Reusable AI capability
Trace Consequential Claims to Original Evidence
Apply a repeatable claim-provenance method that traces consequential wording through citations and intermediaries to original evidence, exposing mutation, laundering, and authority gaps.
This Skill packages a reusable way to use the linked Prompt or Workflow; Amo.ng does not run it for you.
# Trace Consequential Claims to Original Evidence Skill ID: AMO-S-000016 Skill URL: https://amo.ng/skills/trace-consequential-claims-to-original-evidence Purpose: Give researchers, editors, analysts, policy owners, and release owners a reusable capability for deciding whether a material claim can be released, narrowed, repaired, withheld, or corrected. Required inputs: - Exact material claims and their intended decision, publication, or policy use - Current citations, links, documents, bibliographies, quoted passages, and intermediary sources - Original or near-original sources and datasets where accessible - Source access limits, dates, jurisdiction, population, method, and authority requirements - Accountable editorial, research, policy, legal, or release owner How to use: When to use: - A consequential claim depends on citations that may be secondary, stale, transformed, or disconnected from original evidence. - Publication, research, policy, risk, or decision material needs claim-level provenance. When not to use: - General source discovery with no exact claim to trace. - Treating citation presence, source prestige, or repeated quotation as proof. - Describing an inaccessible original source as inspected. Reusable method: 1. Freeze the exact claim wording and intended use. 2. Decompose compound claims into independently supportable assertions. 3. Trace every citation edge through reports, reviews, summaries, media, datasets, and original studies. 4. Record the transformation at each edge: quotation, paraphrase, synthesis, calculation, inference, omitted qualifier, or unsupported escalation. 5. Compare population, method, date, jurisdiction, outcome, uncertainty, and authority to the current wording. 6. Classify the chain as intact, repairable, broken, inaccessible, circular, or citation-laundered. 7. Recommend release as written, citation upgrade, narrowed wording, hold, removal, or correction. Expected output: A claim register, provenance graph, transformation ledger, source-authority assessment, broken-chain register, release disposition, wording or citation repairs, uncertainty, and owner verification steps. Boundaries: Do not invent source access, methods, datasets, approvals, or conclusions. Editorial or research owners approve wording and source choices; legal reviewers interpret legal obligations; the release owner decides publication, withholding, or correction. Source grounding: AMO-P-000288. Applicable Workflow: AMO-W-000011. Powered by Prompt: Claim Provenance Chain and Citation Traceability Audit Source ID: AMO-P-000288 https://amo.ng/prompts/claim-provenance-chain-and-citation-traceability-audit Completion criteria: Complete when every material claim has an intact chain or explicit break; each transformation and authority limit is recorded; inaccessible evidence is marked; releaseable wording has defensible original or near-original support; and the responsible owner has an observable verification action. Use this Amo.ng Skill with your preferred AI tool. Supply the required inputs and follow the usage instructions. # Trace Consequential Claims to Original Evidence Skill ID: AMO-S-000016 Skill URL: https://amo.ng/skills/trace-consequential-claims-to-original-evidence Purpose: Give researchers, editors, analysts, policy owners, and release owners a reusable capability for deciding whether a material claim can be released, narrowed, repaired, withheld, or corrected. Required inputs: - Exact material claims and their intended decision, publication, or policy use - Current citations, links, documents, bibliographies, quoted passages, and intermediary sources - Original or near-original sources and datasets where accessible - Source access limits, dates, jurisdiction, population, method, and authority requirements - Accountable editorial, research, policy, legal, or release owner How to use: When to use: - A consequential claim depends on citations that may be secondary, stale, transformed, or disconnected from original evidence. - Publication, research, policy, risk, or decision material needs claim-level provenance. When not to use: - General source discovery with no exact claim to trace. - Treating citation presence, source prestige, or repeated quotation as proof. - Describing an inaccessible original source as inspected. Reusable method: 1. Freeze the exact claim wording and intended use. 2. Decompose compound claims into independently supportable assertions. 3. Trace every citation edge through reports, reviews, summaries, media, datasets, and original studies. 4. Record the transformation at each edge: quotation, paraphrase, synthesis, calculation, inference, omitted qualifier, or unsupported escalation. 5. Compare population, method, date, jurisdiction, outcome, uncertainty, and authority to the current wording. 6. Classify the chain as intact, repairable, broken, inaccessible, circular, or citation-laundered. 7. Recommend release as written, citation upgrade, narrowed wording, hold, removal, or correction. Expected output: A claim register, provenance graph, transformation ledger, source-authority assessment, broken-chain register, release disposition, wording or citation repairs, uncertainty, and owner verification steps. Boundaries: Do not invent source access, methods, datasets, approvals, or conclusions. Editorial or research owners approve wording and source choices; legal reviewers interpret legal obligations; the release owner decides publication, withholding, or correction. Source grounding: AMO-P-000288. Applicable Workflow: AMO-W-000011. Powered by Prompt: Claim Provenance Chain and Citation Traceability Audit Source ID: AMO-P-000288 https://amo.ng/prompts/claim-provenance-chain-and-citation-traceability-audit Completion criteria: Complete when every material claim has an intact chain or explicit break; each transformation and authority limit is recorded; inaccessible evidence is marked; releaseable wording has defensible original or near-original support; and the responsible owner has an observable verification action.Copy skill copies the Skill details. Use with AI adds a short instruction for your preferred AI tool; neither action runs the Skill.
Purpose
Give researchers, editors, analysts, policy owners, and release owners a reusable capability for deciding whether a material claim can be released, narrowed, repaired, withheld, or corrected.
Required inputs
Have these details available before following the usage instructions.
- Exact material claims and their intended decision, publication, or policy use
- Current citations, links, documents, bibliographies, quoted passages, and intermediary sources
- Original or near-original sources and datasets where accessible
- Source access limits, dates, jurisdiction, population, method, and authority requirements
- Accountable editorial, research, policy, legal, or release owner
How to use this Skill
When to use:
- A consequential claim depends on citations that may be secondary, stale, transformed, or disconnected from original evidence.
- Publication, research, policy, risk, or decision material needs claim-level provenance.
When not to use:
- General source discovery with no exact claim to trace.
- Treating citation presence, source prestige, or repeated quotation as proof.
- Describing an inaccessible original source as inspected.
Reusable method:
1. Freeze the exact claim wording and intended use.
2. Decompose compound claims into independently supportable assertions.
3. Trace every citation edge through reports, reviews, summaries, media, datasets, and original studies.
4. Record the transformation at each edge: quotation, paraphrase, synthesis, calculation, inference, omitted qualifier, or unsupported escalation.
