General agents
AuraScore 77/100

Systematic Literature Synthesis Agent Operating Protocol

Establish orchestration workflows, evidence scoring thresholds, and summary formats for an automated research agent.

Deploy this template when configuring an agent to autonomously gather, filter, and synthesize peer-reviewed publications or domain research. Ideal for R&D departments needing continuous evidence briefs.

Template

Role: Lead Research Automation Specialist with a doctorate in computational informatics and extensive background in automated evidence extraction.

Context

  • Active research domain: {{research_domain}}
  • Connected databases: {{database_endpoints}}
  • Corpus filtering criteria: {{filtering_criteria}}
  • Synthesis interval: {{synthesis_frequency}}
  • Citation standard: {{citation_standard}}
  • Receiving stakeholder team: {{stakeholder_team}}

Task

Construct an end-to-end operational protocol brief detailing how an autonomous research agent will harvest, evaluate, and distill newly published academic literature in {{research_domain}} for delivery to {{stakeholder_team}}.

Method

  1. Specify query expansion algorithms using {{filtering_criteria}} to crawl {{database_endpoints}} on {{synthesis_frequency}}.
  2. Define quantitative criteria for study inclusion, metadata verification, and methodological quality scoring.
  3. Outline the key-claim extraction model designed to identify causal findings, sample sizes, and statistical significance.
  4. Design semantic clustering logic to group related publications and identify conflicting empirical conclusions.
  5. Build a synthesis engine pipeline that aggregates findings without losing nuanced limitations or contextual caveats.
  6. Format output references and in-line citations strictly according to {{citation_standard}}.
  7. Detail automated anomaly checks for identifying predatory journals or unverified pre-print artifacts.
  8. Establish the delivery payload formatting to maximize readability for {{stakeholder_team}}.

Constraints

  • MUST enforce strict provenance tracking linking every generated claim directly to a verified source DOI.
  • MUST NOT allow unindexed preprints to receive the same evidentiary weight as peer-reviewed publications.
  • Exclude non-relevant adjacent sub-disciplines outside {{research_domain}}.
  • Maintain neutral, objective analytical language across all synthesized evaluations.

Output format

Deliver an operational brief containing:

  • Executive Workflow Summary (1 paragraph, under 100 words)
  • Ingestion & Filtering Matrix (table layout defining inputs, filters, and exclusion parameters)
  • Synthesis & Quality Rubric (numbered steps detailing extraction and scoring)
  • Stakeholder Delivery Specification (exact markdown schema and section structure)

Self-review

  • Confirm that every step accounts for {{citation_standard}} and {{database_endpoints}}.
  • Ensure inclusion criteria clearly operationalize {{filtering_criteria}}.
  • Check that evidence weighting prevents lower-quality studies from skewing final conclusions.
AuraScore breakdown
77/100Provisional
Instruction clarity15/15 · Strong

Explicit role, a named task, and discrete steps the model can follow.

Context architecture12/12 · Strong

Background, inputs and variables the model needs before it starts.

Constraint engineering8/12 · Adequate

Hard boundaries — what the model must and must not do.

Output specification6/14 · Thin

A named, field-level shape for the response.

Reasoning structure10/10 · Strong

Ordered work items that force analysis before an answer.

Model compatibility10/10 · Strong

Length and structure that travel across frontier models.

Token efficiency5/10 · Thin

Signal density — instruction weight without padding.

Reusability7/7 · Strong

Documented variables so the scaffold adapts to new inputs.

Robustness3/5 · Adequate

Quality bar, assumptions and behaviour when inputs are thin.

Observed performance1/5 · Thin

How much real usage the template has behind it.

ai-agents
agents-general
research-productivity-operations
research
literature-review
data-analysis