Slide 1
Slide 1 text
Márton Braun
@zsmb13
Building with AI in Kotlin
Sebastian Aigner
@sebi_io
Slide 2
Slide 2 text
Part 1
AI-assisted coding in Kotlin
Part 2
Building AI-powered apps in Kotlin
Slide 3
Slide 3 text
No content
Slide 4
Slide 4 text
No content
Slide 5
Slide 5 text
No content
Slide 6
Slide 6 text
No content
Slide 7
Slide 7 text
No content
Slide 8
Slide 8 text
No content
Slide 9
Slide 9 text
No content
Slide 10
Slide 10 text
github.com/JetBrains/kotlinconf-app
Slide 11
Slide 11 text
No content
Slide 12
Slide 12 text
Next
Edit
Suggestions
Slide 13
Slide 13 text
No content
Slide 14
Slide 14 text
No content
Slide 15
Slide 15 text
No content
Slide 16
Slide 16 text
No content
Slide 17
Slide 17 text
No content
Slide 18
Slide 18 text
No content
Slide 19
Slide 19 text
No content
Slide 20
Slide 20 text
No content
Slide 21
Slide 21 text
No content
Slide 22
Slide 22 text
No content
Slide 23
Slide 23 text
No content
Slide 24
Slide 24 text
No content
Slide 25
Slide 25 text
No content
Slide 26
Slide 26 text
No content
Slide 27
Slide 27 text
No content
Slide 28
Slide 28 text
3x speed
Slide 29
Slide 29 text
No content
Slide 30
Slide 30 text
No content
Slide 31
Slide 31 text
No content
Slide 32
Slide 32 text
No content
Slide 33
Slide 33 text
No content
Slide 34
Slide 34 text
4x speed
Slide 35
Slide 35 text
No content
Slide 36
Slide 36 text
No content
Slide 37
Slide 37 text
3x speed
Slide 38
Slide 38 text
No content
Slide 39
Slide 39 text
No content
Slide 40
Slide 40 text
No content
Slide 41
Slide 41 text
No content
Slide 42
Slide 42 text
No content
Slide 43
Slide 43 text
No content
Slide 44
Slide 44 text
No content
Slide 45
Slide 45 text
EAP
jb.gg/junie-github
Slide 46
Slide 46 text
No content
Slide 47
Slide 47 text
No content
Slide 48
Slide 48 text
No content
Slide 49
Slide 49 text
No content
Slide 50
Slide 50 text
No content
Slide 51
Slide 51 text
No content
Slide 52
Slide 52 text
jb.gg/ai
Slide 53
Slide 53 text
No content
Slide 54
Slide 54 text
Part 1
AI-assisted coding in Kotlin
Part 2
Building AI-powered apps in Kotlin
Slide 55
Slide 55 text
Kotlin ♡ AI on every layer
• Model Provider SDKs
• Core AI toolkit
• Agentic Frameworks
Slide 56
Slide 56 text
Model Provider SDKs
Slide 57
Slide 57 text
Model Provider SDKs
Slide 58
Slide 58 text
ML Kit from Google
Slide 59
Slide 59 text
AI Edge &
MediaPipe
Slide 60
Slide 60 text
Introducing Koog
Kotlin AI Agent Framework
Slide 61
Slide 61 text
What is Koog?
• Kotlin framework for AI agents
– LLM-enabled applications that make decisions and
can influence other systems
• Manages LLM interactions
• Provides DSLs to express complex workflows
via graphs
Slide 62
Slide 62 text
Platforms supported by Koog
• Android
• JVM (Desktop / Server-Side)
• Web (Wasm / JS)
(iOS not supported out of the box, but possible)
Slide 63
Slide 63 text
Let's cook with Koog!
Slide 64
Slide 64 text
Step 0: Get LLM access!
Koog supports major vendors
• Google
• OpenAI
• Anthropic
• OpenRouter
• Ollama (on-device LLMs!)
Slide 65
Slide 65 text
Personal recommendation: OpenRouter
Slide 66
Slide 66 text
Personal recommendation: OpenRouter
prepaid = no scary billing!
(and $5 gets you a lot of tokens!)
