Lenstrum

How Lenstrum Works

Our methodology, our accuracy, and our limitations — published openly.

How bias and framing analysis works

Lenstrum extracts text from a URL and passes it to Claude (Anthropic) using a structured non-partisan prompt. The prompt asks Claude to identify ideological lean, key framing choices, and perspectives that are absent from the coverage. Results are rated Left, Centre, or Right with a confidence level (High, Medium, Low). Lenstrum analyses individual pieces of content — not outlet reputations. The same outlet can produce Centre-rated and Right-rated content on the same day, depending on the specific piece.

How AI involvement detection works

The AI Involvement tab estimates the probability that a piece of content was generated or significantly assisted by AI. Lenstrum looks for structural signals common in AI-generated text: consistent paragraph length, explicit transitional phrases, vocabulary patterns, and a particular kind of fluency that differs from human writing. For video content, synthetic voiceover patterns are also flagged. Results are expressed as a probability score (0–100%) and always framed as analysis, not verdict — AI detection is an inexact science and Lenstrum treats it accordingly.

How source context works

The Source Context tab draws on Brave Search to find related coverage of the same story from across the political spectrum. For known publishers, Lenstrum references AllSides and Ad Fontes Media bias ratings. For independent creators and social accounts, Lenstrum classifies the account type based on content patterns and stated editorial position. Source context is designed to show you what else is being said about the same story — not to endorse any outlet.

Accuracy & validation

We built a 100-item validation corpus to test Lenstrum's analysis engine before public launch. The corpus spans five categories: political articles (40 items), political YouTube videos (25 items), non-political YouTube (15 items), non-political articles (10 items), and centre/balanced sources (10 items). Results were validated against AllSides and Ad Fontes Media ratings where available, and against internal reference ratings for content types with no established third-party benchmark.

Lenstrum performs strongest on political content — 95% accuracy on political articles and 100% on political YouTube, validated against AllSides and Ad Fontes. Non-political content (theology, economics, philosophy, science) is a newer category with no published third-party benchmark; results are reported as v1 baseline data. High-confidence outputs match at 92.9% — when Lenstrum is sure, it is right the vast majority of the time.

Known limitations

• →Lenstrum rates individual content, not outlet reputation. A single outlet can produce content rated differently on the same day.
• →AllSides and Ad Fontes rate outlets and channels, not individual articles or videos. Direct comparisons are approximate.
• →YouTube analysis depends on available transcripts. Videos with poor or missing captions are flagged as Low confidence.
• →Non-political content analysis (science, theology, economics, philosophy) is a novel category with no published accuracy benchmark. Results should be treated as directional.
• →AI involvement detection is probabilistic, not definitive. Lenstrum expresses results as probability scores, never verdicts.

What comes next

The corpus will be expanded to 200 items post-launch using real URLs submitted by users. A user feedback loop — thumbs up/down on every result — will be incorporated as an additional validation signal. The corpus will be re-run after any significant prompt change. We will publish updated accuracy figures here as the methodology evolves.