Source Intelligence

DisclaimerUnofficial, and not affiliated with Anthropic. Nearly all of this is read straight out of what ships: npm bundles, captured prompts, published docs. Anthropic's own notes go in verbatim, marked as theirs. The rest is my reading, and every entry carries the strings behind it. If one looks wrong, vote it down and say why.

All of v2.0.65 Home All releases olderv2.0.64 v2.0.66newer
Claude Code v2.0.65

Prompt Suggestions Enhancement

What: After task completion, Claude now suggests the next logical prompt based on conversation context. Details:

  • Suggestions appear as placeholder text in input field (press Enter to accept)
  • Filters inappropriate suggestions (too long, gratitude responses, etc.)
  • Telemetry tracks acceptance rates
  • Evidence: HN2() at line 440590, wN2() at line 441103, _B5() at line 441117

See this entry in the whole of v2.0.65 →