Upgrade to Pro — share decks privately, control downloads, hide ads and more …

AI Agentにおける評価指標とAgent GPA

Sponsored · Your Podcast. Everywhere. Effortlessly. Share. Educate. Inspire. Entertain. You do you. We'll handle the rest. →
Avatar for tsho tsho
February 26, 2026
Technology
460
1

AI Agentにおける評価指標とAgent GPA

第61回 MLOps 勉強会の発表です。AI Agentの評価指標であるAgent GPAの説明です。

Avatar for tsho

tsho

February 26, 2026

More Decks by tsho

See All by tsho
20260321_エンベディングってなに？RAGってなに？エンベディングの説明とGemini Embedding 2 の紹介
Avatar for tsho tsho
0
220
Scale SciPy with jax.shard_map - jax.shard_mapで SciPy をスケール
Avatar for tsho tsho
0
130
Developer Advocate / Community Managerなるには？
Avatar for tsho tsho
0
760
25/04/12 - Build with AI Hands-on Appendix
Avatar for tsho tsho
1
82
Unit testしてますか？
Avatar for tsho tsho
1
670

Other Decks in Technology

See All in Technology
AsyncStreamでマルチブロードキャストを実装する
Avatar for 1mash0 1mash0
1
180
TypeScriptで実現する既存APIを活用したリモートMCPサーバー構築 / TSKaigi 2026
Avatar for Shodai Suzuki soarteclab
1
180
JaSSTに関わることで変わった人生観 #jasstnano
Avatar for Makky makky_tyuyan
0
170
ルール・ロール・ツールを創る / Creating Rules, Roles and Tools
Avatar for Kenji Saito ks91
PRO
0
150
AI の技術 / AI technology
Avatar for Kenji Saito ks91
PRO
0
110
Oracle AI Database@AWS：サービス概要のご紹介
Avatar for oracle4engineer oracle4engineer
PRO
4
2.6k
Fラン学生が考える、AI時代のデザインに執着した突破口
Avatar for husensan husengs7
1
230
20260516_SecJAWS_Days
Avatar for Takuya Yonezawa takuyay0ne
2
550
How to learn AWS Well-Architected with AWS BuilderCards: Security Edition
Avatar for Kosuke ENOMOTO coosuke
PRO
0
200
コーポレートサイトのアクセシビリティ改善とJIS準拠への実践
Avatar for LINEヤフーTech (LY Corporation Tech) lycorptech_jp
PRO
2
110
【2026年版】プロジェクトマネジメント実践論｜現役エンジニアが語る！～チームでモノづくりをする時のコツとは？～
Avatar for MIXI ENGINEERS mixi_engineers
PRO
1
120
実践 TanStack Start ― 新規プロダクトを開発して確立した、サーバーとクライアント境界の設計パターン / Practical TanStack Start Server-Client Boundary Patterns
Avatar for 株式会社カミナシ kaminashi
2
170

Featured

See All Featured
Being A Developer After 40
Avatar for Adrian Kosmaczewski akosma
91
590k
Bash Introduction
Avatar for André Augusto Costa Santos 62gerente
615
210k
職位にかかわらず全員がリーダーシップを発揮するチーム作り / Building a team where everyone can demonstrate leadership regardless of position
Avatar for MADOX madoxten
62
54k
Chasing Engaging Ingredients in Design
Avatar for Sebastian Deterding codingconduct
0
190
Noah Learner - AI + Me: how we built a GSC Bulk Export data pipeline
Avatar for Tech SEO Connect techseoconnect
PRO
0
180
Future Trends and Review - Lecture 12 - Web Technologies (1019888BNR)
Avatar for Beat Signer signer
PRO
0
3.5k
Code Reviewing Like a Champion
Avatar for maltzj maltzj
528
40k
Building Flexible Design Systems
Avatar for Yesenia Perez-Cruz yeseniaperezcruz
330
40k
GraphQLの誤解/rethinking-graphql
Avatar for sonatard sonatard
75
12k
16th Malabo Montpellier Forum Presentation
Avatar for AKADEMIYA2063 akademiya2063
PRO
0
120
A Soul's Torment
Avatar for Nat Ma seathinner
6
2.8k
Google's AI Overviews - The New Search
Avatar for Barry Adams badams
0
1k

