AI HOT (Curated Pool)Jul 21, 2026, 20:54 UTC+8

Anthropic team says Claude Tag lands 65% of product PRs, system prompt cut by 80%

Anthropic 团队透露 Claude Tag 承担 65% 产品工程 PR，系统提示词缩减 80%

Anthropic's Cat Wu and Thariq Shihipar shared Claude Code team practices at AI Engineer World's Fair with Simon Willison. Claude Tag, their Slack collaboration tool, now lands 65% of the team's product engineering PRs. They found that stuffing system prompts with examples or 'don't do X' rules hurts output quality on Fable 5 and Opus 4.8, so the Claude Code system prompt shrank by 80%. Thariq noted Fable can edit video to meet their brand team's bar, and the team now treats rewrites as a valid move—the Bun-in-Rust Claude Code already shipped to everyone. The transcript cuts off before detailing what non-engineers do with Claude Tag.

Why it matters: First public disclosure of Claude Tag's internal adoption (65% of product PRs) and a concrete prompt-engineering shift (80% reduction) from the Claude Code team. Held at 82 because it's a fireside chat without reproducible evals or scripts — strong signal, not yet a paper.

Read the original ↗Export Markdown

Take

Two numbers here made me click: 65% of product engineering PRs come from a Slack bot, and the Claude Code system prompt shrank by 80% because shorter prompts work better on Fable 5 and Opus 4.8. This came from a fireside chat Cat Wu and Thariq Shihipar did with Simon Willison at AI Engineer World's Fair—internal practice, not a press release.

65% means Claude Tag isn't assisting; it's the primary committer. Thariq said critical changes still get manual review, but the outer layers rely on automated code review. They also only ship features that show retention among Anthropic employees first—using their own team as a filter.

The system prompt finding is more concrete. Stuffing examples or "don't do X" rules into prompts for Fable 5 or Opus 4.8 degraded output. I'd discount this slightly—it likely applies to their specific code workflows and evals—but it lines up with what other teams are seeing: stronger models get more sensitive to bloated instructions.

Thariq also mentioned Fable can edit video to meet their brand team's bar. His advice for "Deep Blue" anxiety: get more ambitious, take on work you wouldn't have attempted before. I don't fully buy that as a universal fix, but for engineers with solid fundamentals, it's a direction worth testing.

Source: AI HOT (Curated Pool) · simonwillison.net
Published: Jul 21, 2026, 20:54 UTC+8 · Jul 21, 2026