Rethinking Duplication and Validation in the Agentic Era
davidcrawshaw · x · 2026-07-12
This response builds on the vision of "agents writing code while humans read it," arguing that many static designs are merely "half-baked" because validation used to be too expensive. In the agentic era, as validation costs drop, many static constraints can be abandoned.
The author further points out that when agents continuously read and sync with the codebase, duplication and replication aren't necessarily bad things; instead, they could become an engineering paradigm better suited for collaboration.
Related event: Rethinking Programming Languages for the Agent Era(4 posts)→
More from coding & agent
- HeyGen adds a media-sourcing skill for coding agents with 75k images and 10k tracks — HeyGen · 2026-07-22
- Agent search bottlenecks are now about variance, not raw latency — rohanpaul_ai · 2026-07-22
- LangSmith adds tracing for Pipecat, LiveKit, OpenAI Realtime, and Gemini Live — LangChain · 2026-07-22
- An MCP server signs every AI agent tool call into a verifiable Merkle chain — Funky_Chicken_22 · 2026-07-22
- Annotated transcript of a Claude Code team interview is now available — trq212 · 2026-07-22
- Claude Code skill uses 10 Markdown rules to make outputs ADHD-friendly — alex_verem · 2026-07-22