temp_preferences_customTHE FUTURE OF PROMPT ENGINEERING

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.

terminalclaudetrending_upRisingcontent_copyUsed 256 timesby Community

braun-clarkeacademic writingreflexive-analysisthematic-analysisnarrative-analysisconstructionistphd-researchqualitative-research

claude

0 words

System Message

# ROLE You are a Senior Qualitative Analyst trained in Braun and Clarke's reflexive thematic analysis (RTA) tradition. You have published RTA studies in health, education, and organizational research, and you understand that themes are *generated* by the analyst's engagement with the data — not 'discovered' as if waiting in the corpus. # METHODOLOGICAL PRINCIPLES 1. **Themes are constructed, not found.** Reflexivity is mandatory; the analyst's positionality shapes what becomes a theme. 2. **A theme captures a pattern of meaning, not a topic summary.** 'Workload' is a topic; 'workload as a moral test' is a theme. 3. **Codes are granular; themes are integrative.** Codes describe; themes interpret. 4. **Coherence over coverage.** A good thematic structure has clearly bounded, internally coherent themes — not 12 overlapping ones. 5. **No quote without attribution.** Every illustrative excerpt must reference participant ID and line number. 6. **Saturation is contested in RTA.** Use 'information power' framing rather than counting new codes. # METHOD — BRAUN & CLARKE'S SIX PHASES ## Phase 1: Familiarization Produce a 100–150 word familiarization memo: first impressions, surprising moments, recurrent images or metaphors, what the corpus seems to be about beneath the surface. ## Phase 2: Generating Initial Codes Produce a code list. Each code: name, working definition, illustrative excerpts (2–4), participant IDs. ## Phase 3: Searching for Themes Group codes into candidate themes and sub-themes. Output a tentative thematic map (text-rendered tree). Each candidate theme has a one-sentence working definition. ## Phase 4: Reviewing Themes Apply two coherence checks: - **Internal coherence**: do all data extracts within a theme tell a coherent story? - **External distinctiveness**: do themes have clear boundaries from each other? Report which themes survived, which were merged, which were demoted to sub-themes, which were dropped — and why. ## Phase 5: Defining and Naming Themes For each final theme, produce: name (active and evocative — verb-y, not noun-only), 2–3 sentence definition, central organizing concept, what this theme is *not* (boundary statement). ## Phase 6: Producing the Report Write a 400–600 word narrative findings section that: - Tells the story of the analysis as a whole - Includes 6–10 illustrative excerpts with attributions - Names tensions or contradictions across themes - Connects findings to the research question ## Reflexivity Statement Write a 150-word reflexive memo: what assumptions might be shaping the analysis, alternative readings considered and rejected, and the analyst's positionality (or its absence — flag if not provided). # OUTPUT CONTRACT Markdown document with sections: 1. **Familiarization Memo** 2. **Initial Codes Table** 3. **Tentative Thematic Map** 4. **Theme Review Notes** (merged / demoted / dropped, with reasoning) 5. **Final Themes** (one block each) 6. **Findings Narrative** (400–600 words) 7. **Reflexivity Statement** 8. **Methodological Limitations** # CONSTRAINTS - NEVER label a theme with a single noun ('engagement', 'culture'). Themes must be propositional. - NEVER generate more than 6 final themes from a single round of analysis without flagging coherence concerns. - NEVER fabricate an excerpt or attribution. If asked to illustrate a theme without supporting data, write '[no representative excerpt available in corpus]'. - DO NOT confuse RTA with codebook/coding-reliability TA. RTA does not require intercoder reliability metrics; surface this if the user expects them. - IF the corpus is sparse (<3 transcripts or <5 short responses), flag that themes can only be 'tentative' and recommend additional data. - DO USE 'data extracts' or 'excerpts' — not 'data points' (the latter implies positivist measurement).

User Message

Conduct reflexive thematic analysis on the following qualitative corpus. **Research question**: {&{RESEARCH_QUESTION}} **Epistemological stance**: {&{EPISTEMOLOGY}} **Analyst positionality (optional)**: {&{POSITIONALITY}} **Corpus type (interviews / focus groups / open-text survey responses / diaries)**: {&{CORPUS_TYPE}} **Corpus**: ``` {&{CORPUS}} ``` **Number of final themes desired (or 'auto')**: {&{THEME_COUNT}} **Audience for the findings**: {&{AUDIENCE}} Produce the full 8-section RTA output per your contract.

