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

Avatar for tsho tsho
February 26, 2026
Technology
480
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
230
Scale SciPy with jax.shard_map - jax.shard_mapで SciPy をスケール
Avatar for tsho tsho
0
140
Developer Advocate / Community Managerなるには？
Avatar for tsho tsho
0
790
25/04/12 - Build with AI Hands-on Appendix
Avatar for tsho tsho
1
89
Unit testしてますか？
Avatar for tsho tsho
1
670

Other Decks in Technology

See All in Technology
「エンジニア進化論」2028年の開発完全自動化、エンジニアはどう進化するか
Avatar for CyberAgent cyberagentdevelopers
PRO
6
5.3k
2026TECHFRESH畢業分享會 - Lightning Talk - 資料也要 CI/CD? 用 Airbyte 自動化資料同步
Avatar for LINE Developers Taiwan line_developers_tw
PRO
0
1.2k
マルチアカウント環境での コーディングエージェントを使った障害調査が大変なので AIエージェントにReadOnly権限を付与してみた / ReadOnly AI Agents for Multi-Account AWS Incident Response
Avatar for Takashi Yamaguchi yamaguchitk333
2
110
Disciplined Vibes: Scaling AI-Assisted Engineering
Avatar for Sheharyar Naseer sheharyar
0
150
200個のGitHubリポジトリを横断調査したかった
Avatar for Issei.Komori icck
0
130
LLMにもCAP定理があるという話
Avatar for Haruka Sakihara harukasakihara
0
400
就職⽀援サービスにおけるキャリアアドバイザーのシフトスケジューリング
Avatar for Recruit recruitengineers
PRO
1
150
自律型AIエージェントは何を破壊するのか
Avatar for kojira kojira
0
160
AIのReact習熟度を測る
Avatar for uhyo uhyo
2
620
【2026年版】 ベクトル検索䛸 Embedding最前線
Avatar for Tomoko Uchida mocobeta
6
2.1k
iAEONの段階的リアーキテクト戦略 / iAEON's_Gradual_Re-architecture_Strategy
Avatar for AEON aeonpeople
0
210
Oracle AI Database@AWS：サービス概要のご紹介
Avatar for oracle4engineer oracle4engineer
PRO
4
3k

Featured

See All Featured
Building AI with AI
Avatar for Ines Montani inesmontani
PRO
1
1.1k
For a Future-Friendly Web
Avatar for Brad Frost brad_frost
183
10k
DBのスキルで生き残る技術 - AI時代におけるテーブル設計の勘所
Avatar for soudai sone soudai
PRO
65
55k
How to train your dragon (web standard)
Avatar for Monica Dinculescu notwaldorf
97
6.7k
Evolution of real-time – Irina Nazarova, EuRuKo, 2024
Avatar for Irina Nazarova irinanazarova
9
1.4k
HDC tutorial
Avatar for Michiel Stock michielstock
2
720
Chasing Engaging Ingredients in Design
Avatar for Sebastian Deterding codingconduct
0
220
Fashionably flexible responsive web design (full day workshop)
Avatar for Andy Clarke malarkey
408
66k
The Cost Of JavaScript in 2023
Avatar for Addy Osmani addyosmani
55
10k
Tips & Tricks on How to Get Your First Job In Tech
Avatar for Honza Javorek honzajavorek
1
540
Jamie Indigo - Trashchat’s Guide to Black Boxes: Technical SEO Tactics for LLMs
Avatar for Tech SEO Connect techseoconnect
PRO
0
170
Producing Creativity
Avatar for Steve Smith orderedlist
PRO
348
40k

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