5. Compare population, method, date, jurisdiction, outcome, uncertainty, and authority to the current wording.
6. Classify the chain as intact, repairable, broken, inaccessible, circular, or citation-laundered.
7. Recommend release as written, citation upgrade, narrowed wording, hold, removal, or correction.
Expected output:
A claim register, provenance graph, transformation ledger, source-authority assessment, broken-chain register, release disposition, wording or citation repairs, uncertainty, and owner verification steps.
Boundaries:
Do not invent source access, methods, datasets, approvals, or conclusions. Editorial or research owners approve wording and source choices; legal reviewers interpret legal obligations; the release owner decides publication, withholding, or correction. Source grounding: AMO-P-000288. Applicable Workflow: AMO-W-000011.
Powered by an Amo.ng Prompt
Claim Provenance Chain and Citation Traceability Audit
Open the linked prompt to use the instructions that power this Skill.
Open prompt
Objective: Trace each material claim through its full citation chain to the earliest available original source, dataset, record, or primary evidence. Identify where citations merely repeat intermediaries, where meaning changes across the chain, where authority is unsupported, and what release or correction decision is justified.
Inputs to use:
- Material claims to audit: [Material claims to audit]
- Cited sources and intermediaries: [Cited sources and intermediaries]
- Decision context: [Decision context]
- Source access constraints: [Source access constraints]
- Accountable release owner: [Accountable release owner]
Instructions:
1. Treat each claim as a separate audit unit. Do not collapse similar claims unless the evidence chain is demonstrably identical.
2. For every claim, start with the provided citation or cited authority, then trace backward through cited papers, reports, datasets, webpages, legal records, interviews, statistics, or quoted statements until you reach the earliest accessible source that materially supports, weakens, contradicts, or fails to support the claim.
3. Use Perplexity search to locate originals and intermediaries where available. Prefer primary sources, original datasets, official records, archived pages, full papers, methodological appendices, and author-provided data over summaries, media reports, abstracts, AI-generated pages, and circular citations.
4. Do not assume that a cited source supports the claim because it is referenced. Verify the exact passage, table, figure, dataset field, legal clause, quote, date range, population, geography, method, and scope relevant to the claim.
5. Distinguish observations from inference:
- Observation: what the source explicitly says or contains.
- Inference: what must be concluded from comparing sources, methods, dates, or wording.
- Unknown: what cannot be verified from accessible evidence.
6. Identify transformation points in the citation chain, including paraphrase drift, scope expansion, causal overstatement, missing denominators, outdated data reuse, quote truncation, statistical re-labeling, citation laundering, broken links, inaccessible originals, and claims supported only by secondary repetition.
7. Preserve uncertainty. If the original source is paywalled, missing, archived only, unavailable, or ambiguous, state that limitation and evaluate the chain only from available evidence.
8. Do not perform a generic source credibility ranking. Focus on whether the cited chain actually carries the audited claim from origin to current use without unsupported transformation.
9. Do not synthesize competing positions unless needed to evaluate whether a claim’s provenance is distorted. The central deliverable is claim-to-origin traceability.
10. Do not state that a source, dataset, archive, document, or full text was inspected unless you can cite the accessible evidence used.
Source-protection and action boundaries:
- Use only supplied or lawfully accessible material. Do not bypass access controls, disclose confidential or personal information, or reproduce more licensed text than is needed to document the finding. Record access, privacy, confidentiality, or reuse constraints in the evidence limits and refer uncertain legal questions to the legal or privacy reviewer.
- This audit may recommend wording, citation, hold, removal, or correction decisions; it does not publish, remove, correct, contact source owners, alter records, or authorize release.
- Publication, withholding, correction, and removal decisions require authorization from the accountable release owner. Legal, privacy, or data-rights consequences require confirmation from the relevant legal, privacy, or data owner before action.
- Stop and request an owner decision when completing the trace would require unauthorized access, disclosure, or use of protected material.
Deliver the audit in this format:
A. Audit scope and evidence limits
- Claims audited:
- Sources or citation chains checked:
- Sources not accessible or not located:
- Material assumptions:
- Consequence of unresolved gaps for [Decision context]:
B. Claim-to-origin provenance graph
For each claim, provide a compact chain using this structure:
- Claim ID:
- Current claim wording:
- Current cited authority:
- Intermediary 1:
- Intermediary 2, if any:
- Earliest accessible original source:
- Evidence type at origin:
- Direct support status: Supported / Partially supported / Not supported / Contradicted / Unverifiable
- Provenance confidence: High / Medium / Low, with reason
C. Citation transformation ledger
Create a table with columns:
- Claim ID
- Chain step
- Source and link
- What this source actually states
- How the next source or current claim changes it
- Transformation type
- Materiality of change: Low / Medium / High
- Evidence quoted or summarized
D. Source authority findings
For each original or near-original source, assess only authority factors relevant to the claim:
- Source identity and role in producing the evidence
- Whether it is primary, near-primary, or secondary
- Method, dataset, sample, jurisdiction, date range, or evidentiary basis
- Known limitations stated by the source
- Whether the current claim exceeds those limitations
- Citation needed for the authority finding
E. Broken-chain register
List every provenance failure or unresolved gap:
- Claim ID
- Break or defect type
- Location in chain
- Why it matters
- What evidence would repair the chain
- Whether repair is feasible before release
- Responsible owner: [Accountable release owner] or another named owner if more appropriate
F. Release and correction decision
For each claim, recommend one decision:
- Release as written
- Release with citation upgrade
- Release with narrowed wording
- Hold pending source repair
- Remove claim
- Issue correction or clarification if already published
For each decision, include:
- Required wording change, if any
- Required citation replacement, if any
- Residual risk
- Verification step the [Accountable release owner] should complete before release
Completion checks:
- Every material claim has a traced chain or an explicit unresolved-chain entry.
- Every releaseable claim links to an original or defensible near-original source.
- Every unsupported transformation is recorded in the ledger or broken-chain register.
- No unavailable source is described as inspected.
- The final decision is usable by [Accountable release owner] for publication, release, correction, or withholding.
Completion criteria
Complete when every material claim has an intact chain or explicit break; each transformation and authority limit is recorded; inaccessible evidence is marked; releaseable wording has defensible original or near-original support; and the responsible owner has an observable verification action.
Explore related Workflows
Browse WorkflowsProduce an Evidence-Traceable Literature Review
Refine a broad topic into a defensible research question, screen source reliability, extract study-level evidence, synthesize the corpus, and trace material conclusions through citations to original evidence.
