Instruction-like passages
Supported text patterns that appear to redirect the AI, alter the task or influence the resulting analysis.
Research document security
Reports, papers and source packs can move quickly from download to project context. .mdSiren is designed to add a review step before outside material influences extraction, synthesis or analysis.
Product coming soonThe research problem
An AI-assisted research project may treat uploaded documents as evidence while also responding to instruction-like text inside them. That creates a risk when sources come from publishers, downloads, partners or shared folders.
Once a source is retained in project context, it may shape later summaries, comparisons and drafts—not only the first response.
Learn how document instructions can persistResearch intake
The goal is a consistent decision for every external source, even when the material and publisher change.
Supported text patterns that appear to redirect the AI, alter the task or influence the resulting analysis.
Downloads, attachments and shared files need the same intake discipline even when they look authoritative.
A source added once may be consulted across later questions, summaries and research outputs.
A safer research workflow
Collect broadly if the work requires it, but make entry into the AI project a deliberate step.
A clean scan is not evidence that a source is accurate, unbiased or methodologically sound. Research quality still requires source evaluation and human judgement.
Before analysis
.mdSiren is designed to support the intake boundary. It does not determine whether a source deserves evidential weight.
.mdSiren is coming soon. The public website describes the intended review pattern while the final product contract is verified elsewhere.
Before the project
Create one repeatable intake decision for reports, papers and source packs before they influence AI-assisted research.