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
550
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
Benchmarking Vector Databases: pgvector vs. LanceDB
Avatar for tsho tsho
0
110
Google IO 2026で進化をとげた Google AI Studio
Avatar for tsho tsho
0
20
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
260
Scale SciPy with jax.shard_map - jax.shard_mapで SciPy をスケール
Avatar for tsho tsho
0
160
Developer Advocate / Community Managerなるには？
Avatar for tsho tsho
0
850
25/04/12 - Build with AI Hands-on Appendix
Avatar for tsho tsho
1
100
Unit testしてますか？
Avatar for tsho tsho
1
680

Other Decks in Technology

See All in Technology
Self Healing Rollouts: Automating Production Fixes with Agentic AI
Avatar for Kevin Dubois kdubois
0
130
Nav2、Nav3 ... はたまた自作？〜 作って理解する Nav3 の設計意図 〜 / Nav2, Nav3 ... or Build Your Own? — Understanding Nav3's design intent by building it from scratch
Avatar for Yuki Anzai yanzm
0
170
Data Hubグループ 紹介資料
Avatar for Sansan, Inc. sansan33
PRO
0
3.2k
[DroidKaigi 2026] Making UI specifications visible: Android UI development in the AI agent era supported by Compose Screenshot Testing and galleries
Avatar for syarihu syarihu
0
460
Kiro Crewしか勝たん！？
Avatar for Kazuki Miura miu_crescent
PRO
0
150
全社に広がるMCPサーバーを、 どう安全に管理するか MCPass開発の舞台裏
Avatar for k.muguruma mtpooh
3
250
はじめてのDatabricks：技術者向けワークショップ / beginner-workshop
Avatar for Databricks Japan databricksjapan
PRO
0
110
少人数データチームのDevin活用実践事例
Avatar for Runa Yamada runandy16
2
320
Bet AI Day 2026丨Agentは、「金融」という巨大産業の何を変えられるのか
Avatar for LayerX layerx
PRO
0
560
振り返りこそエンジニアの本領
Avatar for Negima negima
0
140
現場の暗黙知を継承するAIエージェント — 対話から生まれる長期記憶と Skills
Avatar for Atsuki Shirasawa atsukish
0
220
Bet AI Day 2026丨How We Bet AI: AIとともに働く場をつくる
Avatar for LayerX layerx
PRO
1
1.7k

Featured

See All Featured
Building Adaptive Systems
Avatar for Chris Keathley keathley
44
3.2k
Responsive Adventures: Dirty Tricks From The Dark Corners of Front-End
Avatar for Vitaly Friedman smashingmag
254
22k
How to make the Groovebox
Avatar for あそなす asonas
2
2.4k
Kristin Tynski - Automating Marketing Tasks With AI
Avatar for Tech SEO Connect techseoconnect
PRO
0
490
How to Build an AI Search Optimization Roadmap - Criteria and Steps to Take #SEOIRL
Avatar for Aleyda Solis aleyda
1
2.2k
Agile Actions for Facilitating Distributed Teams - ADO2019
Avatar for Mark Kilby mkilby
0
270
JavaScript: Past, Present, and Future - NDC Porto 2020
Avatar for David Neal reverentgeek
52
6.1k
The Spectacular Lies of Maps
Avatar for Per Axbom axbom
PRO
1
960
CoffeeScript is Beautiful & I Never Want to Write Plain JavaScript Again
Avatar for Sam Stephenson sstephenson
162
16k
How to Grow Your eCommerce with AI & Automation
Avatar for Katarina Dahlin katarinadahlin
PRO
1
260
Winning Ecommerce Organic Search in an AI Era - #searchnstuff2025
Avatar for Aleyda Solis aleyda
1
2.1k
The Impact of AI in SEO - AI Overviews June 2024 Edition
Avatar for Aleyda Solis aleyda
6
1.2k

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