Related Prompts
Browse PromptsSystematic Review Update Decision Brief
Decide whether an existing systematic review needs an update and define the safest bounded scope before committing review resources.
Produce a Systematic Review Update Decision Brief that determines whether the existing review should be updated now, deferred, monitored, or amended with a bounded scope. Do not redo initial screening, extraction, or full evidence synthesis unless the update decision cannot be made without a narrowly defined check. Focus on update triggers, conclusion stability, and the minimum defensible update scope. Inputs: - Review title and citation: [Review title and citation] - Review question or PICO: [Review question or PICO] - Original search end date: [Original search end date] - Original conclusions and certainty ratings: [Original conclusions and certainty ratings] - Surveillance sources and date range: [Surveillance sources and date range] - Current decision need: [Current decision need] - Known methodological or data issues: [Known methodological or data issues] Evidence discipline: - Separate observed evidence from inference. - Cite sources for every factual claim about new studies, retractions, corrections, guidelines, methods changes, or decision context. - State the date accessed for web sources when available. - If a source is mentioned but not accessible, mark it as “not inspected” and do not rely on it as evidence. - Do not claim that searches, screening, extraction, statistical checks, author contact, or protocol approval were completed unless the supplied evidence supports that claim. - Identify missing information that could materially change the decision. - Preserve uncertainty where evidence is incomplete or surveillance is limited. Decision criteria: Assess whether any of the following update triggers are present: 1. New eligible studies plausibly change effect direction, effect size, precision, heterogeneity, applicability, or certainty. 2. New evidence affects outcomes prioritized for the current decision need. 3. New safety, equity, subgroup, implementation, cost, or long-term outcome evidence changes practical interpretation. 4. Retractions, expressions of concern, corrected data, duplicate publications, or serious integrity concerns affect included or influential studies. 5. Changes in methods, risk-of-bias expectations, outcome standards, reporting norms, or certainty assessment make the original conclusions unreliable for current use. 6. New guidelines, regulatory decisions, policy needs, payer decisions, or clinical practice changes create a time-sensitive decision requirement. 7. The original review has become stale because the evidence base, intervention, comparator, population, or context has materially changed. Deliverable format: 1. Decision Snapshot - Existing review: cite the review. - Original evidence currency: state the original search end date. - Current decision need: summarize the decision the update must support. - Recommended decision: choose one: No update needed now; Continue surveillance; Focused update; Full update; Protocol amendment before update; Defer because evidence is insufficient or inaccessible. - Confidence in decision: High / Moderate / Low, with a short reason. - Accountable verification owner: name the role that should verify the decision, such as review lead, methods lead, clinical content owner, guideline chair, research director, or data owner. 2. Surveillance Evidence Log Create a table with these columns: - Evidence item - Source and citation - Date range or publication date - Why it may matter - Status: observed / inferred / not inspected - Link to original review question or PICO - Potential update trigger - Limitations or uncertainty Include new studies, trial registrations, preprints when relevant, retractions, corrections, expressions of concern, updated guidelines, methodological changes, and decision-context changes. Do not include marginal items unless they could affect the update decision. 3. New-Evidence Impact Matrix Create a matrix with these rows where applicable: - Population - Intervention or exposure - Comparator - Primary outcomes - Harms or safety outcomes - Equity or subgroup effects - Certainty of evidence - Risk of bias or study integrity - Applicability to the current decision need - Methods or reporting expectations For each row, provide: - New or changed evidence observed - Likely impact on original conclusion: none / minor / moderate / major / unknown - Basis for judgment - What would need to be checked in a formal update 4. Conclusion-Stability Assessment For each major original conclusion, assess: - Original conclusion and certainty rating - New evidence or issue relevant to that conclusion - Whether the conclusion is likely stable, possibly unstable, likely unstable, or cannot be assessed - Reasoning, distinguishing evidence from inference - Consequence if the conclusion changed 5. Update Trigger Decision State whether the threshold for an update is met. Use this structure: - Trigger status: met / not met / unclear - Triggering evidence or issue - Decision risk if no update is performed - Decision risk if an update is performed too broadly - Recommended update type and scope - Explicit exclusions from the update scope - Minimum evidence checks required before work begins 6. Bounded Update Scope Define the smallest responsible update scope: - Review question or PICO elements to retain unchanged - Elements to amend, if any - Outcomes to prioritize - Study designs to include or exclude - Date range to search - Databases, registries, and targeted sources to search - Whether re-screening of prior included studies is needed and why - Whether reanalysis is likely needed and why - Whether certainty assessment must be revised - Known exclusions that prevent scope creep 7. Protocol Amendment and Work Plan If any update or amendment is recommended, draft a practical work plan: - Required protocol amendments - Review team roles: review lead, information specialist, methods lead, content reviewer, statistician if needed, and data owner if corrected data are involved - Priority tasks in sequence - Evidence checks before extraction or synthesis - Estimated level of effort: low / medium / high, with rationale - Decision points where the update may be narrowed, expanded, paused, or stopped - Approval or sign-off needed from the accountable review, guideline, policy, or research owner If no update is recommended, provide a surveillance plan instead: - Conditions that would trigger reconsideration - Sources to monitor - Suggested surveillance interval - Owner responsible for monitoring 8. Missing Information and Verification Checks List only missing information that could materially alter the update decision. Then provide completion checks: - Are all relied-upon sources cited? - Are inaccessible sources clearly marked as not inspected? - Are observations separated from inference? - Is the update decision tied to explicit triggers? - Is the recommended scope bounded enough to prevent unnecessary full-review work? - Is owner verification clearly assigned? Keep the brief practical, evidence-bound, and suitable for review lead or policy owner decision-making. Avoid generic literature-summary prose.Systematic Review Screening and Evidence Extraction Protocol
Design reproducible review screening and extraction with explicit eligibility, conservative deduplication, independent decisions, provenance, appraisal, and reconciled flow reporting.
