Devvox Belgium - Agentic AI Patterns

Transcript

1. 1 Mario Fusco, IBM Kevin Dubois, IBM Agentic AI Patterns
2. Foundation Memory AI Services Function calling Workflow & Patterns Chaining Parallelization Looping Goal-based Autonomy Planning Multi-agent collaboration
3. It all starts with a single AI Service A Large Language Model is at the core of any AI-Infused Application … but this is not enough. Application LLM
4. It all starts with a single AI Service LLM Application A Large Language Model is at the core of any AI-Infused Application … but this is not enough. You also need: - Well crafted prompts guiding the LLM in the most precise and least ambiguous possible ways Prompts
5. It all starts with a single AI Service LLM Application A Large Language Model is at the core of any AI-Infused Application … but this is not enough. You also need: - Well crafted prompts guiding the LLM in the most precise and least ambiguous possible ways - A chat memory to "remember" previous interactions and make the AI service conversational Prompts Memory
6. It all starts with a single AI Service LLM Application A Large Language Model is at the core of any AI-Infused Application … but this is not enough. You also need: - Well crafted prompts guiding the LLM in the most precise and least ambiguous possible ways - A chat memory to "remember" previous interactions and make the AI service conversational - Data/Knowledge sources to provide contextual information (RAG) and persist the LLM state Prompts Memory Data Sources
7. Guardrails It all starts with a single AI Service LLM Application A Large Language Model is at the core of any AI-Infused Application … but this is not enough. You also need: - Well crafted prompts guiding the LLM in the most precise and least ambiguous possible ways - A chat memory to "remember" previous interactions and make the AI service conversational - Data/Knowledge sources to provide contextual information (RAG) and persist the LLM state - Guardrails to prevent malicious input and block wrong or unacceptable responses Prompts Memory Data Sources
8. Guardrails It all starts with a single AI Service LLM Application A Large Language Model is at the core of any AI-Infused Application … but this is not enough. You also need: - Well crafted prompts guiding the LLM in the most precise and least ambiguous possible ways - A chat memory to "remember" previous interactions and make the AI service conversational - Data/Knowledge sources to provide contextual information (RAG) and persist the LLM state - Guardrails to prevent malicious input and block wrong or unacceptable responses - External tools (function calling & MCP) expanding LLM capabilities and take responsibility for deterministic tasks where generative AI falls short Prompts Memory Tools Data Sources
9. From a single AI service to Agentic Systems Application 1 AI Service, 1 Model x AI Services, y Models, z Agents
10. From single AI Service to Agents and Agentic Systems In essence what makes an AI service also an Agent is the capability to collaborate with other Agents in order to perform more complex tasks and pursue a common goal Foundation Memory AI Services Function calling Workflow & Patterns Chaining Parallelization Looping Goal-based Autonomy Planning Multi-agent collaboration
11. The new langchain4j-agentic module LangChain4j 1.3.0 introduces a new (experimental) agentic module. All use cases discussed in this presentation are based on it.
