要約
30 秒でわかる
Riley Brown describes improving an AI skill by testing its output, asking the AI to revise the skill after a failure, and repeating the test in a new conversation. His approach emphasizes outcomes and a clear standard of quality.
- 1Begin with a testAsk the agent to perform a task using the skill and evaluate what it produces.
- 2Revise after a failureGive feedback about what went wrong and ask the AI to update the skill.
- 3Clear the context and test againBrown starts a new chat and checks whether the revised skill achieves the desired outcome.
ポイント
- Test a skill on a real task against a specific standard.
- Describe failures and ask for a targeted skill revision.
- Retest in a fresh conversation to reduce the influence of prior context.
全文
チャプターごとに整えた全文を読む
01
An iterative skill-improvement loop
Brown recommends testing, feedback, revision and a fresh-context retest.
Riley Brown describes an outcome-based way to improve an AI skill. Ask the agent to use the skill on a task and judge the result against your standard. If it fails, explain what went wrong and ask the AI to revise the skill. Then open a new chat so the earlier conversation no longer supplies the same context, and test again. Repeat as needed: Brown's focus is on whether the workflow produces the intended outcome.
同じチャンネルの記事
46:40EN
Peter Yang· 2026年11月8日ポッドキャスト · 2 人Ashley Alexander: How AI Helps Me Care for My Parents With Cancerゲスト Ashley Alexander · ホスト Peter YangA caregiver uses AI to prepare for appointments, organize records and ask better questions—while keeping doctors at the center of treatment.
17:50ENPeter Yang· 2026年11月4日ポッドキャストPeter Yang’s Five Steps for Using AI to Help Care for His MotherYang uses a shared care brief and organized records to navigate appointments, while making time for family.
15:03ENPeter Yang· 2026年11月3日ポッドキャストHow Peter Yang Used an AI Phone Agent to Negotiate His Internet BillAn AI call negotiated a lower price and faster service, but Yang still had to approve the change himself.
33:09ENPeter Yang· 2026年11月1日ポッドキャスト · 2 人Jaclyn Konzelmann: When AI Can Build More, Choose What Deserves to Existゲスト Jaclyn Konzelmann · ホスト Peter YangGoogle Labs pairs short strategy documents with prototypes, user co-creation and lessons from experiments that end.
13:05ENPeter Yang· 2026年10月28日ポッドキャストPeter Yang Tests Genie 4: Convincing Worlds, Unfinished GameplayFive live demonstrations show scenes that respond to prompts and sound, alongside inconsistent actions and limited game mechanics.
1:06ENPeter Yang· 2026年10月26日ポッドキャストPeter Yang on Setting Up Payroll for a One-Person BusinessIn a paid partnership, Yang describes the paperwork he encountered and a payroll product integrated with a business account.