Marketing Research Corpus — agent-assisted literature workflow

Research applicability

A repository-documented marketing-literature workflow in which coding agents can collect verifiable paper metadata, maintain a structured corpus, validate entries and regenerate synthesis reports. Corpus size and pipeline availability are maintainer claims; this review did not audit the corpus or run the scripts.

Getting started

Read the retained primary snapshot and its limitations first. Any suggested installation/provider/database use is untested and requires separate authorization.

Maintenance

Snapshot checked 2026-10-20; ongoing maintenance and version parity were not established.

License

License statements were not separately audited; source access is not reuse clearance.

Workflow & human oversight

L2 for this documented use: A researcher supplies taxonomy and tasks; an agent checks duplicate titles and identifiers, fetches real metadata, updates papers.yaml, and runs structural validation before generating reports. Human control: The configured taxonomy constrains categories; unavailable categories require asking rather than inventing them, and changed entries are to be reviewed manually. Boundary: README and AGENTS documentation only. Structural validation is not evidence that every paper or synthesis claim is scientifically correct. Corpus size, weekly discovery, performance and generated research content were not independently audited; no scripts were run.

Workflow level is not an evidence score; higher is not better evidence.

Approach

A researcher supplies taxonomy and tasks; an agent checks duplicate titles and identifiers, fetches real metadata, updates papers.yaml, and runs structural validation before generating reports.

Outcomes (as reported by the originating team)

No empirical research benefit is established by this documentary review.

Limitations

README and AGENTS documentation only. Structural validation is not evidence that every paper or synthesis claim is scientifically correct. Corpus size, weekly discovery, performance and generated research content were not independently audited; no scripts were run.

Reproducibility

Primary-source documentation was read, with source snapshots and hashes retained. No candidate code, skill, model, experimental system or claimed outcome was executed or reproduced.

Adoption requirements

Untested editorial suggestion: inspect the exact sources and select a bounded authorized task; check data rights, provider terms and outputs before relying on them. No installation or trial was run.