12. Programmatic orchestration of agents The simplest way to glue agents together is programmatically orchestrating them in fixed and predetermined workflows 4 basic patterns that can be used as building blocks to create more complex interactions - Sequence / Prompt chaining - Loop / Reflection - Parallelization - Conditional / Routing
13. From single agents… public interface CreativeWriter { @UserMessage(""" You are a creative writer. Generate a draft of a story long no more than 3 sentence around the given topic. The topic is {topic}.""") @Agent("Generate a story based on the given topic") String generateStory(String topic); } public interface AudienceEditor { @UserMessage(""" You are a professional editor. Analyze and rewrite the following story to better align with the target audience of {audience}. The story is "{story}".""") @Agent("Edit a story to fit a given audience") String editStory(String story, String audience); } public interface StyleEditor { @UserMessage(""" You are a professional editor. Analyze and rewrite the following story to better fit and be more coherent with the {{style}} style. The story is "{story}".""") @Agent("Edit a story to better fit a given style") String editStory(String story, String style); Topic Story Audience Style Story Story
14. From single agents… public interface CreativeWriter { @UserMessage(""" You are a creative writer. Generate a draft of a story long no more than 3 sentence around the given topic. The topic is {topic}.""") @Agent("Generate a story based on the given topic") String generateStory(String topic); } public interface AudienceEditor { @UserMessage(""" You are a professional editor. Analyze and rewrite the following story to better align with the target audience of {audience}. The story is "{story}".""") @Agent("Edit a story to fit a given audience") String editStory(String story, String audience); } public interface StyleEditor { @UserMessage(""" You are a professional editor. Analyze and rewrite the following story to better fit and be more coherent with the {{style}} style. The story is "{story}".""") @Agent("Edit a story to better fit a given style") String editStory(String story, String style); Topic, Audience, Style Story
15. Defining the typed Agentic System public interface StoryGenerator { @Agent("Generate a story based on the given topic, for a specific audience and in a specific style") String generateStory(String topic, String audience, String style); } Our Agent System Interface (ASI): var story = storyGenerator.generateStory("dragons and wizards", "young adults", "fantasy");
16. Sequence Workflow - Defining agents var creativeWriter = AgenticServices.agentBuilder(CreativeWriter. class) .chatModel(myModel).outputName( "story") .build(); var audienceEditor = agentBuilder(AudienceEditor. class) .chatModel(myModel).outputName( "story").build(); var styleEditor = agentBuilder(StyleEditor. class) .chatModel(myModel).outputName( "story").build();
17. Sequence Workflow - Composing Agents var creativeWriter = AgenticServices.agentBuilder(CreativeWriter. class) .chatModel(myModel).outputName( "story") .build(); var audienceEditor = agentBuilder(AudienceEditor. class) .chatModel(myModel).outputName( "story").build(); var styleEditor = agentBuilder(StyleEditor. class) .chatModel(myModel).outputName( "story").build(); var storyGenerator = AgenticServices.sequenceBuilder( StoryGenerator .class) .subAgents( creativeWriter , audienceEditor , styleEditor) .outputName( "story").build(); Invoke the system using the StoryGenerator ASI
18. Sequence Workflow - Composing Agents public interface StoryGenerator { @Agent("...") String generateStory(String topic, String audience, String style); } var writer = agentBuilder(CreativeWriter. class) .chatModel(myModel).outputName( "story") .build(); var editor = agentBuilder(AudienceEditor. class) .chatModel(myModel).outputName( "story") .build(); var style = agentBuilder(StyleEditor. class) .chatModel(myModel).outputName( "story") .build(); var storyGenerator = sequenceBuilder( StoryGenerator .class) .subAgents( writer, editor, style).outputName("story").build();