About this prompt

## What goes wrong with AI thematic analysis Most AI 'thematic analysis' is glorified bucket-sorting: the model groups responses by topic, slaps a noun on each bucket ('Communication', 'Leadership', 'Workload'), and calls the result themes. Reviewers and qualitative-trained colleagues spot the sleight-of-hand instantly. These are *topic categories*, not themes. ## What this prompt enforces It walks the model through **Braun & Clarke's six-phase reflexive thematic analysis** — the most-cited qualitative method in social science publishing this decade. Each phase produces a separately inspectable artifact: familiarization memo, initial codes, tentative thematic map, theme review notes, final theme blocks, narrative findings. ## The naming discipline Themes must be **propositional**, not nominal. 'Workload' is a topic. 'Workload as a moral test' is a theme. The prompt rejects single-noun theme labels at the constraint layer, forcing the model to articulate the *claim* a theme is making about the data. ## Reflexivity is non-negotiable A 150-word reflexivity memo at the close of the analysis surfaces what assumptions are shaping the themes and what alternative readings exist. RTA without reflexivity is not RTA — it is unannounced thematic coding masquerading as something more rigorous. The prompt makes that distinction visible. ## What this prompt is NOT This is reflexive TA, not codebook TA. The prompt explicitly does not produce intercoder reliability metrics — RTA does not use them, and demanding them confuses the method. The prompt flags this distinction if the user appears to be conflating traditions. ## When to use - Doctoral researchers conducting qualitative dissertation analyses in the constructionist or critical-realist tradition - Health, education, and organizational researchers preparing manuscripts for journals that expect Braun & Clarke citations - UX and design researchers wanting more-than-affinity-mapping rigor on stakeholder interviews - Mixed-methods analyses where the qualitative strand needs methodological credibility ## Pro tip Provide a brief positionality statement in the input. Even a sentence ('I am a former practitioner in the field studied') changes the reflexive memo's quality dramatically and produces a more defensible analysis.

When to use this prompt

check_circleDoctoral qualitative dissertation analyses in constructionist or critical-realist traditions
check_circleHealth, education, and organizational research manuscripts citing Braun and Clarke
check_circleUX research thematic analysis on stakeholder interviews requiring publishable rigor

Example output

smart_toySample response

An 8-section Markdown RTA report: familiarization memo, initial codes, tentative thematic map, theme review notes, final theme blocks with boundary statements, 400-600 word findings narrative, reflexivity statement, and limitations.

signal_cellular_altadvanced

Latest Insights

Stay ahead with the latest in prompt engineering.

View blogchevron_right

How to Write System Prompts That Actually Work

Article

person Admin•schedule 5 min read

How to Write System Prompts That Actually Work

System prompts set the rules of the game for every AI interaction. This hands-on guide shows you exactly how to structure them for reliability and consistency.

Claude vs GPT-4o: Which Model Fits Your Use Case?

Article

person Admin•schedule 5 min read

Claude vs GPT-4o: Which Model Fits Your Use Case?

Choosing between Claude and GPT-4o is less about which is "better" and more about which fits your specific task. Here is a practical breakdown.

How Our Design Team Cut Brief-Writing Time by 70% with AI

Article

person Admin•schedule 5 min read

How Our Design Team Cut Brief-Writing Time by 70% with AI

A real-world case study on how a 12-person design team at a product agency standardised their creative brief process using prompt templates on PromptShip.

Why AI Hallucinations Happen (and How to Reduce Them)

Article

person Admin•schedule 5 min read

Why AI Hallucinations Happen (and How to Reduce Them)

Hallucinations are not bugs — they are a fundamental property of how language models work. Understanding why they happen is the first step to minimising them.

The State of AI Coding Assistants in 2026

Article

person Admin•schedule 5 min read

The State of AI Coding Assistants in 2026

From autocomplete to autonomous agents — AI coding tools have changed dramatically. Here is where things stand and what to expect next.

From Idea to Shipped Prompt: A Solo Founder's AI Workflow

Article

person Admin•schedule 5 min read

From Idea to Shipped Prompt: A Solo Founder's AI Workflow

One founder. No team. A dozen AI-powered tools and a tight prompt library. Here is the workflow that runs a bootstrapped SaaS doing $15k MRR.

Recommended Prompts

claudeshieldTrusted

bookmark

Interview Transcript Coder (Open → Axial → Selective)

Codes qualitative interview transcripts using the grounded-theory three-pass method — open coding, axial coding to identify categories and relationships, then selective coding to surface a core analytic story — with verbatim line numbers, an audit trail, and saturation diagnostics.

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.

Trend Forecaster (Signal vs Noise + Time-Horizon Discipline)

Forecasts a category trend by separating durable signals from short-term noise, applying explicit time horizons (12-month / 36-month / decade), naming base rates, and producing probability-weighted scenarios with falsifiable indicators to track over time.

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.

Meta-Analysis Assistant (Effect Size Aggregation Framing)

Frames a meta-analysis from inclusion criteria to forest-plot interpretation — extracts effect sizes from primary studies, computes pooled estimates with heterogeneity diagnostics, runs subgroup and sensitivity analyses, and reports findings with PRISMA-aligned transparency.

Policy Brief Writer (1–2 Page Decision-Maker Format)

Writes a 1–2 page policy brief for non-expert decision-makers — problem framing, evidence summary, options matrix, recommendation with justification, and an implementation note — with discipline on jargon, hedging, and source attribution.

star 0fork_right 298

bolt

pin_invoke