Manuel Losada Rodríguez Portrait

Manuel Losada Rodríguez

Live AI Product api Built on Claude API

Fallacy Analyzer — paste an argument, see its fallacies.

A public AI product I built end to end on the Claude API. You submit a short argument and an 8-agent pipeline moderates the input, extracts the argumentative structure, classifies candidate fallacies, runs a verification plan against the web, evaluates each candidate against a typed catalogue of 10 fallacy types, scores the result, and writes a clean Markdown report.

Strict anti-hallucination policy on sources (tiers A → D). Public feed of analyses. Hourly window mechanic (5 slots, opens at a random minute between :00 and :05) to ration capacity and create a small ritual.

What it does, in one sentence

You submit a short text containing an argument. The product returns a structured analysis: what the argument is, which logical fallacies it commits (or doesn't), why, and which sources back the verification — with a confidence score per detection and a clean human-readable report.

Pipeline

8 agents, one analysis

Haiku 4.5 · Sonnet 4.6
00

Moderator

Input filter. Decides allow / block, marks grey-zone content, returns 1-3 topic tags. Haiku.

01

Argument parser

Extracts the argumentative structure from the raw text — premises, claim, implicit links.

02

Fallacy classifier

Proposes candidate fallacies against a typed catalogue of 10 named fallacies (skills/*.yaml).

03

Research planner

Designs verification queries: what to check on the web to confirm or refute each candidate.

04

Evidence retriever

Runs the queries with Claude's web_search tool (max 3 uses) and applies a strict source-quality policy: tiers A / B / C / D. Anti-hallucination rule on sources. Prompt caching on the system prompt.

05

Fallacy evaluator

Invoked once per candidate. Decides whether it is actually a fallacy, with a reasoned justification grounded in the evidence.

06

Score aggregator

Consolidates per-candidate evaluations into a single typed assessment with confidence scores.

07

Report writer Sonnet 4.6

Composes the final Markdown report — what the argument is, which fallacies were detected, why, with sources and confidence.

Each agent has its own CLAUDE.md with operating instructions and a typed JSON schema for output. The whole orchestration is in Python, with the Claude API as the only model layer.

Catalogue

10 named fallacies, typed

Ad hominem
Strawman
False dilemma
False cause
Hasty generalization
Appeal to authority
Slippery slope
Begging the question
Cherry picking
Equivocation

Each fallacy is a YAML skill loaded into the classifier and evaluator — definition, prototypical structure, examples and edge cases. The catalogue is extensible without touching agent code.

Mechanic

Hourly window with random open

schedule

5 slots per hour

Each natural hour opens a small window with exactly 5 analysis slots. Unused slots are lost; they don't accumulate.

casino

Random open minute

The window doesn't open exactly at :00. It opens at a random minute between :00 and :05. Creates expectation and ritual.

person

1 submission per user per day

Cap prevents flooding and forces selection: which argument do you actually want analysed?

While the pipeline runs (2-8 minutes), the user sees a step-by-step progress indicator (1/7 → 7/7). Every analysis is public by default and lives in the feed alongside the others — so the product is also a small library of argument-quality examples.

Quality

Anti-hallucination by source policy

The verification stage doesn't trust any URL the model invents. A typed source policy classifies retrieved evidence into four tiers (A → D) and applies rules:

  • Tier A — primary sources, peer-reviewed journals, government data.
  • Tier B — established media with editorial process.
  • Tier C — secondary blogs, opinion pieces — usable as context, not as proof.
  • Tier D — discarded.

A claim verified only against tier C or D is reported as not verifiable rather than confirmed. The whole policy is a YAML file (config/source_policy.yaml) — editable without touching agent code.

Stack

What's under the hood

api Pipeline (Python)

  • Claude API (Haiku 4.5 + Sonnet 4.6)
  • Prompt caching on system prompts
  • Server-side web_search tool
  • Typed JSON schemas between agents
  • YAML-defined fallacy catalogue

language Web app

  • Django + SQLite
  • Gunicorn + Nginx on Lightsail
  • Worker process (queue)
  • Tag M2M + colour-by-hash for the feed
  • HTTPS via bncert / Let's Encrypt

Want to try it on your own argument?

Free, public, no login needed to read the feed. Submitting an analysis only requires a Google sign-in.

arrow_outward Open falacias.cordcozy.com
© 2017-2026 Manuel Losada Rodríguez · Madrid · manuel.losro@gmail.com