19. Sequence Workflow - Composing Agents public interface StoryGenerator { @Agent("...") String generateStory(String topic, String audience, String style); } var writer = agentBuilder(CreativeWriter. class) .chatModel(myModel).outputName( "story") .build(); var editor = agentBuilder(AudienceEditor. class) .chatModel(myModel).outputName( "story") .build(); var style = agentBuilder(StyleEditor. class) .chatModel(myModel).outputName( "story") .build(); var storyGenerator = sequenceBuilder( StoryGenerator .class) .subAgents( writer, editor, style).outputName("story").build(); State topic audience style story
20. Introducing the AgenticScope Stores shared variables written by an agent to communicate the results it produced read by another agent to retrieve the necessary to perform its task Records the sequence of invocations of all agents with their responses Provides agentic system wide context to an agent based on former agent executions Persistable via a pluggable SPI A collection of data shared among the agents participating in the same agentic system State topic audience style story
21. Loop Workflow public interface StyleScorer { @UserMessage(""" You are a critical reviewer. Give a review score between 0.0 and 1.0 for the following story based on how well it aligns with the style '{style}'. Return only the score and nothing else. The story is: "{story}" """) @Agent("Score a story based on how well it aligns with a given style" ) double scoreStyle(String story, String style); }
22. Loop Workflow var styleScorer = agentBuilder( StyleScorer.class) .chatModel(myModel).outputName( "score").build(); UntypedAgent styleReviewLoop = loopBuilder() .subAgents( styleScorer, styleEditor) .maxIterations( 5) .exitCondition( scope -> scope.readState("score", 0.0) >= 0.8) .build(); var storyGenerator = sequenceBuilder(StoryGenerator. class) .subAgents(creativeWriter, styleReviewLoop ) .outputName( "story").build(); Creative Writer Style Scorer Style Editor Style Review Loop
23. Loop Workflow - Untyped Agent var styleScorer = agentBuilder( StyleScorer.class) .chatModel(myModel).outputName( "score").build(); UntypedAgent styleReviewLoop = loopBuilder() .subAgents( styleScorer, styleEditor) .maxIterations( 5) .exitCondition( scope -> scope.readState("score", 0.0) >= 0.8) .build(); var storyGenerator = sequenceBuilder(StoryGenerator. class) .subAgents(creativeWriter, styleReviewLoop ) .outputName( "story").build(); Creative Writer Style Scorer Style Editor Style Review Loop
24. Loop Workflow - Accessing the AgenticScope var styleScorer = agentBuilder( StyleScorer.class) .chatModel(myModel).outputName( "score").build(); UntypedAgent styleReviewLoop = loopBuilder() .subAgents( styleScorer, styleEditor) .maxIterations( 5) .exitCondition( scope -> scope.readState("score", 0.0) >= 0.8) .build(); var storyGenerator = sequenceBuilder(StoryGenerator. class) .subAgents(creativeWriter, styleReviewLoop ) .outputName( "story").build(); Creative Writer Style Scorer Style Editor Style Review Loop
25. Loop Workflow - Referencing workflow agent in workflows Creative Writer Style Scorer Style Editor Style Review Loop var styleScorer = agentBuilder( StyleScorer.class) .chatModel(myModel).outputName( "score").build(); UntypedAgent styleReviewLoop = loopBuilder() .subAgents( styleScorer, styleEditor) .maxIterations( 5) .exitCondition( scope -> scope.readState("score", 0.0) >= 0.8) .build(); var storyGenerator = sequenceBuilder(StoryGenerator. class) .subAgents(creativeWriter, styleReviewLoop ) .outputName( "story").build();
26. Parallel Workflow public interface EveningPlannerAgent { @Agent List<EveningPlan> plan(@V("mood") String mood); } public interface FoodExpert { @UserMessage(""" You are a great evening planner. Propose a list of 3 meals matching the given mood. The mood is {{mood}}. For each meal, just give the name of the meal. Provide a list with the 3 items and nothing else. """) @Agent List<String> findMeal(@V("mood") String mood); } public interface MovieExpert { @UserMessage(""" You are a great evening planner. Propose a list of 3 movies matching the given mood. The mood is {{mood}}. Provide a list with the 3 items and nothing else. """) @Agent List<String> findMovie(@V("mood") String mood); } EveningPlannerAgent eveningPlannerAgent = AgenticServices .parallelBuilder(EveningPlannerAgent.class) .subAgents(foodAgent, movieAgent) .outputName("plans") .output(agenticScope -> { List<String> movies = agenticScope.readState("movies"); List<String> meals = agenticScope.readState("meals"); List<EveningPlan> moviesAndMeals = new ArrayList<>(); for (int i = 0; i < movies.size(); i++) { if (i >= meals.size()) { break; } moviesAndMeals.add(new EveningPlan(movies.get(i), meals.get(i))); } return moviesAndMeals; }); List<EveningPlan> plans = eveningPlannerAgent.plan("romantic");
