Evidence-Backed Portfolio Case Study Prompt

Create an evidence-backed portfolio case study from the following input packet.

Input packet
- Target audience and career objective: [Target audience and career objective]
- Project context and challenge: [Project context and challenge]
- Personal role and contribution: [Personal role and contribution]
- Process, decisions, and trade-offs: [Process decisions and trade-offs]
- Evidence and outcomes: [Evidence and outcomes]
- Source materials: [Source materials]
- Confidentiality and publishing constraints: [Confidentiality and publishing constraints]
- Desired format and length: [Desired format and length]

Input requirements
The minimum reliable inputs are the project context, the candidate's role, the problem addressed, and credible evidence of at least part of the work or decision process. Useful supporting material includes briefs, notes, deliverables, screenshots, research summaries, designs, repositories, analytics exports, feedback, testimonials, timelines, and outcome calculations.

If a missing or conflicting detail would materially change authorship, chronology, confidentiality, or an outcome claim, ask up to five focused blocking questions before drafting. If answers are unavailable, continue only with bounded progress: preserve the gap as “Unknown—author input required,” omit unsupported specificity, and classify the result as a review draft rather than publish-ready.

Evidence and claim rules
1. Work only from information supplied in the conversation and materials Claude can actually inspect. If a file, link, system, or private record is inaccessible, identify it as unavailable rather than implying it was reviewed.
2. Classify material claims as artifact-backed, attributed self-report, calculation, assumption, disputed, or unknown. Cite the relevant source name, file, excerpt, or data point when available.
3. Never invent metrics, dates, user quotes, research findings, employer approval, team composition, responsibilities, or business impact. Do not convert correlation into causation.
4. For quantitative outcomes, record the baseline, result, measurement period, calculation method, data source, and attribution limits. Separate measured results from estimates and qualitative observations.
5. Attribute shared work precisely. Distinguish what the candidate owned, contributed to, influenced, reviewed, or merely observed. Do not present team output as sole authorship.
6. Quote testimonials or stakeholder feedback exactly when source text exists. State whether permission to publish is confirmed, unknown, or unnecessary because the quote will be anonymized.
7. Resolve conflicting sources where possible. Otherwise show the conflict in the evidence ledger and use the more conservative formulation in the narrative.

Privacy, authority, and publication boundaries
- Draft and analyze only. Do not claim to publish, submit, contact anyone, obtain approval, edit source records, or verify private systems.
- Do not disclose personal data, credentials, unreleased financial figures, client secrets, security details, protected research, or information restricted by an NDA or employer policy.
- Recommend anonymization, aggregation, redaction, or omission where needed. Do not infer that anonymization makes restricted information safe to publish.
- Flag claims requiring employer, client, legal, testimonial, or asset-licensing approval. Human approval is required before publication.
- If the requested case study depends on fabricated achievements, deceptive authorship, or prohibited disclosure, stop that portion and provide a safe evidence-gathering or anonymized-outline alternative.

Case-study development workflow
1. Inventory the supplied materials and identify the project, audience, candidate contribution, chronology, constraints, artifacts, and claimed outcomes.
2. Build an evidence ledger before writing. Reconcile duplicate, incomplete, or conflicting claims and identify which statements can safely appear in public.
3. Select a positioning angle that connects the demonstrated work to the target career objective without forcing an unsupported narrative.
4. Define the case-study arc: context, challenge, candidate mandate, constraints, investigation, pivotal decisions, execution, complications, outcomes, and reflection.
5. Identify two to four decisions that reveal judgment. For each, explain the alternatives considered, evidence used, trade-off accepted, candidate's authority, and resulting consequence.
6. Separate process description from proof. Pair important claims with an artifact, observation, calculation, or clearly attributed account.
7. Draft in direct first person unless another voice is requested. Prefer concrete actions and decision rationale over vague claims such as “helped,” “optimized,” or “made an impact.”
8. Audit the draft for inflated ownership, hindsight bias, missing constraints, unexplained metrics, confidential details, unsupported causality, and portfolio artifacts that lack context.
9. Produce a verification matrix and assign the final handoff state: publish-ready after human approval, review draft, or blocked pending evidence or permission.

Required output: Portfolio Case Study Package

A. Readiness and positioning
- Handoff state and the reason for it
- Intended audience and career objective
- Recommended case-study angle
- Material assumptions, unknowns, conflicts, and blocking gaps
- Confidentiality or approval flags

B. Evidence ledger
Provide a table with these columns:
- Claim or fact
- Claim classification
- Candidate attribution
- Supporting source or artifact
- Confidence
- Publication status: usable, anonymize, permission required, unsupported, or omit
- Notes or conflict

C. Publishable case-study draft
Include:
- Specific title and one-sentence value proposition
- Project snapshot: organization or anonymized descriptor, candidate role, team context, duration, scope, and outcome status
- Context and challenge
- Candidate mandate and contribution boundaries
- Constraints and stakes
- Investigation or discovery process
- Pivotal decisions, alternatives, evidence, and trade-offs
- Execution narrative with the candidate's actions separated from team actions
- Complications, failures, or course corrections
- Outcomes, with measured, estimated, and qualitative results clearly separated
- Reflection: what worked, what did not, and what the candidate would change
- Skills demonstrated, each mapped to a specific passage or artifact
- Suggested artifact placements and captions; do not invent artifact contents

D. Decision record
Provide a table with these columns:
- Decision
- Options considered
- Evidence available at the time
- Chosen approach and rationale
- Trade-off or risk accepted
- Candidate's level of authority
- Observed consequence or current unknown

E. Verification and acceptance matrix
Check each of the following and report the expected standard, actual observation, evidence inspected, status, and required correction:
- Every major claim has a traceable source or is explicitly qualified
- Personal contribution is distinguishable from team contribution
- Chronology is internally consistent
- Quantitative outcomes include baseline, result, period, method, and attribution limits
- Quotes and testimonials are exact and have an appropriate permission status
- Confidential or identifying details are removed or flagged
- The narrative explains constraints, decisions, alternatives, and trade-offs
- Skills claims map to demonstrated behavior or artifacts
- No inaccessible source is described as inspected
- No approval, publication, measurement, or verification is claimed without evidence
- Length and format match the requested destination

Use pass, needs review, blocked, or not applicable for each check. A pass must cite the supporting passage or source. Do not label the package verified, approved, published, or complete unless that state is supported by evidence supplied in the conversation. End with the smallest safe action the author should take to move the package toward publication.