Slide 67
Slide 67 text
You can choose and try different models
Slide 68
Slide 68 text
A very simple agent
val agent = AIAgent(
executor = simpleOpenRouterExecutor(ApiKeys.openRouter),
systemPrompt = "You are a helpful assistant. Answer concisely.",
llmModel = OpenAIModels.Chat.GPT5,
)
suspend fun main() {
val result: Agent =
agent.run("What is the capital of Bavaria?")
println(result)
}
The capital of Bavaria is Munich.
Slide 69
Slide 69 text
We need more… much more!
• Exchanging more than one message
• A way to steer the agent
• Working with tools
• A way to observe the agent
Slide 70
Slide 70 text
Koog gives you everything to build
production-ready agents.
Slide 71
Slide 71 text
Koog's fundamental structures
Graph(s): Made from nodes and edges
LLM message history
Slide 72
Slide 72 text
LLM message history
• Automatically managed by Koog
• Doesn't have to be manually changed in
normal operation
– Ability to make changes is still exposed
• Advanced features for management (like
history compression)
Slide 73
Slide 73 text
Introducing graphs and nodes
Output
Input Node
Slide 74
Slide 74 text
Some available nodes
Message.Response
String
node
LLMRequest
ReceivedToolResult
Message.Tool.Call
node
executeTool
Message.Response
ReceivedToolResult
node
LLM
SendToolResult
Message.Assistant
Message.Tool.Call
node
Start
node
Finish
Slide 75
Slide 75 text
ReceivedToolResult
node
LLM
SendToolResult
ReceivedToolResult
Message.Tool.Call
node
executeTool
Nodes snap together with edges
Message.Response
node
LLMRequest
Message.Assistant
Message.Tool.Call
Slide 76
Slide 76 text
Custom node
U
T block()
val nodeCustom by node { str ->
println(str)
42
}
Slide 77
Slide 77 text
String
String node
Finish
node
Start
Creating graphs with nodes and edges
used
node
LLMRequest
"only use
"
else
"I'm blue. What
emotion am I
feeling?"
private val classificationStrategy = strategy("Emotion classification") {
val nodeSendToLLM by nodeLLMRequest()
val nodeSayEmojiOnlyPlease by node {
"Please only react using the following emojis: "
}
edge(nodeStart forwardTo nodeSendToLLM)
edge(nodeSendToLLM forwardTo nodeFinish onAssistantMessage { msg ->
listOf(" ", " ", " ").any { emoji -> emoji in msg.content }
})
edge(nodeSendToLLM forwardTo nodeSayEmojiOnlyPlease)
edge(nodeSayEmojiOnlyPlease forwardTo nodeSendToLLM)
}
Slide 78
Slide 78 text
Plugging it in
AIAgent(
executor = simpleOpenRouterExecutor(ApiKeys.openRouter),
systemPrompt = "Answer the user's question.",
llmModel = OpenAIModels.Chat.GPT5,
strategy = classificationStrategy,
)
Slide 79
Slide 79 text
Integrating with tools
• We want our agent to affect the world around it!
• We need to provide it with (deterministic) integrations for the agent to:
– Obtain task-specific information (e.g. "Read this GitHub issue")
– Perform task-specific actions (e.g. "Transfer to ")
• LLMs are specifically trained for this!
Slide 80
Slide 80 text
Declaring our own tool (almost)
suspend fun getGitHubIssueContents(
owner: String,
repo: String,
issueNumber: Int,
token: String? = null,
): String =
GitHubIssueClient.getGitHubIssueContents(
owner,
repo,
issueNumber,
token
)
Slide 81
Slide 81 text
Creating a toolset with LLM descriptions
@LLMDescription("Tools for interacting with GitHub Issues API. Can fetch JSON of a GitHub issue.")
class GitHubIssueToolset : ToolSet {
@Tool("get_github_issue_contents")
@LLMDescription("Fetch the JSON of a GitHub issue and return it as a raw string.")
suspend fun getGitHubIssueContents(
@LLMDescription("Repository owner or organization, e.g., 'octocat'.")
owner: String,
@LLMDescription("Repository name, e.g., 'hello-world'.")
repo: String,
@LLMDescription("Issue number in the repository.")
issueNumber: Int,
@LLMDescription("Optional GitHub token. If omitted, GITHUB_TOKEN env variable will be used.")
token: String? = null,
): String =
GitHubIssueClient.getGitHubIssueContents(
owner,
repo,
issueNumber,
token
)
}
Slide 82
Slide 82 text
Plugging it in
AIAgent(
executor = simpleOpenRouterExecutor(ApiKeys.openRouter),
systemPrompt = """Answer the user's question
|about a specific GitHub issue using tools.""".trimMargin(),
llmModel = OpenAIModels.Chat.GPT5,
toolRegistry = ToolRegistry {
tools(GitHubIssueToolset())
},
strategy = oneShotStrategy,
)
Slide 83
Slide 83 text
Let's run it!
