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
Harnessing the power of AI in IntelliJ IDEA
Search
Anton Arhipov
March 26, 2025
Programming
280
1
Share
Embed
Copy iframe code
Copy JS code
Copy link
Start on current slide
Harnessing the power of AI in IntelliJ IDEA
Anton Arhipov
March 26, 2025
More Decks by Anton Arhipov
See All by Anton Arhipov
Spec-Driven Development with AI-Agents: From High-Level Requirements to Working Software
antonarhipov
2
690
Spec-Driven Development with AI Agents (Workshop, May 2026)
antonarhipov
4
600
Spec-Driven Development with AI Agents. Java Day Istanbul 2026
antonarhipov
3
160
Spec-Driven Development with AI Agents: From High-Level Requirements to Working Software
antonarhipov
3
190
Strengthening Immutability in Kotlin. A Glimpse into Valhalla
antonarhipov
3
120
Kotlin—the New and Noteworthy in 2.2
antonarhipov
1
59
Levels of AI-assisted programming
antonarhipov
0
190
Devoxx France 2024. Kotlin - the new and noteworthy
antonarhipov
2
120
VirtualJUG: Kotlin 2.0 and beyond
antonarhipov
1
220
Other Decks in Programming
See All in Programming
Go × SIMDで高速化するベクトル検索 ~ルーフラインモデルでSIMDが効く境界を探れ! ~
po3rin
1
5k
難しいけど、読めた。- OSSの入口に立った話。
sts11142
0
130
ハーネス設計入門 〜 基礎知識の整理から実務へのステップアップ 〜
kinopeee
19
19k
設計次第でAIコードの読む量は減らせる / designing-for-code-reading
minodriven
29
12k
大喜利で理解するLLM as a Judge / Understanding LLM-as-a-Judge through Ogiri
rockname
0
170
[2026-09-26]空論ジェネリックプロセス~テスト資産とAIで紡ぐ、再現可能なパフォーマンスチューニングの話~
tosite
0
240
Starting & Sustaining Code-Based E2E Testing for Non-Coding QA Teams( #jasstniigata )
teyamagu
PRO
1
750
IBM Bob Dojo #1 仕様駆動開発入門
oniak3ibm
PRO
0
320
選挙速報を多くのユーザーへ 届ける Live Activities 設計
hamayokokuririn
0
190
ソニーのクラウド共通基盤の変遷とAI時代の開発スタイルに合わせた進化 / The Journey of Sony’s Common Cloud Platform and Its Evolution for AI-Native Development
kenjiyoneyama
0
200
動作中のプログラムの中身をリアルタイムに覗く / Realtime Debugger for CSharp with Roslyn
prota
1
1.6k
AI が書く Go コードの品質を劇的に向上させる Linter: “declscope”
mpyw
0
450
Featured
See All Featured
Lightning talk: Run Django tests with GitHub Actions
sabderemane
0
270
How to Think Like a Performance Engineer
csswizardry
28
2.8k
Improving Core Web Vitals using Speculation Rules API
sergeychernyshev
21
1.6k
Marketing to machines
jonoalderson
1
5.8k
Designing for Timeless Needs
cassininazir
1
510
Balancing Empowerment & Direction
lara
6
1.3k
Build your cross-platform service in a week with App Engine
jlugia
234
19k
Why Mistakes Are the Best Teachers: Turning Failure into a Pathway for Growth
auna
0
310
How GitHub (no longer) Works
holman
316
150k
Java REST API Framework Comparison - PWX 2021
mraible
34
9.7k
Music & Morning Musume
bryan
48
7.4k
Navigating the moral maze — ethical principles for Al-driven product design
skipperchong
2
590
Transcript
Harnessing the power of AI in Intell iJ IDEA
None
None
Full-line code completion Minimal assistance. Doesn't get in a way.
Can accept word-by- word with Alt + ->
None
As a result, completion provides a multi-line snippet of code
The comment act as a prompt, adding the information to the context
The snippets of code can be accepted line- by line
.
The snippets of code can be accepted line- by line
. ... or word-by-word
None
inline code generation
Specify additional requirements
With AI actions, we can generate more code. For instance,
generate unit tests.
AI assistant will trigger the workflow to generate unit tests
You still have to execute the tests, verify results, etc
You still have to execute the tests, verify results, etc
You are in control!
None
A more complex change spanning multiple par t s of
the application
The workflow makes changes to multiple files and creates new
files
The workflow makes changes to multiple files and creates new
files You still have to review the changes, accept of decline, run tests, review code .
The workflow makes changes to multiple files and creates new
files You are in control! You still have to review the changes, accept of decline, run tests, review code .
None
None
None
Junie writes code, writes tests, verifies new code, etc .
It's an "autopilot" for writing code under your supervision
Automatically executes tests. Iterates on the task
None
The level of control Max Min
The level of control Max Min You can have various
levels of control over the process To get the most out of the agentic mode, you will need the relax the control. Then you can move faster!
None
None
None
None
None
https://speakerdeck.com/antonarhipov @antonarhipov https://github.com/antonarhipov