27. Routing public interface ExpertRouterAgent { @Agent String ask(@V("request") String request); } public enum RequestCategory { LEGAL, MEDICAL, TECHNICAL, UNKNOWN } public interface RouterAgent { @UserMessage(""" Analyze the user request and categorize it as 'legal', 'medical' or 'technical', The user request is: '{{request}}'. """) @Agent String askToExpert(@V("request") String request); } public interface MedicalExpert { @UserMessage(""" You are a medical expert. Analyze the user request under a medical point of view and provide the best possible answer. The user request is {{request}}. """) @Agent("A medical expert") String medical(@V("request") String request); } RouterAgent routerAgent = AgenticServices.agentBuilder(RouterAgent.class) .chatModel(myModel).outputName("category").build(); MedicalExpert medicalExpert = AgenticServices .agentBuilder(MedicalExpert.class) .chatModel(myModel).outputName("response").build()); LegalExpert legalExpert = ... TechnicalExpert techExpert = UntypedAgent expertsAgent = AgenticServices.conditionalBuilder() .subAgents(scope -> scope.readState("category",UNKNOWN) == MEDICAL, medicalExpert) .subAgents(scope -> scope.readState("category",UNKNOWN) == LEGAL, legalExpert) .subAgents(scope -> scope.readState("category",UNKNOWN) == TECHNICAL, techExpert) .build(); ExpertRouterAgent expertRouterAgent = AgenticServices .sequenceBuilder(ExpertRouterAgent.class) .subAgents(routerAgent, expertsAgent) .outputName("response").build(); expertRouterAgent.ask("I broke my leg what should I do")
28. Memory and context engineering - All agents discussed so far are stateless, meaning that they do not maintain any context or memory of previous interactions - AI Services can be provided with a ChatMemory, but this is local to the single agent, so in many cases not enough in a complex agentic system - In general an agent requires a broader context, carrying information about everything that happened in the agentic system before its invocation - That’s another task for the AgenticScope
29. DEMO TIME !!!
30. Foundation Memory AI Services Function calling Workflow & Patterns Chaining Parallelization Looping Goal-based Autonomy Planning Multi-agent collaboration
31. From AI Orchestration to Autonomous Agentic AI LLMs and tools are programmatically orchestrated through predefined code paths and workflows LLMs dynamically direct their own processes and tool usage, maintaining control over how they execute tasks Workflow Agents
32. An Autonomous Agentic AI case study – Supervisor pattern Input Response Supervisor Agent A Agent B Agent C Select and invoke (Agent Invocation) Agent result + State Determine if done or next invocation Pool of agents
33. An Autonomous Agentic AI case study – Supervisor pattern - All agentic systems explored so far orchestrated agents programmatically in a fully deterministic way - In some cases agentic system have to be more flexible and adaptive - An autonomous agentic AI system ◦ Takes autonomous decisions ◦ Decides iteratively which agent has to be invoked next ◦ Uses the result of previous interactions to determine if it is done and achieved its final goal ◦ Uses the context and state to generate the arguments to be passed to the selected agent
34. An Autonomous Agentic AI case study – Supervisor pattern Input Response Supervisor Agent A Agent B Agent C Agent result + State Determine if done or next invocation Pool of agents Done Select and invoke (Agent Invocation)
35. An Autonomous Agentic AI case study – Supervisor pattern Input Response Supervisor Agent A Agent B Agent C Agent result + State Determine if done or next invocation Pool of agents public record AgentInvocation( String agentName, Map<String, String> arguments) { } Done