Slide 84
Slide 84 text
External tools in Koog via MCP
• AI Tool communication protocol
• stdio or server-sent events
Slide 85
Slide 85 text
MCP server inspiration
Slide 86
Slide 86 text
Adding MCP
val process = ProcessBuilder("path/to/mcp/server").start()
val stdioTransport =
McpToolRegistryProvider.defaultStdioTransport(process)
val sseTransport =
McpToolRegistryProvider.defaultSseTransport(
"http://localhost:8931"
)
val toolRegistry = McpToolRegistryProvider.fromTransport(
transport = yourTransport,
name = "my-client",
version = "1.0.0"
)
Slide 87
Slide 87 text
Koog also covers advanced
use cases!
Slide 88
Slide 88 text
Agents as tools
takes
String
returns
String
val tool = myAgent.asTool(/*...*/)
Slide 89
Slide 89 text
Not just String → String!
val typedStrategy = strategy("Calculation") {
val nodeToNumber by node { it.split(" ").sumOf { it.toInt() } }
edge(nodeStart forwardTo nodeToNumber)
edge(nodeToNumber forwardTo nodeFinish)
}
val typedAgent = AIAgent(
inputType = typeOf(),
outputType = typeOf(),
promptExecutor = simpleOpenRouterExecutor(ApiKeys.openRouter),
strategy = typedStrategy,
agentConfig = AIAgentConfig.withSystemPrompt(prompt = "You are..."),
)
val result: Int = typedAgent.run("5 7 10")
Slide 90
Slide 90 text
Structured data processing
@Serializable
data class WeatherForecast(
val temperature: Int,
val conditions: String,
val precipitation: Int
)
Slide 91
Slide 91 text
Structured data processing
@Serializable
@SerialName("WeatherForecast")
@LLMDescription("Weather forecast for a given location")
data class WeatherForecast(
@property:LLMDescription("Temperature in Celsius")
val temperature: Int,
@property:LLMDescription("Weather conditions (e.g., sunny, cloudy, rainy)")
val conditions: String,
@property:LLMDescription("Chance of precipitation in percentage")
val precipitation: Int
)
node
LLMRequest
node
LLMRequestStructured
Slide 92
Slide 92 text
History compression
• LLM APIs are $/token
• LLMs have limited context windows
Slide 93
Slide 93 text
• Different strategies to remove unnecessary
information from LLM message history
– WholeHistory
– FromLastNMessages
– Chunked
node
LLM
CompressHistory
Slide 94
Slide 94 text
Observability / Tracing
• Insights into what's happening inside your
agent via the tracing module
• Integration with OpenTelemetry
Slide 95
Slide 95 text
Supporting advanced use cases
• Memory: Concepts & Facts management
• Content moderation
• Ranked Document Storage for RAG
• Semantic meaning via Embeddings
• Testing & Mocking
Slide 96
Slide 96 text
Koog runs on phones and servers!
• You can write and run Koog agents to run on
Android phones!
• Koog doesn't do inference by itself – it uses
APIs for that
• Agents themselves aren't that
computationally heavy!
Slide 97
Slide 97 text
koog.ai
youtube.com/kotlin
Slide 98
Slide 98 text
Concluding highlights
• AI Tooling helps you work with Kotlin!
– IDE features like completion and next edit suggestions help write code
– AI Assistant provides project insights and edits
– Junie, the JetBrains AI agent, can write full features end-to-end
• Koog makes building AI agents idiomatic
– It's superpower is composability via graphs!
– It type-safely integrates into 3rd party systems and your own systems,
via tools, MCP & co.
– It's designed to scale, with features like history compression,
observability integrations, and tracing.
– Koog becomes more powerful day by day!
Slide 99
Slide 99 text
Come visit the JetBrains booth!
Enjoy DroidKaigi!
Márton
Braun
@zsmb13
Sebastian
Aigner
@sebi_io