“A final tip: probably the most important thing to get great results out of Claude Code -- give Claude a way to verify its work. If Claude has that feedback loop, it will 2-3x the quality of the final result. … Verification looks different for each domain. It might be as simple as running a bash command, or running a test suite, or testing the app in a browser or phone simulator. Make sure to invest in making this rock-solid.”
Boris Cherny, Creator and head of Claude Code. Leads the product and describes how Anthropic's own engineers use it, so he is in a position to know the internal practice. Anthropic sells Claude Code, so his account is first-party and promotional, and the figures he gives are spoken claims.
Anthropic sells AI or agent tools or services, so it has a reason to publish flattering numbers about AI. The passage stays in the archive; read it with that in mind.
How this was checked
Checked against the source by a first reader, then confirmed independently by a second reader who fetched the source without seeing the first reader's notes (Independent review agent (Codex, GPT-6 Astra), blind second pass from passage text and citation only, told not to read the repository, 2026-11-07).
Matches the first and third paragraphs of post 13, after the numbering prefix, with whitespace normalization. The … omits the intervening paragraph describing Claude testing changes to claude.ai/code using the Claude Chrome extension, opening a browser, testing the UI, and iterating. The returned author is Boris Cherny (@bcherny), and created_at is Fri Jan 02 19:59:05 +0000 2026. Presented as his own words.
How to cite this passage
Boris Cherny (Anthropic), “X post by Boris Cherny (the last post of a numbered thread of tips)”, X post by Boris Cherny, 2026-01-02. https://x.com/bcherny/status/2007179861115511237 Archived at https://the-ai-record.com/passages/anthropic-give-claude-way-to-verify-its-work-2026
Anthropic