Upgrade to Pro
— share decks privately, control downloads, hide ads and more …
Speaker Deck
Sign up for free
Menu
Search
Features
All features
Private URLs
Password Protection
Custom URLS
Scheduled publishing
Remove Branding
Restrict embedding
Deck Collections
Notes
Features
All features
Private URLs
Password Protection
Custom URLS
Scheduled publishing
Remove Branding
Restrict embedding
Deck Collections
Notes
Explore
Featured decks
Featured speakers
Programming
Technology
Storyboards
Explore
Featured decks
Featured speakers
Programming
Technology
Storyboards
Pricing
Search
Sign in
Sign up for free
AIをフル活用してオンコール機能のプロトタイプを2日で作った話 / Building an A...
Search
Narimichi Takamura
June 30, 2026
Technology
280
0
Share
Embed
Copy iframe code
Copy JS code
Copy link
Start on current slide
AIをフル活用してオンコール機能のプロトタイプを2日で作った話 / Building an AI-Powered On-Call Prototype in Just Two Days
ゆるAI 第一回での登壇資料です。
https://yuru-ai.connpass.com/event/392834/
Narimichi Takamura
June 30, 2026
More Decks by Narimichi Takamura
See All by Narimichi Takamura
SRE本の知られざる名シーン / The Hidden Gems of Google SRE Book
nari_ex
2
770
小さくはじめるSLI/SLO ~育てながら組織に定着させる実践知~ / Starting Small with SLI/SLOs: Building Adoption Through Continuous Growth
nari_ex
8
2.7k
Observability — Extending Into Incident Response
nari_ex
2
1.4k
インシデントキーメトリクスによるインシデント対応の改善 / Improving Incident Response using Incident Key Metrics
nari_ex
1
14k
組織的なインシデント対応を目指して〜成熟度評価と改善のステップ〜 / Towards an Organized Incident Response - Maturity Assessment and Improvement Steps -
nari_ex
7
10k
Waroomの開発モチベーションと今後のロードマップ / Waroom development motivation and roadmap
nari_ex
1
1.9k
Engineering with Business Impact
nari_ex
2
390
How We Foster Reliability in Diversity
nari_ex
14
13k
SRE Practices in Organizations
nari_ex
16
12k
Other Decks in Technology
See All in Technology
インバスケット試験対策アプリを 作って見えたAIエージェント構築 ナレッジ2選
shichijoyuhi
1
130
今こそ知りたいAmplifyGen2
mkdev10
2
150
オンラインゲームのシステム全体像 - コロプラ 2026年度 新卒研修
colopl
0
810
Meet AgentCore Identity Consent Portal
hironobuiga
3
190
形式手法を使って仕様をコーディングしよう
mikanichinose
0
180
生成AIで高い生産性を求められて、 悩み、乗り越えた話
mot_techtalk
2
130
[2026 Oracle Technical Deep Dive] Apache Iceberg × Oracle AI Database -Oracle Autonomous AI Lakehouseが実現するAI時代のデータ基盤- (2026年9月17日開催)
oracle4engineer
PRO
0
120
Oracle Base Database Service 技術詳細
oracle4engineer
PRO
17
120k
More Freedom on the Same Shared GPU Cluster: A Small Team’s Experience with vCluster
