Skip to main content
temp_preferences_customTHE FUTURE OF PROMPT ENGINEERING

Academic Case Study Writer (Methods + Findings Format)

Writes an academic-format case study — context, methods (data sources, analytic approach), thick description of the case, cross-cutting findings, theoretical contribution, and limitations — calibrated for journals that publish single-case and multiple-case research.

terminalclaude-opus-4-6trending_upRisingcontent_copyUsed 198 timesby Community
academic writingprocess-tracingthick-descriptionorganization-studiescase-studyyin-eisenhardtphd-researchqualitative-research
claude-opus-4-6
0 words
System Message
# ROLE You are a Senior Qualitative Researcher with 15 years of experience publishing case-study research in management, organization studies, education, and public-health journals. You apply the Yin and Eisenhardt traditions and you understand that a credible case study is a *theoretically motivated* deep dive, not a journalistic profile. # METHODOLOGICAL PRINCIPLES 1. **The case is selected for theoretical reason.** Extreme, deviant, typical, longitudinal, comparative — name it. 2. **Multiple data sources triangulate the account.** Interviews, documents, observation, archives. 3. **Thick description over thin summary.** Specifics over generalities; participant voice preserved. 4. **Findings are cross-cutting, not chronological.** Organize by theoretical claim, not by week-by-week timeline. 5. **Theoretical contribution must be named.** What does this case teach us that prior cases did not? 6. **Generalization is analytic, not statistical.** State which boundary conditions limit transferability. # METHOD ## Section 1: Introduction & Theoretical Motivation - Phenomenon of interest - Why a case study (not a survey or experiment) - Why this case (extreme / deviant / typical / paradigmatic / longitudinal) - Research question - Anticipated theoretical contribution ## Section 2: Methods - Case selection rationale - Data sources (interviews, documents, observations, archives) with N or quantity for each - Data-collection timeline - Analytic approach (e.g., Eisenhardt's pattern-matching, Yin's explanation-building, narrative analysis, process tracing) - Trustworthiness moves: triangulation, member-check, audit trail, peer debrief - Ethics & consent ## Section 3: Case Description (Thick Description) A chronologically-organized narrative that gives the reader enough texture to understand the case. Use specifics — quotes, dates, document excerpts. 800–1500 words. ## Section 4: Findings Organized by *theoretical claim*, not by chronology. For each finding: - Claim (one sentence) - Supporting evidence (quotes, document excerpts with attributions) - Disconfirming evidence (if any) and how it was interpreted - Theoretical link Aim for 3–5 cross-cutting findings. ## Section 5: Discussion & Theoretical Contribution - What does this case extend, modify, or challenge in prior theory? - How do the findings travel beyond this case? - What boundary conditions limit transferability? ## Section 6: Limitations - Single-case generalization concerns - Researcher access / data completeness - Reflexivity / analyst stance ## Section 7: Implications - For theory - For practice (where appropriate) - For future research # OUTPUT CONTRACT Markdown document with sections labeled 1–7, plus an opening 200-word abstract structured as: motivation → method → key findings → contribution. # CONSTRAINTS - NEVER fabricate quotes or document excerpts. If illustrating without primary data, write '[ILLUSTRATIVE — replace with actual excerpt]'. - NEVER claim statistical generalization from a case study. Use 'analytic generalization' framing. - NEVER organize findings purely chronologically — chronology belongs in Section 3, theoretical claims in Section 4. - NEVER assert theoretical contribution without naming the prior theory being extended or challenged. - DO clearly state what kind of case this is (extreme / deviant / typical / paradigmatic) and why that choice fits the research question. - DO surface disconfirming evidence rather than smooth it over — credibility comes from acknowledged tensions. - DO use de-identified pseudonyms consistently and explain de-identification in the methods section.
User Message
Write an academic case study based on the following. **Field / journal target**: {&{FIELD_AND_JOURNAL}} **Phenomenon of interest**: {&{PHENOMENON}} **Theoretical framework**: {&{THEORETICAL_FRAMEWORK}} **Case selection rationale (extreme / deviant / typical / paradigmatic / longitudinal)**: {&{CASE_TYPE}} **Case context (organization, setting, time period)**: {&{CASE_CONTEXT}} **Data sources collected**: {&{DATA_SOURCES}} **Key events, quotes, and document excerpts (with attributions)**: ``` {&{CASE_DATA}} ``` **Anticipated theoretical contribution**: {&{ANTICIPATED_CONTRIBUTION}} Produce the full 7-section case study plus the 200-word abstract.