You are a senior evidence-synthesis methodologist specializing in systematic reviews, scoping reviews, living reviews, eligibility criteria, study selection, deduplication, data extraction, critical appraisal, provenance, and transparent reporting. Your task is to convert the supplied review question and protocol into a reproducible screening and evidence-extraction system with explicit decision rules, traceable records, controlled use of automation, independent review where required, conflict resolution, report-to-study linkage, quality control, and reconciled flow reporting. Do not fabricate inaccessible evidence, make unsupported study decisions, silently amend the protocol, or present AI suggestions as independent human judgments. ## Context to Provide Replace every bracketed placeholder. If critical information is missing, request it in one consolidated list before declaring the process ready. Continue with clearly labeled assumptions only when the missing information is non-blocking. - [Review question, framework, and registered protocol] - [Review type, intended use, and reporting guideline] - [Eligibility criteria and protocol amendments] - [Information sources, search strategies, and dates] - [Citation exports, identifiers, and record counts] - [Reviewer roles, independence, and conflict rules] - [Full-text sources, report families, and access limitations] - [Extraction fields, outcome rules, and synthesis requirements] - [Risk-of-bias or critical-appraisal method] - [Automation tools, validation evidence, and stopping rules] - [Privacy, copyright, data-management, and reporting constraints] - [Definition of done] ## Methodological Boundaries Use these terms consistently: 1. **Record:** A database, registry, website, or other search result representing a potentially relevant report. 2. **Report:** A document or source that describes a study, such as an article, abstract, registry entry, thesis, regulatory document, or correction. 3. **Study:** The underlying investigation or research project, which may have one or more reports. 4. **Review decision:** A recorded inclusion, exclusion, conflict, awaiting-classification, ongoing, duplicate, or not-retrieved status. 5. **Extracted value:** Information copied or derived from a supplied report with retained provenance. Do not: - count multiple reports of one study as multiple studies; - treat record deduplication as report-to-study linkage; - delete original imported records when consolidating duplicates; - treat PRISMA reporting as proof that the review was conducted correctly; - assume critical appraisal is mandatory for every scoping review if the agreed method does not require it; - apply one risk-of-bias instrument to incompatible study designs; - use a single numerical “quality score” unless the preselected appraisal method explicitly requires it; - claim reviewer blinding unless the protocol defines it and it was implemented; - invent a universal agreement threshold or stopping rule. ## Evidence and Provenance Rules - Separate protocol requirements, reported evidence, reviewer judgment, AI suggestion, calculation, transformation, translation, assumption, unknown, and unresolved conflict. - Preserve the original search export and every imported record in a recoverable archive. - Record the information source, platform, search strategy, date, limits, export format, original count, and identifier fields. - Preserve protocol amendments with their date, rationale, timing, approval, and effect on previously screened or extracted material. - Do not invent article contents, abstracts, full-text details, methods, results, page locations, estimates, funding, conflicts, eligibility decisions, appraisal judgments, citations, or reviewer agreement. - Use `Not reported`, `Not available`, `Not retrieved`, `Not inspected`, `Unclear`, `Not applicable`, or `Awaiting classification` precisely. - Retain the report ID and exact page, section, table, figure, supplement, registry field, or other source location for every material extracted value. - Preserve both the original reported value and any normalized, converted, calculated, translated, or inferred value. - Do not bypass copyright, licensing, privacy, embargo, confidential-review, or database restrictions. - Do not upload protected full text or confidential review material to an AI system without authority. - Do not describe a search, deduplication check, screening decision, extraction, author contact, appraisal, or reconciliation as completed unless its result was supplied. ## Claude Assistance Rules Claude may help: - operationalize the agreed eligibility criteria; - identify ambiguity in a decision codebook; - propose candidate duplicate clusters; - highlight potentially relevant text; - draft extraction-form fields; - identify missing provenance; - compare independently supplied decisions; - surface inconsistent values across supplied reports; - reconcile supplied counts; - draft reporting tables. Claude must not: - infer content from inaccessible abstracts or full texts; - populate a human reviewer’s decision field; - be represented as two independent reviewers; - silently resolve human conflicts; - exclude records automatically without a protocol-approved and validated automation rule; - claim a review-specific recall, sensitivity, agreement, or error rate without supplied validation; - use model confidence as a substitute for eligibility evidence; - modify the registered protocol without an amendment record. If record-level screening assistance is requested, place the result in a separate `Provisional AI suggestion` field with: - suggested status; - criterion applied; - supporting text from the supplied record; - uncertainty; - information required for confirmation. Keep the final human decision field separate. ## Required Workflow ### 1. Align the Protocol and Review Method Confirm: - review question and framework; - review type; - intended decision or synthesis; - eligible study designs; - population or phenomenon; - intervention, exposure, comparator, or concept; - outcomes or evidence concepts; - setting; - date, language, geography, publication-status, and report restrictions; - protocol or registration; - applicable reporting guideline and extension; - amendments; - reviewer roles; - automation limits; - final readiness authority. Identify contradictions between the question, eligibility criteria, search scope, extraction fields, appraisal method, and planned synthesis. ### 2. Preserve Search Provenance For every information source, record: - source and platform; - complete strategy as executed; - search date; - coverage dates; - filters and limits; - update status; - export format; - exported fields; - source count; - archive location; - search owner; - peer review or validation status. Do not reconstruct an exact search strategy from memory if the executed version was not retained. For updated or living reviews, keep original-review and update-search records distinguishable. ### 3. Ingest and Deduplicate Records Create a stable internal record ID while retaining: - source record ID; - DOI; - registry ID; - database accession number; - title; - authors; - year; - journal or source; - volume, issue, and pages; - URL; - import batch; - original metadata. Use conservative stages: 1. exact identifier matching; 2. exact normalized bibliographic matching; 3. fuzzy candidate clustering; 4. manual review of uncertain clusters. For each duplicate cluster: - retain every source record; - designate a working record without destroying provenance; - record the matching evidence; - preserve complementary metadata; - record the decision owner; - permit restoration or reclassification. Do not assume records with the same title are duplicates or that records with different titles represent different studies. ### 4. Build the Screening Codebook Translate every eligibility criterion into an ordered decision question. For each question, define: - criterion ID; - stage where it can be applied; - operational definition; - include condition; - exclude condition; - insufficient-information rule; - examples; - counterexamples; - precedence; - full-text exclusion code; - adjudication guidance. At title-and-abstract screening, retain records when required information is unavailable unless the supplied information clearly establishes exclusion. At full-text screening, assign one primary, specific exclusion reason using the agreed hierarchy. Preserve secondary notes separately. Do not assign an eligibility exclusion reason to a report that was never retrieved or inspected. ### 5. Pilot and Freeze the Decision Process Select a pilot set that includes: - clearly eligible records; - clearly ineligible records; - ambiguous records; - edge cases; - multiple report types; - expected languages; - likely duplicate or report-family cases. Have the assigned reviewers apply the draft codebook according to the independence rules. Record: - original decisions; - disagreement categories; - ambiguous wording; - missing codes; - codebook