Asking an AI to use verifiable info changes its picks dramatically
santiviquez · x · 2026-11-17
While testing tools, the author found that simply asking the model to rely on verifiable information significantly changed its recommendations. He reflects that output quality still depends heavily on how much the person prompting knows the right questions to ask. Having spent too much to quit, he pivoted to a new approach: having an agent read each tool's API documentation and verify whether it could handle each of 10 specific use cases, to find which tool is actually best.
More from coding & agent
- Developer ships ASC CLI 7.0.0 ahead of schedule — rudrank · 2026-11-17
- Google report: hackers use AI agents to auto-exploit just-patched vulnerabilities — khademinori · 2026-11-17
- Grok Bot Content System: Automate Research, Never Judgment — a $10K Side-Biz Play — PrajwalTomar_ · 2026-11-17
- Qwen Code Desktop v0.28.0 ships DingTalk managed-agent adapter and workspace sidebar filter — github-actions[bot] · 2026-11-17
- Qodo article: building a verification stack for the agentic software factory — blaizedsouza · 2026-11-17
- Solo dev open-sources OpsBridge, an agent workbench for investigating blocked invoices — Fit_Fortune953 · 2026-11-17