Persona + expertise prompting turns generic reviews into senior-engineer code audits
JafarNajafov · x · 2026-10-13
Part 1 of a context-engineering series: give the model a specific role, years of experience, named skills and communication style, and it activates different reasoning. The screenshot shows a 'senior frontend engineer, 12 years' persona auditing React code far beyond generic feedback: useEffect deep clones on every state change, broken useMemo deps, O(n) includes → Set, duplicate IDs in selectAll, inline style objects, missing React.memo — each with fixes.
More from coding & agent
- LangChain adds support for ScaleDown's cheap, fast constrained decision models for agent loops — LangChain · 2026-10-13
- Yoniq Compute repo ships inference recipes validated on 1x-8x RTX Pro 6000 with SGLang and vLLM — TheZachMueller · 2026-10-13
- SaaS Vendors and Agencies Are Asking to Plug Into HQ, the New Entry Point for Work — jacob_posel · 2026-10-13
- He Built a 7-Bot Product Swarm on Grok Bot — Here's What Actually Works — PawelHuryn · 2026-10-13
- Claude tried installing ffmpeg from a sketchy fork instead of apt while setting up a VM — haydendevs · 2026-10-13
- Google rolling out custom MCP support in Gemini desktop app to more users — testingcatalog · 2026-10-13