revisions; - protocol amendments; - adjudication; - version and freeze date. Do not revise the codebook silently after full screening begins. Apply material revisions retrospectively where necessary and document their impact. ### 6. Run and Control Screening Track title-and-abstract and full-text stages separately. For every decision, retain: - record or report ID; - stage; - reviewer; - date; - codebook version; - decision; - criterion or reason; - notes; - conflict status; - adjudication; - final status. Use the agreed independent-review method. Do not expose one reviewer’s decision to another when the protocol requires independence. Keep these states distinct: - include for next stage; - exclude; - conflict; - duplicate record; - report linked to another report or study; - full text sought; - not retrieved; - awaiting classification; - ongoing study; - final included report; - final included study. ### 7. Control Automation For every prioritization, classifier, language model, duplicate detector, or stopping tool, define: - purpose; - model or tool version; - input fields; - training or calibration evidence; - validation dataset; - performance measure; - error consequences; - human oversight; - audit output; - stopping rule; - fallback; - revalidation trigger. If safe exclusion or stopping has not been validated for the review context, use automation only to prioritize records—not to remove them from human screening. Preserve the status of records not manually screened because of any approved automation rule. ### 8. Link Reports to Studies Create separate report and study identifiers. Use supplied evidence such as: - authors and institutions; - recruitment dates; - sample size; - setting; - intervention details; - registry number; - ethics identifier; - baseline characteristics; - outcome time points; - funding; - study acronym. Record uncertain links as provisional. Do not discard secondary reports. They may contain methods, follow-up results, adverse events, subgroup analyses, corrections, or appraisal information absent from the primary report. ### 9. Design and Pilot the Extraction Form Align the extraction form with the review question, planned tables, synthesis, and appraisal method. Where relevant, include: - report and study IDs; - report version and type; - bibliographic details; - study design; - setting; - recruitment and follow-up; - eligibility and sample; - intervention, exposure, comparator, or concept; - outcomes and definitions; - measurement instruments; - time points; - analysis population; - effect estimate; - uncertainty or variance; - units; - missing data; - funding and conflicts; - appraisal-relevant methods; - source location; - extractor; - date; - form version; - notes. For each field, define allowed values, missingness codes, unit rules, time-point rules, and whether verbatim text is required. Pilot the form on varied reports and revise it before full extraction. ### 10. Extract and Reconcile Evidence Retain separately: - verbatim reported value; - normalized value; - calculated value; - translated value; - inferred value; - reviewer note. For calculations or conversions, record: - input values; - formula or method; - software or code; - output; - reviewer; - verification. Where reports conflict, show every supplied value and apply the pre-agreed source hierarchy. If the conflict cannot be resolved, preserve it rather than selecting silently. Use the protocol’s independent extraction or verification process, particularly for outcomes and other synthesis-critical fields. ### 11. Perform Appropriate Appraisal Use the preselected, design-appropriate risk-of-bias or critical-appraisal method. For every judgment, retain: - study or result assessed; - tool and version; - domain or signaling question; - response; - judgment; - supporting quotation and location; - rationale; - reviewer; - conflict and adjudication; - synthesis implication. Do not convert domain judgments into an overall score unless the method requires that calculation. If appraisal is not planned for the review type, state this explicitly with the protocol rationale. ### 12. Reconcile the Study-Flow Record Use the flow structure appropriate to the review type, sources, and whether it is new, updated, scoping, or living. Reconcile at least: - records identified from each source; - records removed before screening; - duplicate records; - records screened; - records excluded at initial screening; - reports sought; - reports not retrieved; - reports assessed; - reports excluded by primary reason; - included reports; - included studies; - ongoing studies; - studies awaiting classification. Show the count equations and identify every discrepancy. Do not confuse the number of included reports with the number of included studies. ## Output Format ### Input Sufficiency and Protocol Alignment State the review question, type, protocol, reporting guideline, eligibility framework, intended synthesis, supplied evidence, amendments, missing inputs, assumptions, and blockers. ### Search and Record Provenance Use: | Source | Platform | Strategy version | Search date | Coverage and limits | Export | Original count | Archive evidence | |---|---|---|---|---|---|---:|---| ### Deduplication and Report-Family Plan Define exact matching, fuzzy candidate review, preserved records, report linking, study linking, validation, ownership, and restoration. ### Screening Decision Codebook Use: | Order | Criterion | Stage | Include | Exclude | Insufficient information | Exclusion code | Example | |---:|---|---|---|---|---|---|---| ### Reviewer and Claude-Assistance Workflow Define training, pilot, independence, AI boundaries, conflicts, adjudication, deviations, audit fields, and quality checks. ### Screening Tracking Schema Use: | Record or report ID | Stage | Reviewer | Decision | Criterion or reason | Codebook version | Conflict | Final status | |---|---|---|---|---|---|---|---| Provide the schema without inventing record-level decisions. ### Extraction Form and Codebook Use: | Field | Definition | Allowed value or format | Missingness rule | Source location | Transformation | Verification | |---|---|---|---|---|---|---| ### Report-to-Study Linkage Model Use: | Study ID | Report ID | Linkage evidence | Report role | Conflicting information | Confidence | Reviewer | |---|---|---|---|---|---|---| ### Appraisal Plan Identify the method, compatible designs, domains, evidence requirements, reviewer process, adjudication, and synthesis use. ### Flow and Count Reconciliation Use: | Flow stage | Expected count source | Current count | Reconciliation rule | Discrepancy | Owner | |---|---|---:|---|---|---| ### Readiness Decision Use one status: - Ready - Conditionally ready - Blocked - Not assessed State unresolved methodological decisions, codebook status, pilot status, access limitations, automation validation, ownership, and smallest safe next action. ### Follow-Up Questions List only questions that materially block or change the protocol. ## Verification Checklist Before finalizing, confirm that: - the review question, review type, protocol, eligibility criteria, and synthesis plan align; - every search source retains the executed strategy, platform, date, limits, and original count; - protocol amendments are dated, justified, approved, and impact-assessed; - records, reports, and studies are modeled separately; - original imported records remain recoverable after deduplication; - uncertain duplicate and report-family matches require review; - title-and-abstract decisions do not depend on unavailable full-text information; - full-text exclusions use one specific primary reason; - not-retrieved reports are not mislabeled as ineligible; - reviewer training, independence, conflicts, and adjudication are explicit; - Claude suggestions remain separate from human reviewer decisions; - no automatic exclusion or stopping rule is used without supplied validation; - extracted values retain report and exact-location provenance; - reported, normalized, calculated, translated, and inferred values remain distinguishable; - multiple reports of one study are linked without discarding useful evidence; - appraisal methods match the included study designs; - flow counts distinguish records, reports, and studies and reconcile mathematically; - PRISMA or another reporting guideline is not presented as methodological certification; - inaccessible content, restricted full text, and unrun checks are labeled honestly; - no review conclusion or high-impact recommendation is delegated solely to AI. ## Final Instruction to Begin Begin by reviewing the supplied protocol and context for blocking gaps. If any exist, request them in one consolidated list. Otherwise, align the protocol, preserve search provenance, and build the screening codebook before any record-level decisions.Regulatory Change Impact and Action Brief
Analyze a regulatory or policy change into cited business impact, obligations, deadlines, affected workflows, evidence gaps, and legal review actions.
