicle types and ownership timelines, helping you understand what you're really "paying" for ownership vs. financing.

3. What is my true cost of ownership, not just monthly payment? The TCO analysis includes financing, insurance, fuel, maintenance, and taxes — forcing you to see the complete financial picture, not just the monthly number advertised at the dealership.

4. What's the maximum car payment I can afford without financial stress? Affordability research produces income-based rules (e.g., "10% of take-home income") and helps you determine a safe payment range given your financial situation.

5. Is waiting 6–12 months likely to improve my situation or make it worse? Opportunity cost research explores interest rate trends, depreciation timelines, technology changes, and incentive cycles to help you think through the timing question explicitly.

6. Are emerging trends (EV adoption, autonomous vehicles, subscription models) making my purchase less desirable? Trend research surfaces technology shifts and market changes that might make a 2026 purchase feel obsolete faster than expected.

7. What psychological traps am I likely to fall into, and how do I avoid them? Psychology research exposes anchoring effects, FOMO, false urgency, and other behavioral patterns that lead to regrettable car purchases.

8. Given all this research, what does a clear decision framework look like for my situation? Framework synthesis takes all the threads and produces concrete, actionable decision criteria: if you have $X income, max payment is Y; if you have Z in savings, down payment should be W; breakeven ownership is N years.

Platform-Specific Tips

ChatGPT

ChatGPT's Deep Research is available in the web version and requires a ChatGPT Plus subscription. To access it: (1) Click the "+" icon when starting a new chat, (2) Select "Deep Research" from the options, (3) Paste the prompt above into the input field, and (4) Send. ChatGPT will search actively for 5–10 minutes, then compile the report. ChatGPT's Deep Research is fast and produces well-organized reports with clear section headers. The citations are reliable and include URLs. Pro tip: ChatGPT's Deep Research sometimes requires follow-up questions to drill into specific threads; be prepared with follow-ups like "Can you expand the depreciation section?" or "Give me more detail on APRs by credit tier?"

Claude

Claude's Extended Thinking mode (which serves a similar function to Deep Research) is available in Claude 3.5 Sonnet and requires a Claude Pro subscription or sufficient API credits. To access: (1) Use Claude.ai or a Claude API client, (2) Paste the prompt above, (3) Select "Extended Thinking" toggle before sending, and (4) Send. Claude will spend 2–5 minutes in Extended Thinking mode before drafting the report. Claude's reports are typically the longest and most detailed of the three platforms, with sophisticated analysis of trade-offs and nuance. Claude also tends to be more explicit about data gaps and uncertainty. Pro tip: Claude's Extended Thinking sometimes produces reports in a more narrative style; if you need structured tables, ask a follow-up: "Create a table summarizing the TCO analysis across the three scenarios."

Gemini

Google Gemini's Deep Research is available in the web version (gemini.google.com) with a Google account. To access: (1) Start a new conversation in Gemini, (2) Look for "Research with Gemini" or "Use web insights" option (exact wording may vary by interface), (3) Paste the prompt above, and (4) Send. Gemini's Deep Research is typically fastest (5–10 minutes) and produces concise, well-cited reports. Gemini excels at finding diverse sources and often surfaces regional variations and emerging trends that Claude and ChatGPT miss. Pro tip: Gemini's interface sometimes limits output length; if the report cuts off, ask a follow-up: "Continue the report with the Decision Framework section."

Cross-Platform Consideration: All three platforms will produce usable reports, but they'll differ in emphasis, depth, and structure. ChatGPT's is the most polished; Claude's is the most detailed; Gemini's is the most efficient. If you want the most thorough analysis, run the prompt on Claude. If you prefer speed and polish, ChatGPT is solid. If you want multiple perspectives, run it on all three and compare findings.

How This Connects to the Weekly Posts

The "AI at the Dealership" series includes three parallel blog posts this week: a ChatGPT version, a Claude version, and a Gemini comparison post. Those posts teach practical prompts for specific car-buying decisions (New vs. CPO, financing questions, negotiation tactics). This Deep Research post is the conceptual foundation — it shows you how to use Deep Research mode to conduct your own comprehensive investigation. The individual platform posts are tactical; this post is strategic. Together, they provide the full toolkit: use Deep Research for the big, foundational question ("Should I buy now?"), then use the platform-specific prompts for the tactical follow-ups ("New or CPO?" "What can I negotiate?"). The comparison post breaks down which platform excels at which type of car-buying question.

Adaptability Tips

Adapting for Home Buying

The Deep Research prompt structure applies perfectly to real estate. Replace the research threads with: Market Timing (inventory, days-on-market, price trends by neighborhood), Affordability (debt-to-income ratios, down payment requirements, closing costs), Opportunity Cost (rent vs. buy analysis, mortgage rate trends), Market Conditions (interest rate forecasts, supply/demand by region), Risk Factors (home inspection issues, property tax trends, HOA dynamics), and Decision Framework (affordability calculators, neighborhood analysis, scenario planning). The output structure stays identical: executive summary, per-thread findings, data tables, decision framework, citations. Estimated report length: 20–30 pages.