36. Supervisor pattern - Planner public interface PlannerAgent { @SystemMessage( """ You are a planner expert that is provided with a set of agents. You know nothing about any domain, don't take any assumptions about the user request. Your role is to analyze the user request and decide which one of the provided agents to call next. You return an agent invocation consisting of the name of the agent and the arguments to pass to it. If no further agent requests are required, return an agentName of "done" and an argument named "response", where the value of the response argument is a recap of all the performed actions, written in the same language as the user request. Agents are provided with their name and description together with a list of applicable arguments in the format {name: description, [argument1, argument2]}. The comma separated list of available agents is: '{agents}'. Use the following optional supervisor context to better understand constraints, policies or preferences when creating the plan (can be empty): '{supervisorContext}'. """) @UserMessage("The user request is: '{req}'. The last received response is: '{lastResponse}'.") AgentInvocation plan(@MemoryId Object userId, String agents, String req, String lastResponse, String ctx); }
37. Supervisor pattern - Planner public interface PlannerAgent { @SystemMessage( """ You are a planner expert that is provided with a set of agents. You know nothing about any domain, don't take any assumptions about the user request. Your role is to analyze the user request and decide which one of the provided agents to call next. You return an agent invocation consisting of the name of the agent and the arguments to pass to it. If no further agent requests are required, return an agentName of "done" and an argument named "response", where the value of the response argument is a recap of all the performed actions, written in the same language as the user request. Agents are provided with their name and description together with a list of applicable arguments in the format {name: description, [argument1, argument2]}. The comma separated list of available agents is: '{agents}'. Use the following optional supervisor context to better understand constraints, policies or preferences when creating the plan (can be empty): '{supervisorContext}'. """) @UserMessage("The user request is: '{req}'. The last received response is: '{lastResponse}'.") AgentInvocation plan(@MemoryId Object userId, String agents, String req, String lastResponse, String ctx); } Definition of “done”
38. Supervisor pattern - Planner public interface PlannerAgent { @SystemMessage( """ You are a planner expert that is provided with a set of agents. You know nothing about any domain, don't take any assumptions about the user request. Your role is to analyze the user request and decide which one of the provided agents to call next. You return an agent invocation consisting of the name of the agent and the arguments to pass to it. If no further agent requests are required, return an agentName of "done" and an argument named "response", where the value of the response argument is a recap of all the performed actions, written in the same language as the user request. Agents are provided with their name and description together with a list of applicable arguments in the format {name: description, [argument1, argument2]}. The comma separated list of available agents is: '{agents}'. Use the following optional supervisor context to better understand constraints, policies or preferences when creating the plan (can be empty): '{supervisorContext}'. """) @UserMessage("The user request is: '{req}'. The last received response is: '{lastResponse}'.") AgentInvocation plan(@MemoryId Object userId, String agents, String req, String lastResponse, String ctx); } Passing the pool of agents
39. Supervisor pattern - Planner public interface PlannerAgent { @SystemMessage( """ You are a planner expert that is provided with a set of agents. You know nothing about any domain, don't take any assumptions about the user request. Your role is to analyze the user request and decide which one of the provided agents to call next. You return an agent invocation consisting of the name of the agent and the arguments to pass to it. If no further agent requests are required, return an agentName of "done" and an argument named "response", where the value of the response argument is a recap of all the performed actions, written in the same language as the user request. Agents are provided with their name and description together with a list of applicable arguments in the format {name: description, [argument1, argument2]}. The comma separated list of available agents is: '{agents}'. Use the following optional supervisor context to better understand constraints, policies or preferences when creating the plan (can be empty): '{supervisorContext}'. """) @UserMessage("The user request is: '{req}'. The last received response is: '{lastResponse}'.") AgentInvocation plan(@MemoryId Object userId, String agents, String req, String lastResponse, String ctx); } User message of the planner