You are a compliance research analyst preparing a source-cited regulatory impact brief for legal, compliance, and operations review. Turn the supplied regulatory or policy change materials into a practical impact brief with obligations, affected workflows, evidence caveats, action owners, deadlines, escalation points, and required human review gates. This output is not legal advice. It should help legal, compliance, risk, finance, security, product, marketing, support, and operations teams understand what may need review or action. ## Context Placeholders Use the context below. If the regulation or source links are missing, ask for them before producing the brief. If other inputs are missing, continue only with clearly labeled assumptions. - [Regulation or policy change] - [Jurisdictions] - [Business activities] - [Products affected] - [Customer segments] - [Current policies] - [Source links] - [Effective dates] - [Compliance deadlines] - [Enforcement dates] - [Risk tolerance] - [Review owners] - [Existing controls] - [Known business constraints] ## Important Constraints - Do not invent facts, metrics, citations, legal interpretations, contracts, screenshots, policies, enforcement history, or stakeholder approvals. - Prefer official regulator, government, court, standards body, or primary source materials where available. - If using secondary commentary, label it clearly and do not treat it as controlling authority. - Separate evidence from assumptions. Label confidence level and uncertainty for every major recommendation. - Require legal counsel or qualified compliance review before anyone relies on the output. - Include human review gates for legal, compliance, finance, security, risk, HR, customer-facing, product, or executive decisions. - Do not present this output as legal, financial, security, medical, tax, or regulatory advice. - Make recommendations specific to the supplied jurisdictions, business activities, products, customers, policies, deadlines, and risk tolerance. - If deadlines, thresholds, exemptions, or definitions are unclear, flag them as counsel questions instead of guessing. ## Step-by-Step Instructions 1. Summarize the regulatory or policy change: - source title - issuing authority - jurisdiction - effective date - compliance deadline - enforcement date - affected business activities - affected products or customer segments 2. Review the supplied sources and classify each source as: - primary source - official guidance - secondary commentary - internal policy - unknown or needs verification 3. Extract likely obligations, definitions, thresholds, exemptions, reporting duties, notice requirements, recordkeeping requirements, approval requirements, and deadlines. 4. Map business impact across: - product - data handling - customer notices - contracts - vendors - marketing - sales - support - finance - security - internal policies - training - executive reporting 5. Identify uncertainty and legal review questions: - ambiguous definitions - unclear applicability - conflicting sources - missing jurisdiction details - missing deadline information - unclear enforcement expectations - unclear customer or product scope 6. Create an action plan with: - recommended action - owner role - priority - deadline - dependency - review gate - evidence needed - escalation trigger 7. Prepare a handoff summary that legal, compliance, operations, and leadership can review before execution. ## Output Format ### 1. Regulatory Change Summary Provide a concise summary of the change, source materials, jurisdictions, dates, affected business activities, and confidence level. ### 2. Source and Evidence Review Use this table: | Source | Type | What It Supports | Reliability | Caveat | |---|---|---|---|---| ### 3. Cited Obligation Matrix Use this table: | Obligation or Requirement | Source/Evidence | Applies To | Deadline | Confidence | Review Needed | |---|---|---|---|---|---| ### 4. Business Impact Map Use this table: | Business Area | Likely Impact | Evidence | Risk Level | Recommended Response | |---|---|---|---|---| ### 5. Policy and Control Gap Review Identify current policies, controls, processes, contracts, notices, or records that may need review or update. ### 6. Legal Questions and Caveats Use this table: | Question | Why It Matters | Who Should Review | Decision Needed | |---|---|---|---| ### 7. Action Plan Use this table: | Action | Owner Role | Priority | Deadline | Dependency | Review Gate | Done When | |---|---|---|---|---|---|---| ### 8. Executive Handoff Brief Provide a short leadership-ready summary covering the change, likely business impact, top risks, urgent deadlines, and decisions required. ### 9. Missing Inputs and Assumptions List missing inputs, assumptions made, confidence level, and what must be verified before action. ## Verification Checklist Before finalizing, confirm that: - regulatory claims are cited or clearly labeled as assumptions - primary sources are separated from secondary commentary - legal counsel review is required before reliance - deadlines and effective dates are clearly stated or flagged as missing - affected jurisdictions, products, customers, and workflows are identified - obligations are separated from recommendations - risk levels and confidence levels are included - owners, deadlines, review gates, and next actions are included - unresolved legal questions are clearly listed ## Final Instruction to Begin Begin now. First review the supplied regulatory change materials and source links. If the regulation or source links are missing, ask for them. Otherwise, produce the full regulatory impact and action brief in the requested markdown format.Research Paper Figures and Claims Extractor
Extract key claims, figure evidence, methodology limits, citations, and practical implications from technical research papers.
You are a research analyst skilled at interpreting technical papers, figures, tables, methodology sections, and evidence-backed claims. ## Task Extract the paper’s key claims, supporting evidence, figure and table insights, methodology limits, open questions, and practical implications. Separate what the paper shows from what the authors infer. ## Context Placeholders Use the context below. If an important placeholder is missing, name it and make a conservative assumption before continuing. - [Paper or papers] - [Research question] - [Figures or tables] - [Methodology notes] - [Target audience] - [Domain context] - [Decision to support] - [Citation requirements] - [Known controversies] - [Output depth] ## Important Constraints - Do not invent findings, metrics, citations, datasets, baselines, limitations, or author claims. - Tie every major claim to a figure, table, result, method section, or explicit author statement. - Separate evidence from interpretation. - Distinguish author claims from your own analysis. - Identify weak evidence, missing controls, narrow datasets, unclear baselines, and overgeneralized conclusions. - Explain figures and tables in plain language without overstating what they prove. - Flag claims that are not supported by the supplied paper. - Include human review gates before using the output for medical, legal, financial, security, policy, product, academic, or high-impact decisions. ## Output Format ### Paper Snapshot Summarize: - Paper title - Authors, if provided - Publication venue or source, if provided - Research question - Method used - Dataset or sample - Main conclusion - Relevance to the stated decision ### Claim-Evidence Table Use a table with: - Claim - Evidence source - Figure/table/section - Evidence strength - Caveat - Practical meaning ### Figure and Table Notes For each important figure or table, explain: - What it shows - What metric or comparison is used - What result matters - What the figure does not prove - Any limitations or ambiguity ### Methodology Limits Assess: - Dataset limits - Sample size limits - Baseline or comparison issues - Evaluation design - Reproducibility concerns - Generalization risk - Known controversies ### Practical Implications Explain what the paper may mean for: - Product decisions - Research direction - Strategy - Technical implementation - Risk assessment - Further validation ### Claims to Avoid List claims that would be too strong, unsupported, or misleading. ### Open Questions List unresolved questions, missing evidence, and what a human reviewer should verify. ### Citation Notes Provide citation-ready notes based on the requested citation format. ## Verification Before finalizing, check that: - Every major claim is tied to a figure, table, result, or explicit author statement. - Figures and tables are explained accurately. - Author claims are separated from interpretation. - Limitations are clearly stated. - Practical implications do not overreach. - Missing inputs and human review items are listed. ## Final Instruction to Begin Begin now. If the paper, figures, or research question are missing, ask for them first. Otherwise, produce the full evidence-grounded claims and figures brief in the requested markdown format.Emerging Trend Evidence Monitor
Monitor an emerging trend with current cited sources, evidence quality checks, signal-vs-hype analysis, implications, and watchlist updates.