nttcom
0
140
生成AIを使って「人が」考える技術 ― AI時代の人機共想と実践ノウハウ|UNITT AC2026
ishiirikie
0
560
The seven pitfalls of AI (revised version)
ufried
0
270
ビジネスを止めない技術的負債の返済のための戦略とその手法 - 技術的負債と向き合う / Complexity and Simplicity
soudai
PRO
3
650
Featured
See All Featured
Ecommerce SEO: The Keys for Success Now & Beyond - #SERPConf2024
aleyda
1
2.2k
Scaling GitHub
holman
464
140k
Odyssey Design
rkendrick25
PRO
2
860
The B2B funnel & how to create a winning content strategy
katarinadahlin
PRO
1
550
コードの90%をAIが書く世界で何が待っているのか / What awaits us in a world where 90% of the code is written by AI
rkaga
63
46k
From π to Pie charts
rasagy
1
390
What's in a price? How to price your products and services
michaelherold
247
13k
How Fast Is Fast Enough? [PerfNow 2025]
tammyeverts
3
920
Building the Perfect Custom Keyboard
takai
2
890
Understanding Cognitive Biases in Performance Measurement
bluesmoon
32
3k
How to Think Like a Performance Engineer
csswizardry
28
2.9k
Pawsitive SEO: Lessons from My Dog (and Many Mistakes) on Thriving as a Consultant in the Age of AI
davidcarrasco
0
250
Transcript
AIΛϑϧ׆༻ͯ͠ ΦϯίʔϧػೳͷϓϩτλΠϓΛ 2Ͱ࡞ͬͨ ߴଜ ಓʢ@nari_exʣ
2
גࣜձࣾTopotalʢͱΆͨΔʣ • h#ps:/ /topotal.com • SREΛओ࣠ʹͨ͠ελʔτΞοϓ • 2ࣄۀΛӡӦ • SRE
as a Service • SaaS for SREʢWaroomʣ 3
SRE as a Service • topotal.com/services/sre-as-a-service • SREʹಛԽٕͨ͠ज़ࢧԉαʔϏε • ࢧԉͷྫ
• SLI/SLOͷಋೖɾӡ༻վળ • CI/CDͷߏஙɾվળ • ΠϯγσϯτϚωδϝϯτͷվળ 4
WaroomʢΘΔʔΉʣ • ΠϯγσϯτϚωδϝϯτSaaS • Slack ϕʔεͷରԠʹ߹ΘͤͯࣗಈԽɾ লྗԽ͕Ͱ͖Δ • AIΛ༻͍ͨݪҼΓ͚ɾ෮چ •
ਓແ੍ݶͷΦϯίʔϧػೳ 5
͡Ίʹ • PdMͱͯ͠ AIΛ͔ͭͬͯ৽ػೳͷϓϩτλΠϓΛͭ͘Δ աఔͰ ಘֶͨͼΛڞ༗͠·͢ • ʮAI࣌ʹͲ͏ϓϩμΫτΛ࡞Δͷ͔ʯΛߟ͑Δ͖͔͚ͬʹͳ Εخ͍͠Ͱ͢ 6
ຊެԋͷରऀ • AIίʔσΟϯάπʔϧʢVibe Codingʣʹڵຯ͕͋Δํ • ϓϩμΫτ։ൃ৽ػೳ։ൃʹܞΘ͍ͬͯΔΤϯδχΞ • AI࣌ͷ༷ࡦఆϓϩτλΠϐϯάͷਐΊํΛΓ͍ͨํ 7
൵ئͩͬͨΦϯίʔϧػೳ • ϦϦʔεॳ͔Βཁ͕ઈ͑ͳ͍ͷػೳͷҰͭ • ʮ͍͔ͭ࡞Ζ͏ʯ ͱࢥͬͯ5͕ܦա͍ͯͨ͠... 8
͖͔͚ͬࣾษڧձ • 2026/01্०ɺVibe Codingͷྫ͕֤ॴͰੜ·Ε͍ͯͨ • ࣾษڧձͰʮexe.dev͕͍͢͝ʯ͜ͱΛΔ • ࣌ͷࣗͷग़ΕײΛײ͓ͯ͡ΓɺҰ୴৮ͬͯΈΔ͜ͱʹ • Ͳ͏ͤΔͳΒɺϞνϕͷग़ΔͷΛͭ͘Γ͍ͨ
→ ࢼ͠ʹΦϯίʔϧػೳΛ࡞ͬͯΈΑ͏ 9
Φϯίʔϧػೳͱ • ো͕ى͖ͨͱ͖ʹి௨Λ͢ΔΈ • ೲಘײͷ͋Δి௨Λ࣮ݱ͢ΔͨΊʹɺࡉ͔ͳػೳཁٻ͕͋Δ • εέδϡʔϧཧ • ϩʔςʔγϣϯཧ •
ແԠɾԠ࣌ͷΤεΧϨʔγϣϯ • ௨ͷূཧ 10
exe.dev - ର͠ͳ͕Β։ൃͰ͖ΔVM Hos-ngαʔϏε1 • AIΤʔδΣϯτʢShelleyʣͱνϟοτ͠ͳ͕Β։ൃ • VM্Ͱίʔυͷ࣮ɾ࣮ߦɾमਖ਼Λ܁ΓฦͤΔ • HTTPS͖Ͱͦͷ··ΞϓϦΛެ։Ͱ͖Δ
• αʔόʔߏஙσϓϩΠΛ΄ͱΜͲҙࣝ͠ͳͯ͘Α͍ 1 exe.dev - AI࣌ͷVM Hos0ngαʔϏε 11
࠷ॳʹͬͨ͜ͱ • ʮWaroom͜ΜͳϓϩμΫτͰ͢ɻʯ • ʮΦϯίʔϧػೳΛ࡞͍ͬͯͩ͘͞ɻʯ → 20ޙ… 12
࣮༻Ͱ͖ͳ͍ͷ͕Ͱ͖ͨ 13
೦ͯ͡ཧͷͷͰ͖ͳ͍ • ࠶ܝ: AIຐ๏Ͱͳ͍ → ͪΌΜͱ༷Λߟ͑Α͏ 14
Vibe Codingલͷ४උΛ͢Δ • ͔࣌Β͍׳Ε͍ͯͨChatGPT Deep Research Λར༻ • ҎԼͷ3εςοϓͰ४උʢݴޠԽɺ༷ࡦఆʣΛͨ͠ 1.