40. An Autonomous Agentic AI case study – Supervisor pattern Input Response Planner Agent A Agent B Agent C Agent result Agentic Scope (Invocations +results) Pool of agents Done? Response Scorer Response Strategy State Scores Last, Score, Summary Input, response, action summary
41. Supervisor pattern at work - Pool of agents public interface WithdrawAgent { @SystemMessage("You are a banker that can only withdraw Swiss Francs (CHF) from a user account.") @UserMessage("Withdraw {amountInCHF} CHF from {withdrawUser}'s account and return the new balance.") @Agent("A banker that withdraws CHF from an account") String withdraw(String withdrawUser, Double amountInCHF); } public interface CreditAgent { @SystemMessage("You are a banker that can only credit Swiss Francs (CHF) to a user account.") @UserMessage("Credit {amountInCHF} CHF to {creditUser}'s account and return the new balance.") @Agent("A banker that credit CHF to an account") String credit(String creditUser, Double amountInCHF); } public interface ExchangeAgent { @UserMessage(""" You are an operator exchanging money in different currencies. Use the tool to exchange {amount} {originalCurrency} into {targetCurrency} returning only the final amount provided by the tool as it is and nothing else. """) @Agent("A money exchanger that converts a given amount from the original to the target currency") Double exchange(String originalCurrency, Double amount, String targetCurrency); }
42. Supervisor pattern at work - Creating the system BankTool bankTool = new BankTool(); bankTool.createAccount("Mario",1000.0); bankTool.createAccount("Kevin",1000.0); WithdrawAgent withdrawAgent = AgenticServices.agentBuilder(WithdrawAgent.class) .chatModel(myModel).tools(bankTool).build(); CreditAgent creditAgent = AgenticServices.agentBuilder(CreditAgent.class) .chatModel(myModel).tools(bankTool).build(); ExchangeAgent exchange = AgenticServices.agentBuilder(ExchangeAgent.class) .chatModel(myModel).tools(new ExchangeTool()).build(); SupervisorAgent bankSupervisor = AgenticServices.supervisorBuilder() .chatModel(plannerModel).subAgents(withdrawAgent, creditAgent, exchange).build();
43. Supervisor pattern at work 100 EUR has been transferred from Mario's account to Kevin's account. Kevin's account has been credited with 95.0 CHF, and the new balance is 1095.0 CHF. The withdrawal of 95.0 CHF from Mario's account has been completed, and the new balance is 905.0 CHF. var result = bankSupervisor .invoke("Transfer 100 EUR from Mario's account to Kevin's" ); System.out.println(result);
44. Supervisor pattern - Agent Invocation Sequence public interface PlannerAgent { @SystemMessage( """ … """) @UserMessage("The user request is: '{req}'. The last received response is: '{lastResponse}'.") AgentInvocation plan(@MemoryId Object userId, String agents, String req, String lastResponse, String ctx); } AgentInvocation{agentName='exchange', arguments={originalCurrency=EUR, amount=100, targetCurrency=CHF}} AgentInvocation{agentName='credit', arguments={creditUser=Kevin, amountInUSD=95.0}} AgentInvocation{agentName='withdraw', arguments={withdrawUser=Mario, amountInUSD=95.0}} AgentInvocation{agentName='done', arguments={response=100 EUR has been transferred from Mario's account to Kevin's account. Kevin's account has been credited with 95.0 CHF, and the new balance is 1095.0 CHF. The withdrawal of 95.0 CHF from Mario's account has been completed, and the new balance is 905.0 CHF.}
45. Other langchain4j-agentic features ➢ Error handling and recovery strategies UntypedAgent novelCreator = AgenticServices.sequenceBuilder() .subAgents(creativeWriter, audienceEditor, styleEditor) .errorHandler(errorContext -> { if (errorContext.agentName().equals( "generateStory" ) && errorContext.exception() instanceof MissingArgumentException mEx && mEx.argumentName().equals("topic")) { errorContext.agenticScope().writeState( "topic", "dragons and wizards" ); return ErrorRecoveryResult.retry(); } return ErrorRecoveryResult.throwException(); }) .outputName("story") .build();