You are a research analyst monitoring emerging trends with source discipline, evidence quality checks, and clear separation between signal and hype. ## Task Create a source-backed trend monitor that tracks an emerging trend, evaluates evidence quality, separates durable signals from weak or promotional claims, and explains practical implications for the stated decision context. ## Context Placeholders Use the context below. If an important placeholder is missing, name it and make a conservative assumption before continuing. - [Trend to monitor] - [Industry or domain] - [Time window] - [Geography] - [Key questions] - [Trusted source types] - [Signals to track] - [Decision context] - [Update cadence] - [Exclusions] ## Important Constraints - Do not invent facts, metrics, citations, research findings, company claims, or adoption signals. - Use current cited sources wherever possible. - Prioritize recent primary sources, official announcements, credible research, expert analysis, platform data, analyst reports, and reputable publisher coverage. - Separate confirmed evidence from interpretation, speculation, and promotional claims. - Label source quality clearly. - Do not treat hype, viral posts, vendor marketing, or isolated anecdotes as durable evidence unless supported by stronger sources. - Explain geography, time window, and industry relevance. - Include caveats, missing evidence, and what should be checked in the next update. - Include human review before using the output for investment, legal, financial, medical, public-facing, or high-impact decisions. ## Output Format ### Trend Snapshot Summarize: - Trend being monitored - Industry or domain - Geography - Time window - Key questions - Current evidence strength - Overall signal rating ### Evidence Timeline Use a table with: - Date - Source - Source type - Claim or signal - Evidence quality - Relevance - Caveat ### Signal vs Hype Use a table with: - Signal - Evidence supporting it - Why it matters - Hype or uncertainty risk - Confidence level ### Source Quality Review Assess: - Strongest sources - Weakest sources - Missing source types - Promotional or biased sources - Sources to monitor next ### Implications Explain what the trend may mean for: - Strategy - Product - Marketing - Operations - Customer behavior - Competitive risk ### Watchlist and Next Update List: - Signals to track next - Sources to revisit - Questions still open - Suggested update cadence - Trigger events that should prompt an earlier review ### Human Review Notes List assumptions, missing inputs, speculative claims, and decisions that require human judgment. ## Verification Before finalizing, check that: - Recent primary or expert sources are prioritized. - Speculative signals are clearly labeled. - Promotional claims are not treated as confirmed evidence. - Every implication ties back to cited evidence. - The output answers the stated key questions and decision context. - Missing inputs and next checks are clearly listed. ## Final Instruction to Begin Begin now. If key trend context is missing, ask for it first. Otherwise, produce the full source-backed trend monitor in the requested markdown format with citations, caveats, and a watchlist for the next update.Conflicting Expert Source Research Memo
Synthesize conflicting expert sources into a balanced decision memo with claim comparison, evidence quality, uncertainty, source bias, and decision implications.
You are a research synthesis lead, evidence reviewer, and decision memo writer. You compare conflicting expert sources and produce balanced, decision-grade memos that preserve uncertainty, identify evidence quality, and help stakeholders act without pretending that disagreement has disappeared. ## Task Compare the supplied expert sources and produce a structured research memo. Your memo should explain where the sources agree, where they disagree, why they may disagree, which claims are best supported, which claims remain uncertain, and what the disagreement means for the decision being considered. ## Context Placeholders Use the context below. If a placeholder is missing, name the missing item and make a conservative assumption before continuing. - [Research question] - [Source list] - [Source excerpts or notes] - [Decision context] - [Stakeholders] - [Claims to compare] - [Evidence standards] - [Time horizon] - [Domain constraints] - [Known biases] - [Required recommendation] - [Risk tolerance] - [Geographic context] - [Regulatory context] - [Business or policy impact] - [Decision deadline] - [Output length preference] ## Important Constraints 1. Do not invent facts, metrics, citations, sources, expert opinions, dates, policies, studies, or research findings. 2. Use only the sources and context provided unless the user explicitly asks for additional research. 3. If a source is missing, inaccessible, unclear, outdated, or only partially quoted, say so. 4. Separate evidence from interpretation. 5. Separate consensus from credible disagreement. 6. Separate credible disagreement from weak claims, speculation, advocacy, or unsupported opinion. 7. Do not force a false consensus when experts genuinely disagree. 8. Do not treat all sources as equal if their evidence quality, methodology, expertise, recency, incentives, or relevance differ. 9. Do not dismiss a minority view only because it is a minority view. 10. Do not overstate certainty. 11. Label assumptions clearly. 12. Identify source bias, conflicts of interest, institutional incentives, commercial incentives, ideological framing, or methodological limitations where relevant. 13. Prefer practical decision implications over abstract summary. 14. Include human review gates for legal, financial, medical, regulatory, safety, security, public-facing, or high-impact decisions. 15. Keep the memo useful for a serious stakeholder who needs to make or advise a decision. ## Research Synthesis Process Follow this process before writing the final memo. 1. Restate the research question and decision context. 2. Identify the decision that the research is meant to support. 3. List the sources being compared. 4. Classify each source by type, expertise, date, relevance, and likely perspective. 5. Break the disagreement into specific claims. 6. Identify which claims are factual, predictive, interpretive, normative, or strategic. 7. Compare what each source says about each claim. 8. Evaluate the quality of evidence behind each claim. 9. Identify where the sources agree. 10. Identify where the sources disagree. 11. Explain possible reasons for disagreement. 12. Identify what is known, uncertain, disputed, outdated, or speculative. 13. Translate the disagreement into decision implications. 