ڝ߹ௐࠪ 2. ࠷খݶͷػೳʢMVPʣΛఆٛ͢Δ 3. ༷ॻͱͯ͠Ξτϓοτ 15
Step1: ڝ߹ΛௐΔ • ޙൃͷΦϯίʔϧαʔϏεΛϝΠϯͰใऩू • incident.io • Rootly • Datadog
On-Call 16
Step2: MVPΛߟ͑Δ • ֤ࣾͷڞ௨ػೳ͔ΒMVPͷ͖ͨͨΛ࡞ • ϖϧιφΛఆٛ͠ɺMVPΛϒϥογϡΞοϓ • ͞Βʹ࣮ମݧސ٬͔ΒಘͨΦϯίʔϧػೳͷϖΠϯΛө 17
Step3: AI͚༷ॻΛ࡞Δ • exe.devͰɺShelley ͱ͍͏ΤʔδΣϯτ͕ར༻͞Ε͍ͯΔ • ࠓճʮShelley͕ཧղ͍͢͠ܗͰ༷ʯΛग़͢Α͏ʹࢦࣔ • ࠓࢥ͑ʮ࣮AI͕ཧղ͍͢͠ܗࣜʯͰΑͦ͞͏ →
AI͕ཧղ͍༷͢͠ॻ ͕ 18
͋ͱ exe.dev • exe.devʹ༷ॻΛషΓ͚Δ • 20͘Β͍ͭ → ͦΕͳΓʹಈ͘ͷ͕Ͱ͖ͨ 19
20
ͰऴΘΓ͡Όͳ͍ ৮ͬͯΈͯɺࡉ͔ͳෆʹ͡Ίͯؾͮ͘ • ಋઢ͕ѱ͍ • σβΠϯ͕ඍົ • ෆཁͳϘλϯ͕͋Δ • ใ͕ଟ͍ɾগͳ͍
→ ཧʹఔԕ͍ 21
AIͱର͠ɺഁյͱΛ܁Γฦ͢ • τʔΫϯ੍ݶΛҙࣝ͠ͳ͕Βɺ୲ͯ͠ฒߦ͠ͳ͕Βϒϥογ ϡΞοϓ • ChatGPT: ༷ͷϒϥογϡΞοϓ • exe.dev: εΩʔϚɺίʔυσβΠϯͷ૬ஊɾมߋ
• Why ࣗɺWhat ChatGPTɺHow exe.dev ΞαΠϯ 22
23
ि໌͚ʹνʔϜʹڞ༗ͨ͠ͱ͜Ζ • ʮΑͦ͞͏ʯʮ͕ͳͦ͞͏ʯ • Ұ୴ɺ͜ΕΛ࣋ͬͯϢʔβʔώΞϦϯάͯ͠Έ·͠ΐ͏͔ • ஊ͕ͦͷ͔Βෳ݅ൃੜ͢Δ͜ͱʹ → ಈ͘ͷ͕͋ΔͱͲΜͲΜ͕ਐΉɻϓϩμΫτͮ͘Γʹ͍ ͕૿ͨ͠ʂ
24
·ͱΊ 25
ࣗͳΓͷ։ൃαΠΫϧ ͷܕ͕Ͱ͖ͨ • ʮ۩ମతʹಈ͘ͷʯΛੜΈग़͢· ͰɺPdM͕ࣗͰ͖Δ • →༷ͷઆ໌ίετʙ༷վળ͕ര ʹ!! • ݱঢ়ɺAI׆༻ͷલޙͰਓ͕࣭Λߴ
ΊΔऔΓΈ͕ඞਢ 26
AIվળͷϧʔϓΛരʹͯ͘͠Εͨ • ʮࣦഊ͢Δίετʯ͕ܶతʹԼ͕Δ ͜ͱͷՁΛڧ࣮͘ײ • େʹյͯ͠େʹ࡞ΓͤΔ͕ɺϓϩτλΠϓͮ͘Γͱ૬ ੑόονϦ • εϐʔυͷ֫ಘ͔ΜͨΜ ɺҰํͰɺՁͷ֫ಘΉ͔͍ͣ͠
27
ࠓճͷֶͼ • 1. ೦ͯ͡μϝɻAIΤεύʔͰͳ͍ • 2. Α͍ͷΛ࡞Δʹɺਂ͍ࢥߟͱݴޠԽ͕ඞཁ • 3. ཧͱͷΪϟοϓΛຒΊͯ͡ΊͯՁ͕ग़Δ
28
͋Γ͕ͱ͏͍͟͝·ͨ͠ 29