How we produce a report.
Every report that leaves this platform follows the same discipline. We publish the method because methodology is the only thing that separates intelligence from opinion.
1. Sources
We prioritise primary sources — regulator publications, statute, case law, official statistics, exchange filings, central-bank releases, and credible trade press. Secondary commentary is used to sharpen framing, not to establish fact. Every material claim carries a citation to its source, dated at point of retrieval.
2. AI-assisted drafting
We use large language models (Claude by Anthropic) to accelerate research synthesis and structure. The model is never the author of record. It produces a structured draft against a controlled prompt taxonomy that enforces reference hygiene, currency of data, and the absence of hallucinated statistics. Every section is logged with the model version and prompt hash used to produce it.
3. Senior human review
No report is published without sign-off by a human reviewer with professional background in the relevant risk domain. Reviewers verify citations, correct framing, remove generalities, and cut anything that sounds like opinion masquerading as analysis.
4. Citation discipline
If we can't cite it, we don't state it. Claims are anchored to a numbered reference list. Where we rely on estimates, ranges, or structural reasoning rather than hard data, we say so in plain text. Fabricated citations are the worst failure mode of AI-assisted research; we explicitly validate against fabrication at multiple points in the pipeline.
5. Dating and freshness
Every report carries a production date on the cover. Reports in fast-moving domains (sanctions, tech, crypto, political) are reviewed on a shorter cycle than slower-moving ones (trust law, probate). We flag when a report is stale and queue it for refresh before re-selling.
6. What we won't do
- We won't publish without review.
- We won't accept paid placement inside reports.
- We won't name specific recruiters, advisory boutiques, or law firms inside reports unless context demands it and the mention survives review.
- We won't invent statistics. If the data doesn't exist, we say so.
7. Corrections
If you spot an error, write to support@theriskagent.com. Substantive corrections are made to the live report and noted with the change date. We don't silently edit.
Full policy details
Read the editorial policy, sources and citations policy, and AI and agentic update policy for the full documented approach.
Browse published reports