Skip to content
Log in

Research Agent System Prompt

Generates a research agent prompt that cites sources, states its confidence, separates fact from inference, and refuses to fill gaps with plausible invention.

0

Share this prompt

Free — no card needed

Create a free account

to open Research Agent System Prompt — and the other 364 prompts across 21 categories.

We store your email address to send these. We never sell it or pass it to advertisers. Withdraw at any time. Privacy Policy.

Already have an account?

CategoryAI AgentsForAnalysts, Developers, ConsultantsTested onClaudeChatGPTGemini

Running it, start to finish

  1. Describe the research scope and what sources it can reach.
  2. Run all three verification tests before relying on it.
  3. Spot-check citations on the first few real answers.

What you get back

The output this produces, every time.

  • Forbids invented citations explicitly, which is the failure that makes research agents dangerous rather than unhelpful.
  • Separates what a source says from what the agent inferred, labelled.
  • Includes an unanswerable test question, since handling that well is the real quality bar.

Getting better results

Where this usually goes wrong, and how to avoid it.

  • Run the unanswerable question first. How the agent handles a question it cannot answer tells you more than a dozen it can.
  • Keep the confidence labels. An answer where everything reads with equal certainty cannot be triaged by the person acting on it.
  • Spot-check the citations. Verify a few sources actually say what is claimed. This is where a well-written answer quietly fails.

More AI Agents prompts

All AI Agents

Written for The AI University. Every prompt in this library is original work — authored, tested and revised here, not collected from elsewhere. 365 of them, free with an account.