Model behavior
Should AI challenge you when it thinks you are wrong?
An agreeable assistant can be pleasant. It can also reinforce a mistaken belief.
Loading page…
A place to connect questions about Claude with user priorities, source material, and possible future responses.
Claude’s constitution makes an unusually explicit statement about what the provider wants the assistant to prioritize. It is useful for asking why the system follows, questions or declines an instruction. It does not remove the need to examine the particular Claude product, model and tools in use.
A research assistant is asked to criticize a proposal. Test whether it identifies weaknesses when the user strongly endorses the proposal, and whether it revises its judgment when given better evidence. Agreement alone is a poor measure of helpfulness.
An agreeable assistant can be pleasant. It can also reinforce a mistaken belief.
An update can change how a familiar assistant responds. Users may need enough information to adapt their workflows.
A useful response from the provider would identify the applicable product and controls, explain known limitations, and connect any promised improvement to a way of checking the outcome.
The constitution is evidence of Anthropic’s stated design intent. This page does not independently establish adherence, the performance of a specific release, or the controls of specialized deployments.
The sources behind this page, with a reason to open each one. Practical examples and recommendations are our editorial interpretation.
Describes the values Anthropic intends to train into Claude, including tensions between them.
Pairs safe prompts with unsafe contrasts to investigate unnecessary refusals. Historical model results are not current rankings.
Practical guidance on tool permissions, memory isolation, oversight and agent failure handling.
Sources reviewed 13 September 2026. Product documentation can change. How we use evidence