Adapting for College Selection

Replace threads with: Institution Fit (academic programs, campus culture, selectivity), Financial Reality (sticker price, aid packages, ROI data), Opportunity Factors (transfer options, graduate school impact, industry connections), Market Positioning (employer brand of graduates, regional prestige, career outcomes by major), Lifestyle Fit (location, climate, extracurriculars, housing), Alternative Paths (community college transfer, gap year, online programs), and Decision Framework (cost-benefit scenarios, career impact modeling). This produces a comprehensive report on whether a specific college is right for you and right now. Estimated length: 15–25 pages.

Adapting for Career Changes

Research threads become: Market Demand (job growth, salary ranges by region/industry), Retraining Requirements (time, cost, certifications needed), Financial Impact (income loss during transition, return-on-investment timeline), Opportunity Cost (what you give up by switching), Personal Fit (skills, interests, lifestyle alignment), Risk Factors (industry trends, job security, automation risk), and Decision Framework (scenarios for different risk tolerances, break-even timeline). The result is a research report on whether a specific career change makes sense and when. Estimated length: 15–20 pages.

Adapting for Business Equipment Investment

Threads include: Business Impact (productivity gains, revenue impact, risk reduction), Financial Analysis (upfront cost, financing options, depreciation, maintenance), Competitive Landscape (what competitors use, technology trends, risk of obsolescence), Market Timing (pricing trends, tax incentives, leasing vs. buying), Vendor Options (brands, support, warranty), and Decision Framework (ROI models, cash flow impact, scenarios by business size). This produces a professional research report on whether and when to invest in equipment. Estimated length: 10–15 pages.

Follow-Up Prompts

After your Deep Research report completes, you'll have a strong foundation for the decision. But you'll likely have tactical questions the report doesn't fully answer. Here are three recommended follow-up prompts:

Follow-Up 1: Decision Clarification

After reading the report, you'll know whether NOW is a good time, but you might need clarification on your personal situation: "Based on the report, I have $X in emergency savings, make $Y per month, and have $Z in other debt. Walking through your decision framework, what's the maximum car payment I should take? What down payment would be prudent? Should I wait 6 months?" This turns the general research into your specific decision.

Follow-Up 2: Negotiation Strategy

Once you've decided to buy, you'll want to negotiate effectively: "Using the market data from the Deep Research report (MSRPs, incentives, credit tier APRs), create a negotiation script for [specific vehicle]. What should I offer first? What is a realistic target price? What financing term and APR should I target given my credit score?" This uses the research to build a negotiation playbook.

Follow-Up 3: Post-Purchase Validation

After you've made your decision (or if you decide to wait), you might want to validate the choice: "I've decided to buy [specific vehicle] at [specific price with specific financing]. Validate this decision against the research findings. Where did I do well? Where am I taking unnecessary risk?" This is a final sanity check before commitment.

Metadata

Topic Deep Research Methodology, Car Buying Decisions, Market Research
Week Week 1
Series AI at the Dealership: 7 Weeks of Prompts That Could Save You Thousands
Platform Compatibility ChatGPT (Plus, Deep Research), Claude (Pro/API, Extended Thinking), Gemini (web, Deep Research)
Post Type Deep Research Prompt + Methodology Teaching
Tags car-buying, deep-research, prompt-engineering, market-research, decision-frameworks, affordability, opportunity-cost, ai-tools
Categories AI Tools, Prompts, Decision Making, Financial Literacy
Reading Time 12-15 minutes
SEO Title Week 1 Deep Research Prompt: Should You Really Buy a Car Right Now? | Ketelsen.ai
SEO Description The complete Deep Research prompt for car-buying decisions. 8 research threads, decision frameworks, and platform-specific tips for ChatGPT, Claude, and Gemini. Includes 2026 market data and affordability analysis.
Word Count (Prompt) Approximately 1,100 words (in the styled div)
Publish Date April 6, 2026

End of post. This Deep Research prompt and methodology teaching is the foundation for Week 1 of the AI at the Dealership series. It equips you to conduct your own comprehensive research instead of relying on casual advice. Use this prompt in ChatGPT, Claude, or Gemini's Deep Research/Extended Thinking mode, then follow up with platform-specific prompts for tactical questions. The result is a decision grounded in current evidence, not assumptions.

Richard Ketelsen
Previous

Week 5 Deep Research: The New vs. CPO Investigation
Next

Week 5 AI Showdown: Which Platform Wrote the Best New vs. CPO Post?