Apps

🧪 This platform is in early beta. Features may change and you might encounter bugs. We appreciate your patience!

Why TellDear Exists

Because fact-checking tells you what is wrong. We want to understand how and why reasoning fails.

The Problem

Every day, billions of arguments are made — in boardrooms and parliaments, on social media and in news broadcasts, in advertising and in private conversations. Some are sound. Most are not. And the gap between the two is where manipulation lives.

Fact-checkers tell us whether a claim is true or false. That's important. But it doesn't explain why a flawed argument felt convincing. It doesn't reveal the structure of the deception. It doesn't name the technique being used.

Consider this statement:

"Millions of parents are concerned about vaccines. If that many people worry, there must be something wrong. Scientists who disagree are obviously funded by pharma."

A fact-checker would label this "misleading." But inside these three sentences hide at least four distinct reasoning flaws: an argumentum ad populum, a hasty generalization, an ad hominem, and a genetic fallacy. Each exploits a different cognitive weakness. Each requires a different defense.

TellDear exists because naming the error is the first step to disarming it.

What We Do Differently

Fact-Checking

  • "Is this claim true or false?"
  • Binary verdict: true / false / misleading
  • Checks the content
  • Requires domain expertise per claim

Reasoning Analysis (TellDear)

  • "How is this argument constructed?"
  • Identifies specific techniques & patterns
  • Checks the structure
  • Applies universally across domains

We don't judge whether a claim is true. We examine whether the reasoning behind it is valid. A true conclusion can still be supported by terrible logic. A false conclusion can be wrapped in seemingly perfect argumentation. Both deserve scrutiny.

Where This Matters

Politics & Policy

Campaign speeches, parliamentary debates, policy proposals — dissect the rhetoric behind political positions. Identify when leaders use emotional manipulation instead of evidence.

Corporate & Business

Board presentations, strategy memos, investor pitches — reveal when business arguments rest on faulty logic, cherry-picked data, or false dilemmas.

Media & Journalism

Editorials, opinion pieces, news framing — go beyond what is said to analyze how it is said. Detect loaded language, false balance, and narrative manipulation.

Education

Teach students not just what to think, but how to evaluate thinking. A searchable taxonomy of 535+ reasoning patterns as a teaching resource.

Social Media

Viral posts, threads, comment wars — identify the manipulation techniques that make misinformation spread. Understand why certain arguments feel compelling despite being hollow.

Personal Discourse

Everyday conversations, family arguments, negotiation — recognize when you or others fall into cognitive traps. Better reasoning starts with self-awareness.

The Landscape: Who Else Is Working on This?

TellDear is part of a growing movement that goes beyond fact-checking into structural analysis of arguments. Here's who else is working in this space:

Argument Mining & Academic Research

Argument Visualization & Mapping

Media Bias & Framing Analysis

AI-Powered Analysis & Education

Where TellDear Fits

Most existing tools focus on one slice: logical fallacies or propaganda or media bias. TellDear integrates all of these into a single, machine-readable taxonomy with 535 aspects across 6 dimensions.

What makes TellDear unique

  • 1. Comprehensive — 6 dimensions covering fallacies, biases, propaganda, statistics, argumentation schemes, and discourse mechanics in one system.
  • 2. Machine-readable — Every aspect has binary verification steps that both humans and AI can evaluate systematically.
  • 3. Formally grounded — First-Order Logic patterns and SMT verification provide mathematical proof, not just subjective judgment.
  • 4. Interactive — Not just a reference book, but a living platform with deep analysis, knowledge graph, and AI-powered text scanning.
  • 5. Quote-level precision — The analyzer identifies exactly which sentences in a text contain which reasoning flaws, with detailed explanations.

Start Analyzing

The best defense against bad reasoning is the ability to recognize it. Try the analyzer, explore the taxonomy, understand the patterns.