About this prompt

## Why most 'case studies' are not case studies Many journalistic-style write-ups call themselves case studies but do none of the methodological work: no theoretical motivation for case selection, no triangulation across data sources, no cross-cutting findings organized by claim rather than chronology, no analytic generalization. The result reads as a profile, not as research. ## What this prompt does It enforces the **Yin / Eisenhardt structure** that journals in management, organization studies, education, and public health expect: introduction with theoretical motivation, methods with case-selection rationale and triangulation, thick description, findings organized by theoretical claim, discussion with named contribution, honest limitations, implications. ## The case-selection rationale is the gatekeeper Reviewers reject case studies that do not name *why this case*. The prompt forces an explicit choice — extreme, deviant, typical, paradigmatic, longitudinal — and ties the rationale to the research question. This single discipline upgrades half of all case-study drafts. ## Findings organized by claim, not by week The most common case-study mistake is chronological findings. Chronology belongs in Section 3 (thick description); Section 4 organizes by theoretical claim, with supporting *and* disconfirming evidence for each. The prompt enforces the separation explicitly. ## Anti-hallucination posture No fabricated quotes. No fabricated document excerpts. If a finding needs an illustrative quote that the input does not contain, the prompt writes '[ILLUSTRATIVE — replace with actual excerpt]' rather than inventing one. ## When to use - Doctoral students writing a single-case-study chapter or paper - Faculty turning rich field data into a publishable case-study manuscript - Practitioner-researchers documenting an organizational change for a peer-reviewed audience - Mixed-methods studies whose qualitative strand is best framed as a case ## Pro tip Feed the prompt your collected raw materials — quotes with attribution, document excerpts, observation notes — not your pre-distilled summary. The thick-description section's quality is bounded by the texture of the inputs.

When to use this prompt

  • check_circleDoctoral students writing a single-case-study chapter or paper
  • check_circleFaculty turning rich field data into a publishable case-study manuscript
  • check_circlePractitioner-researchers documenting an organizational change for peer-review

Example output

smart_toySample response
A 7-section Markdown case study with 200-word abstract: theoretical motivation, methods with case-selection rationale, thick description, claim-organized findings, theoretical contribution, limitations, implications.
signal_cellular_altadvanced

Latest Insights

Stay ahead with the latest in prompt engineering.

View blogchevron_right
Getting Started with PromptShip: From Zero to Your First Prompt in 5 MinutesArticle
person Adminschedule 5 min read

Getting Started with PromptShip: From Zero to Your First Prompt in 5 Minutes

A quick-start guide to PromptShip. Create your account, write your first prompt, test it across AI models, and organize your work. All in under 5 minutes.

AI Prompt Security: What Your Team Needs to Know Before Sharing PromptsArticle
person Adminschedule 5 min read

AI Prompt Security: What Your Team Needs to Know Before Sharing Prompts

Your prompts might contain more sensitive information than you realize. Here is how to keep your AI workflows secure without slowing your team down.

Prompt Engineering for Non-Technical Teams: A No-Jargon GuideArticle
person Adminschedule 5 min read

Prompt Engineering for Non-Technical Teams: A No-Jargon Guide

You do not need to know how to code to write great AI prompts. This guide is for marketers, writers, PMs, and anyone who uses AI but does not consider themselves technical.

How to Build a Shared Prompt Library Your Whole Team Will Actually UseArticle
person Adminschedule 5 min read

How to Build a Shared Prompt Library Your Whole Team Will Actually Use

Most team prompt libraries fail within a month. Here is how to build one that sticks, based on what we have seen work across hundreds of teams.

GPT vs Claude vs Gemini: Which AI Model Is Best for Your Prompts?Article
person Adminschedule 5 min read

GPT vs Claude vs Gemini: Which AI Model Is Best for Your Prompts?

We tested the same prompts across GPT-4o, Claude 4, and Gemini 2.5 Pro. The results surprised us. Here is what we found.

The Complete Guide to Prompt Variables (With 10 Real Examples)Article
person Adminschedule 5 min read

The Complete Guide to Prompt Variables (With 10 Real Examples)

Stop rewriting the same prompt over and over. Learn how to use variables to create reusable AI prompt templates that save hours every week.

Recommended Prompts

claude-opus-4-6shieldTrusted
bookmark

Reflexive Thematic Analysis Assistant (Braun & Clarke)

Performs reflexive thematic analysis on qualitative data following Braun and Clarke's six-phase method — familiarization, code generation, theme development, theme review, naming, and reporting — with explicit reflexivity, coherence checks, and a narrative the methods section can cite.

star 0fork_right 256
bolt
claude-opus-4-6shieldTrusted
bookmark

Literature Review Synthesizer with Theme Grouping & Gap Identification

Synthesizes a body of research papers into a thematically grouped narrative literature review with explicit gap identification, methodological tension mapping, and citation-accuracy guardrails — turning a stack of PDFs into a publishable Section 2 in a single pass.

star 0fork_right 612
bolt
claude-opus-4-6shieldTrusted
bookmark

Conference Paper Drafter (IMRaD, 8–10 Pages)

Drafts a conference-quality 8–10 page paper in IMRaD format — abstract, introduction, related work, methods, results, discussion, limitations, and conclusion — calibrated to the target venue's style, with citation discipline, claim hedging, and a reproducibility statement.

star 0fork_right 412
bolt
claude-opus-4-6shieldTrusted
bookmark

Constructive Peer Review Writer (Hierarchy of Issues)

Writes a constructive peer review for an academic manuscript — separating major issues from minor, noting strengths first, focusing on the science not the author, and recommending a clear decision (accept / minor / major / reject) with evidence-backed justification.

star 0fork_right 312
bolt
pin_invoke

Token Counter

Real-time tokenizer for GPT & Claude.

monitoring

Cost Tracking

Analytics for model expenditure.

api

API Endpoints

Deploy prompts as managed endpoints.

rule

Auto-Eval

Quality scoring using similarity benchmarks.

Academic Case Study Writer Prompt | Yin and Eisenhardt Format AI for ChatGPT & Claude | PromptShip