46. Other langchain4j-agentic features ➢ Error handling and recovery strategies ➢ Programmatic non-AI agents public class ExchangeOperator { @Agent("A money exchanger that converts a given amount of money from the original to the target currency" ) public Double exchange( @V("originalCurrency" ) String originalCurrency, @V("amount") Double amount, @V("targetCurrency" ) String targetCurrency) { // invoke the REST API to perform the currency exchange } }
47. Other langchain4j-agentic features HumanInTheLoop humanInTheLoop = AgenticServices.humanInTheLoopBuilder() .description( "An agent that asks the audience for the story" ) .inputName( "topic") .outputName( "audience") .requestWriter(topic -> { System.out.println( "Which audience for topic " + topic + "?"); System.out.print( "> "); }) .responseReader(() -> System.console().readLine()) .build(); ➢ Error handling and recovery strategies ➢ Programmatic non-AI agents ➢ Human-in-the-loop
48. Other langchain4j-agentic features FoodExpert foodExpert = AgenticServices .agentBuilder(FoodExpert. class) .chatModel(baseModel()) .async( true) .outputName("meals") .build(); ➢ Error handling and recovery strategies ➢ Programmatic non-AI agents ➢ Human-in-the-loop ➢ Asynchronous agents
49. Other langchain4j-agentic features CreativeWriter creativeWriter = AgenticServices.a2aBuilder(A2A_SERVER_URL, CreativeWriter. class) .outputName( "story") .build(); ➢ Error handling and recovery strategies ➢ Programmatic non-AI agents ➢ Human-in-the-loop ➢ Asynchronous agents ➢ A2A integration
50. Other langchain4j-agentic features ➢ Error handling and recovery strategies ➢ Programmatic non-AI agents ➢ Human-in-the-loop ➢ Asynchronous agents ➢ A2A integration ➢ Comprehensive Declarative API public interface StyleReviewLoopAgent { @LoopAgent( description = "Review the story for the given style" , outputName = "story", maxIterations = 5, subAgents = { @SubAgent(type = StyleScorer. class, outputName = "score"), @SubAgent(type = StyleEditor. class, outputName = "story") } ) String write( @V("story") String story); @ExitCondition static boolean exit(@V("score") double score) { return score >= 0.8; } }
51. Other langchain4j-agentic features ➢ Error handling and recovery strategies ➢ Programmatic non-AI agents ➢ Human-in-the-loop ➢ Asynchronous agents ➢ A2A integration ➢ Comprehensive Declarative API ➢ CDI support (via Quarkus extension) public interface StoryCreator { @SequenceAgent (outputName = "story", subAgents = { @SubAgent(type = CreativeWriter. class), @SubAgent(type = AudienceEditor. class), @SubAgent(type = StyleEditor. class) }) String write( @V("topic") String topic, @V("style") String style, @V("audience") String audience); } @Inject StoryCreator storyCreator;
52. What did we see and didn’t see? From AI-Infused to pure agentic https://docs.langchain4j.dev/ tutorials/agents https://docs.quarkiverse.io/ Quarkus-langchain4j https://quarkus.io/ quarkus-workshop-langchain4j Langchain4J Quarkus DECLARATIVE API MEMORY Workflow SUPERVISOR CONTEXT MCP FUNCTION CALLING Agentic MODELS OBSERVABILITY RESILIENCE agent Slides State Scope A2A PROGRAMMATIC AGENT HUMAN-IN-THE-LOOP PlanNer SPI Workflow SPI
53. https://github.com/quarkusio/quarkus/discussions/49392
 Picocli: put some Java in your terminal!
 Mon
 TIA
 Building secure AI agents with Quarkus LangChain4j
 Hands on
 Mon
 30 minutes to understand MCP
 TIA
 Mon
 From LLM orchestration to autonomous agents
 Deep Dive
 Tue
 Going serverless with Quarkus, GraalVM native images and AWS Lambda
 Deep Dive
 Tue
 Build your own Java-powered Agentic Apps
 Tue
 Hands on
 On standards and AI agents
 Deep Dive
 Tue
 The Road Not Taken: A Developer's Guide to Life Beyond Spring Boot
 Wed
 Conf
 Quarkus Community BOF
 Wed
 BOF
 6.5 ridiculous things to do with Quarkus
 Thu
 Conf
 Quarkus: The Bold, the Broken, and the Burned
 Thu
 Conf
 Things You Thought You Didn’t Need To Care About That Have a Big Impact On Your Job
 Thu
 Conf
 Agentic AI Patterns
 Thu
 Conf
 MCP in Action: Connecting AI to Enterprise Systems
 Thu
 Conf
 Panel Discussion: LangChain4j Turns Two
 Thu
 Conf
 LangChain4j Community BOF
 BOF
 Thu
 Quarkus Unleashed
 Fri
 Conf
 From AI-Infused to Agentic
 Wed
 Conf
 Local Development in the AI Era
 Conf
 Fri
 Breaking Down the AI Silos
 Thu
 Conf
 Behavioral Software Engineering
 Fri
 Conf