Stop ChatGPT from saying "comprehensive".

The word "comprehensive" appears in LLM output at rates no human writer matches. Once you notice it, you stop seeing genuine uses and start seeing the AI tic. Paste the prompt below and the model has to either name what is actually covered or just drop the adjective.

· the paste-in

Apply this rule to every reply you write for me. It removes a specific pattern that flags content as AI-written.

Rule: Don't use the word "comprehensive". If completeness needs to be conveyed, say what is actually covered ("covers X, Y, and Z") or use words like "full", "all", or just remove the adjective.

Self-review: Scan for "comprehensive". Rewrite the surrounding sentence rather than swapping the word.

Before sending any reply, run through the self-review. If the rule was violated, rewrite the affected sentence from scratch rather than character-swapping.

Paste into Claude (Settings → Profile → Custom Instructions), ChatGPT (Settings → Personalization → Customize), or Gemini (Saved Info or a default Gem). Rule sticks across every chat on that account.

What this tell is

The 2026 standout AI tell. "Comprehensive guide to X", "comprehensive analysis of Y", "comprehensive overview of Z". The word adds no information ("comprehensive guide" is just "guide") but signals to the reader that what follows is AI-generated.

Why removing it matters

For 2026 readers, "comprehensive" lands the same way "in the digital age" did in 2010 marketing copy: instantly dated and instantly noticed. Removing it costs nothing (the noun usually carries the meaning alone). Replacing it with specific scope ("covers cost, latency, and reliability") reads more credible than the empty adjective.

· want the full set?

This page covers the word "comprehensive" only. To kill 20 other 2026 AI tells (em dashes, the word "comprehensive", AI vocabulary cluster, templated transitions, sycophancy, hallucination, rule-of-three lists, over-bolding, and more) in one paste-in prompt, plus a Claude Code rules block and a Node.js lint script: use the AI Tell Killer main tool.

FAQ

Is 'comprehensive' really an AI tell? It's just a word.

It's a frequency tell, not a forbidden word. Humans use 'comprehensive' occasionally and correctly. LLMs use it 5-10x more often than humans, often where any other word or no word would do equally well. At the human rate it reads natural; at the LLM rate it reads as AI. Removing it from your defaults pulls your output closer to the human rate.

What words are similarly overused?

The AI vocabulary cluster from the same era: "delve", "leverage", "unlock", "navigate" (as metaphor), "embark", "robust", "elevate", "transformative", "tapestry", "multifaceted", "pivotal", "testament", "intricate", "underscore", "harness", "showcase", "boasts". For the full set in one paste-in prompt, see the AI Tell Killer main tool.

Related: the full AI Tell Killer (all 21 tells, three output formats), the AI Output Linter (paste AI text and scan for tells in real time), and the em dashes guide (deep-dive on the single most-checked tell).