Jared Zoneraich on Building Agents for Improving Models

The Cognition builder argues that agent designs should account for model progress and avoid unnecessary scaffolding.

JZJared Zoneraichゲスト · Cognition
チャンネル
Peter Yang
公開日
2026年7月13日
動画
0:43
読了時間
1 分
原文
英語
YouTube で開く
スクロールすると動画は右下に小さくなって再生を続けます。字幕は閲覧言語に合わせて切り替わります。
閲覧言語2 言語で読めます
この記事はまだ日本語に翻訳されていないため、英語の原文を表示しています。
要約

30 秒でわかる

Asked about common agent-building mistakes, Jared Zoneraich advises teams to account for model progress and avoid scaffolding that fights the model's capabilities.

  1. 1Account for model progressZoneraich says teams should consider the direction of model development.
  2. 2Avoid fighting the modelHe recommends allowing the model to use its capabilities instead of forcing every step.
  3. 3Revisit scaffoldingHe predicts that stronger models will need less surrounding scaffolding for some tasks.

ポイント

  1. Consider how model capabilities may change when designing an agent.
  2. Let the model handle tasks it can perform rather than adding unnecessary direction.
  3. Zoneraich expects improving models to reduce some scaffolding needs over time.
全文

チャプターごとに整えた全文を読む

文字起こしのみ
01

Designing as models improve

Zoneraich discusses model progress and agent scaffolding.

Asked about mistakes in building AI agents, Cognition builder-in-residence Jared Zoneraich says teams should account for progress in model capabilities. He recommends designing with the direction of model development in mind and avoiding unnecessary scaffolding that forces the model into a particular path. In his view, improving models will reduce the amount of surrounding machinery needed for some tasks; this is his expectation rather than a universal rule for every agent.

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.AI in healthcareHuman-AI CollaborationProductivity
17:50EN
Peter 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.AI in healthcareHuman-AI CollaborationProductivity
15:03EN
Peter 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.AI agentsProductivityHuman-AI Collaboration
33:09EN
Peter 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.AI Product ManagementProduct StrategyHuman-AI Collaboration+1
スライド 4 枚13:05EN
Peter 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.Generative media画像と動画
スライド1:06EN
Peter 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.EntrepreneurshipProductivity