Riley Brown's Outcome-Based Way to Improve AI Skills

Test a skill, describe a failure, revise it and retest in a fresh chat.

RBRiley BrownGuest · Creator
Channel
Peter Yang
Published
Aug 16, 2026
Video
0:34
Read
1 min
Original
English
Open on YouTube
Scroll to read and the video shrinks to the bottom-right corner. Captions follow your reading language.
Reading languageAvailable in 2 languages
You're reading the original English.
SUMMARY

In 30 seconds

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.

  1. 1Begin with a testAsk the agent to perform a task using the skill and evaluate what it produces.
  2. 2Revise after a failureGive feedback about what went wrong and ask the AI to update the skill.
  3. 3Clear the context and test againBrown starts a new chat and checks whether the revised skill achieves the desired outcome.

Takeaways

  1. Test a skill on a real task against a specific standard.
  2. Describe failures and ask for a targeted skill revision.
  3. Retest in a fresh conversation to reduce the influence of prior context.
FULL TEXT

Read the edited text by chapter

Transcript only
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.

More from this channel

46:40EN
Peter Yang· Nov 8, 2026Podcast · 2 speakersAshley Alexander: How AI Helps Me Care for My Parents With CancerGuest Ashley Alexander · Host Peter YangA caregiver uses AI to prepare for appointments, organize records and ask better questions—while keeping doctors at the center of treatment.AI in healthcareHuman-AI CollaborationProductivity
17:50EN
Peter Yang· Nov 4, 2026PodcastPeter 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.AI in healthcareHuman-AI CollaborationProductivity
15:03EN
Peter Yang· Nov 3, 2026PodcastHow 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.AI agentsProductivityHuman-AI Collaboration
33:09EN
Peter Yang· Nov 1, 2026Podcast · 2 speakersJaclyn Konzelmann: When AI Can Build More, Choose What Deserves to ExistGuest Jaclyn Konzelmann · Host Peter YangGoogle Labs pairs short strategy documents with prototypes, user co-creation and lessons from experiments that end.AI Product ManagementProduct StrategyHuman-AI Collaboration+1
4 slides13:05EN
Peter Yang· Oct 28, 2026PodcastPeter 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.Generative mediaVision & video
Slides1:06EN
Peter Yang· Oct 26, 2026PodcastPeter 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.EntrepreneurshipProductivity