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
440
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
200
Scale SciPy with jax.shard_map - jax.shard_mapで SciPy をスケール
Avatar for tsho tsho
0
120
Developer Advocate / Community Managerなるには？
Avatar for tsho tsho
0
730
25/04/12 - Build with AI Hands-on Appendix
Avatar for tsho tsho
1
81
Unit testしてますか？
Avatar for tsho tsho
1
660

Other Decks in Technology

See All in Technology
データを"持てない"環境でのアノテーション基盤設計
Avatar for SansanTech sansantech
PRO
1
150
Oracle Cloud Infrastructure：2026年4月度サービス・アップデート
Avatar for oracle4engineer oracle4engineer
PRO
0
120
Building a Standalone Programming Environment
Avatar for Harukasan harukasan
PRO
1
100
目的ファーストのハーネス設計 ~ハーネスの変更容易性を高めるための優先順位~
Avatar for Gota gotalab555
8
2.5k
AI와 협업하는 조직으로의 여정
Avatar for Arawn Park arawn
0
530
M5Stack CoreS3とZephyr(RTOS)で Edge AIっぽいことしてみた
Avatar for misoji engineer iotengineer22
0
350
小説執筆のハーネスエンジニアリング
Avatar for osushi_cr yoshitetsu
0
810
Anthropic「Long-running a gents」をGeminiで再現してみた
Avatar for t-kikuchi tkikuchi
0
590
AI活用時代の事業判断高度化を導くエンジニアリング基盤 / 20260424 Atsushi Funahashi
Avatar for SHIFT EVOLVE shift_evolve
PRO
2
100
AndroidアプリとCopilot Studioの統合
Avatar for なかしょ nakasho
0
170
AIが盛んな時代に 技術記事を書き始めて起きた私の中での小さな変化
Avatar for 松尾淳平 peintangos
0
260
バイブコーディングで3倍早く⚪⚪を作ってみた
Avatar for Sam Akada samakada
0
180

Featured

See All Featured
More Than Pixels: Becoming A User Experience Designer
Avatar for Michelle Schulp Hunt marktimemedia
3
380
From π to Pie charts
Avatar for Rasagy Sharma rasagy
0
170
Crafting Experiences
Avatar for Bethany Jepchumba bethany
1
120
How Software Deployment tools have changed in the past 20 years
Avatar for Geshan Manandhar geshan
0
33k
Odyssey Design
Avatar for Ryan Kendrick rkendrick25
PRO
2
580
Music & Morning Musume
Avatar for Bryan Veloso bryan
47
7.2k
Taking LLMs out of the black box: A practical guide to human-in-the-loop distillation
Avatar for Ines Montani inesmontani
PRO
3
2.2k
The Language of Interfaces
Avatar for Des Traynor destraynor
162
26k
New Earth Scene 8
Avatar for Sydney Stone popppiees
3
2.1k
Darren the Foodie - Storyboard
Avatar for Kevinho.art khoart
PRO
3
3.3k
Six Lessons from altMBA
Avatar for Skipper Chong Warson skipperchong
29
4.2k
Become a Pro
Avatar for Speaker Deck speakerdeck
PRO
31
5.9k

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