Transcript

  1. © 2026 Snowflake Inc. All Rights Reserved AI Agent における評価手法と

    Agent GPA Sho Tanaka Feb 2026

  2. © 2026 Snowflake Inc. All Rights Reserved AI/ML, Dataの登壇やデモ開発を担当 -

    ex-Google gTech Ads, ML/Data - MLOps community 運営 (2020~) - Google Developer Expert, AI/ML tsho / 田中 翔 (Sho Tanaka) Linkedin.com/in/tsho Lead Developer Advocate @ Snowflake

  3. © 2026 Snowflake Inc. All Rights Reserved AI Agentとは?

  4. © 2026 Snowflake Inc. All Rights Reserved

  5. © 2026 Snowflake Inc. All Rights Reserved AI Agent の活用事例

    メルカリにおけるデータアナリティクス AI エージェント「Socrates」と ADK 活用 事例 - Speaker Deck コクヨ、ジンズなどがAIエージェント自社 開発 「Snowflake Intelligence」日本提 供

  6. © 2026 Snowflake Inc. All Rights Reserved

  7. © 2026 Snowflake Inc. All Rights Reserved AIOpsは2016年ごろにガー トナーが定義したものもあ るので注意

  8. © 2026 Snowflake Inc. All Rights Reserved

  9. © 2026 Snowflake Inc. All Rights Reserved 評価手法

  10. © 2026 Snowflake Inc. All Rights Reserved AI Agent /

    LLM による代表的な評価指標

  11. © 2026 Snowflake Inc. All Rights Reserved 例：ADK の評価指標 Why

    Evaluate Agents - Agent Development Kit (ADK) LLM-as-a-judge Final_response_match_v2, rubric_based_final_response_qual ity_v1 etc. Code-based / Deterministic コード・ルールベース/一致 tool_trajectory_avg_score Traditional NLP Metrics 従来の自然言語処理指標 response_match_score Human Evaluation 人間による評価 (機能として明示的な「指標」はない が、Web UI (Trace View) で支援)

  12. © 2026 Snowflake Inc. All Rights Reserved Agent GPA と

    TruLens

  13. © 2026 Snowflake Inc. All Rights Reserved

  14. © 2026 Snowflake Inc. All Rights Reserved

  15. © 2026 Snowflake Inc. All Rights Reserved

  16. © 2026 Snowflake Inc. All Rights Reserved Agent GPA の論文

    What Is Your Agent's GPA? A Framework for Evaluating Agent Goal-Plan-Action Alignment

  17. © 2026 Snowflake Inc. All Rights Reserved OSS としても提供中 https://github.com/truera/trulens

    https://www.trulens.org/

  18. © 2026 Snowflake Inc. All Rights Reserved https://www.trulens.org/getting_started/quickstarts/web-search-agent-evaluation/#10-add- evaluations

  19. © 2026 Snowflake Inc. All Rights Reserved

  20. © 2026 Snowflake Inc. All Rights Reserved さいごに

  21. © 2026 Snowflake Inc. All Rights Reserved Snowflake 上で Private

    Preview として提供中 What’s Your Agent’s GPA? A Framework for Evaluating AI Agent Reliability

  22. © 2026 Snowflake Inc. All Rights Reserved 参考

  23. © 2026 Snowflake Inc. All Rights Reserved CS 329T: Trustworthy

    Machine Learning

  24. © 2026 Snowflake Inc. All Rights Reserved https://learn.deeplearning.ai/

  25. © 2026 Snowflake Inc. All Rights Reserved THANK YOU