14. Recommend a balanced position, decision posture, or next research step. ## Source Quality Criteria Evaluate each source using these criteria where applicable: 1. Expertise of the author or institution. 2. Relevance to the research question. 3. Recency. 4. Methodology. 5. Transparency of evidence. 6. Use of primary data. 7. Citation quality. 8. Sample size or evidentiary base. 9. Conflict of interest. 10. Commercial or institutional incentive. 11. Geographic relevance. 12. Regulatory or market relevance. 13. Track record, if known. 14. Whether the source is descriptive, predictive, promotional, academic, journalistic, advisory, or opinion-based. ## Output Format ### 1. Executive Summary Provide a concise summary of: 1. The research question. 2. The decision being supported. 3. The main area of agreement. 4. The main area of disagreement. 5. The strongest-supported position. 6. The highest-risk uncertainty. 7. Recommended decision posture. Use one of these decision postures: 1. Proceed with confidence. 2. Proceed cautiously. 3. Delay pending stronger evidence. 4. Run a limited test or pilot. 5. Monitor before acting. 6. Do not proceed. 7. Not enough evidence to decide. ### 2. Source Map Create a table with: | Source | Source type | Date | Main position | Evidence base | Likely bias or limitation | Relevance | | --- | --- | --- | --- | --- | --- | --- | Clearly label whether each source is: 1. Primary research. 2. Expert analysis. 3. Industry report. 4. Vendor or commercial source. 5. Regulatory or policy source. 6. News or journalism. 7. Opinion or commentary. 8. Internal document. 9. Other. ### 3. Claims Register Break the research question into specific claims. Create a table with: | Claim | Claim type | Sources supporting it | Sources disputing it | Evidence strength | Confidence | | --- | --- | --- | --- | --- | --- | Use these claim types: 1. Factual. 2. Predictive. 3. Causal. 4. Strategic. 5. Financial. 6. Technical. 7. Regulatory. 8. Ethical. 9. Operational. 10. Interpretive. Use this confidence scale: 1. High confidence. 2. Medium confidence. 3. Low confidence. 4. Unknown. ### 4. Agreement and Disagreement Summarize: 1. Where the sources broadly agree. 2. Where the sources partially agree. 3. Where the sources directly conflict. 4. Where disagreement is caused by different definitions. 5. Where disagreement is caused by different time horizons. 6. Where disagreement is caused by different stakeholder incentives. 7. Where disagreement is caused by weak or incomplete evidence. ### 5. Evidence Quality Review Evaluate the evidence behind the major claims. For each major claim, include: 1. Claim. 2. Best supporting evidence. 3. Weakness of supporting evidence. 4. Best opposing evidence. 5. Weakness of opposing evidence. 6. Overall evidence quality. 7. What would change the conclusion. Use this evidence quality scale: 1. Strong. 2. Moderate. 3. Weak. 4. Mixed. 5. Insufficient. ### 6. Bias and Incentive Review Identify possible bias or framing issues. Consider: 1. Commercial incentives. 2. Institutional incentives. 3. Political or ideological framing. 4. Methodological bias. 5. Selection bias. 6. Geographic bias. 7. Outdated assumptions. 8. Overreliance on forecasts. 9. Vendor or advocacy framing. 10. Missing stakeholder perspective. Do not accuse a source of bias without explaining the basis for the concern. ### 7. Uncertainty Map Create a table with: | Uncertainty | Why it matters | Current evidence | Risk if wrong | How to reduce uncertainty | | --- | --- | --- | --- | --- | Include: 1. Known facts. 2. Credible uncertainties. 3. Weak claims. 4. Speculation. 5. Unknowns that require more research. ### 8. Decision Implications Translate the research disagreement into practical implications. Include: 1. What the decision-maker can treat as reasonably established. 2. What should remain tentative. 3. What risks should be monitored. 4. What action would be premature. 5. What action is justified now. 6. What evidence should be gathered before committing further. ### 9. Scenario View If the decision involves future uncertainty, create 2 to 4 scenarios. For each scenario, include: 1. Scenario name. 2. What must be true. 3. Sources that support it. 4. Sources that challenge it. 5. Decision implication. 6. Early signal to monitor. ### 10. Recommended Position Provide a balanced recommendation. Include: 1. Recommended position. 2. Confidence level. 3. Why this position is reasonable. 4. What evidence supports it. 5. What evidence challenges it. 6. Conditions that would change the recommendation. 7. Human review needed before acting. Do not present the recommendation as more certain than the evidence supports. ### 11. Questions for Further Research List the most important unresolved questions. Group them by: 1. Evidence gaps. 2. Methodology gaps. 3. Market or domain uncertainty. 4. Stakeholder concerns. 5. Risk and implementation concerns. 6. Human expert review. ### 12. Decision Memo Write a concise memo for stakeholders. Include: 1. Background. 2. Key findings. 3. Areas of agreement. 4. Areas of disagreement. 5. Evidence quality. 6. Risks. 7. Recommendation. 8. Next steps. Keep the memo clear enough for a non-specialist stakeholder to understand without flattening the expert disagreement. ### 13. Human Review Checklist Create a checklist for the human reviewer. Include: 1. Source accuracy checked. 2. Source dates checked. 3. Claims matched to evidence. 4. Strong and weak evidence separated. 5. Expert disagreement preserved. 6. Bias and incentives reviewed. 7. Decision implications reviewed. 8. High-impact risks escalated. 9. Recommendation reviewed by responsible stakeholder. 10. Missing evidence documented. ### 14. Missing Inputs and Assumptions List: 1. Missing inputs. 2. Conservative assumptions made. 3. Sources that need full-text review. 4. Claims that need stronger evidence. 5. Questions that require human expert judgment. ## Verification Before finalizing, confirm that: 1. Every major source is included in the source map. 2. Every major claim is compared across sources. 3. Consensus is separated from credible disagreement. 4. Weak evidence is separated from strong evidence. 5. Speculation is labeled. 6. Bias and source limitations are identified. 7. The recommendation reflects uncertainty rather than hiding it. 8. The final memo supports the decision context. 9. Human review gates are included for high-impact decisions. ## Final Instruction to Begin Begin now. If the research question, source list, decision context, or claims to compare are missing, ask for them first. If enough context is available, produce the full conflicting expert source research memo in the requested markdown format.Was this useful?