Practical notes: Java AI in 2026, LangChain4j Turns Agents into Ordinary

This walkthrough rebuilds the path from raw materials to a working system for: Java AI in 2026, LangChain4j Turns Agents into Ordinary Interfaces. The focus is operable steps, explicit checks, and code that you can drop into a repo without guessing intent. For the Overview stage, define the inputs, the owner of the step, and the exit criteria before changing code. Operators should be able to re-run the step from a known checkpoint without guessing hidden state. Record timings and token or query cost next to functional results. Cost visibility early prevents surprise bills when the path moves from demo to shared environments.

Start with the most annoying layer: let the model call your business methods

When working through the Start with the most stage, write down the contract first: required inputs, success signal, and what happens on partial failure. That checklist keeps later code changes honest. Keep configuration outside application code. Environment files, secret stores, and feature flags belong in one place operators can audit without reading the whole graph. Cache stable system instructions and tool schemas. Re-sending identical preamble is a common source of burn.

<dependency>
  <groupId>dev.langchain4j</groupId>
  <artifactId>langchain4j-open-ai</artifactId>
  <version>1.19.0</version>
</dependency>
<dependency>
  <groupId>dev.langchain4j</groupId>
  <artifactId>langchain4j-agentic</artifactId>
  <version>1.19.0</version>
</dependency>
<dependency>
  <groupId>dev.langchain4j</groupId>
  <artifactId>langchain4j-skills</artifactId>
  <version>1.19.0-beta29</version>
</dependency>

class OrderTools {

    @Tool("Look up the status of an order by ID")
    String queryOrder(@P("Order ID") String orderId) {
        return "Order " + orderId + " has shipped and should arrive tomorrow";
    }
    @Tool("Refund the specified order")
    String refund(@P("Order ID") String orderId, @P("Refund reason") String reason) {
        return "Order " + orderId + " refund initiated. Reason: " + reason;
    }
}

interface CustomerServiceAssistant {

@UserMessage("You are an e-commerce customer service assistant. Answer questions about orders and refunds. The customer's question is {{question}}")
    String answer(String question);
}
CustomerServiceAssistant assistant = AiServices.builder(CustomerServiceAssistant.class)
        .chatModel(model)
        .tools(new OrderTools())
        .chatMemory(MessageWindowChatMemory.withMaxMessages(20))
        .build();
String reply = assistant.answer("Where is order 20260907001?");

An agent is an interface plus a shared scope

When working through the An agent is an stage, write down the contract first: required inputs, success signal, and what happens on partial failure. That checklist keeps later code changes honest. Document the happy path and the recovery path together. Retries, human gates, and dead-letter handling are part of the product, not later polish. Checkpoint after expensive steps. Resume should not re-bill the same LLM call when an operator retries a later node.

public interface DraftWriter {

@UserMessage("""
            You are a technical editor. Write an opening of no more than 200 words on the topic {{topic}}.
            Return only the opening, with no explanation.
            """)
    @Agent(outputKey = "draft", description = "Writes an opening based on a topic")
    String write(@V("topic") String topic);
}

public interface Sharpener {
    @UserMessage("""
            You are a reviewer. Make the following opening more specific and remove filler.
            The opening is {{draft}}.
            Return only the revised text.
            """)
    @Agent(outputKey = "draft", description = "Makes the opening more specific")
    String polish(@V("draft") String draft);
}

public interface TitlePicker {
    @UserMessage("""
            Write 3 headlines suitable for a technical blog for the following content, one per line.
            The content is {{draft}}.
            """)
    @Agent(outputKey = "titles", description = "Writes headlines for the content")
    String pickTitle(@V("draft") String draft);
}

DraftWriter writer = AgenticServices
        .agentBuilder(DraftWriter.class)
        .chatModel(model)
        .build();


Sharpener sharpener = AgenticServices
        .agentBuilder(Sharpener.class)
        .chatModel(model)
        .build();
TitlePicker titlePicker = AgenticServices
        .agentBuilder(TitlePicker.class)
        .chatModel(model)
        .build();
UntypedAgent editor = AgenticServices
        .sequenceBuilder()
        .subAgents(writer, sharpener, titlePicker)
        .outputKey("titles")
        .build();
Object result = editor.invoke(Map.of("topic", "Building agents with LangChain4j"));

Skills are on-demand instructions, not an @Skill annotation

When working through the Skills are on-demand instructions stage, write down the contract first: required inputs, success signal, and what happens on partial failure. That checklist keeps later code changes honest. Prefer small, testable units over sprawling scripts. When a step fails, the failure should point at a single responsibility rather than a tangled pipeline. Checkpoint after expensive steps. Resume should not re-bill the same LLM call when an operator retries a later node. When working through the Skills are on-demand instructions stage, write down the contract first: required inputs, success signal, and what happens on partial failure. That checklist keeps later code changes honest. Record timings and token or query cost next to functional results. Cost visibility early prevents surprise bills when the path moves from demo to shared environments.

skills/refund/SKILL.md

---
name: refund
description: Handle refund requests. Look up the order, check the conditions, then either refund or escalate to a human.
---
When a customer requests a refund:
1. First call queryOrder to check the order status.
2. Only call refund when the order has shipped or is complete.
3. If the order is still awaiting payment, tell the customer to cancel it.
4. If the amount exceeds 500, escalate to a human instead of refunding directly.

List<FileSystemSkill> loadedSkills = FileSystemSkillLoader.loadSkills(Path.of("skills"));
Skills skillSet = Skills.from(loadedSkills);

CustomerServiceAssistant assistant = AiServices.builder(CustomerServiceAssistant.class)
        .chatModel(model)
        .chatMemory(MessageWindowChatMemory.withMaxMessages(20))
        .tools(new OrderTools())
        .toolProvider(skillSet.toolProvider())
        .systemMessage("You have access to the following skills. When a request relates to one of them, activate it first.\n"
                + skillSet.formatAvailableSkills())
        .build();

Long workflows must be able to pause and resume

The Long workflows must be stage works best when treated as a measurable surface. Capture one golden transcript, one failure case, and the rollback note before expanding scope. Keep configuration outside application code. Environment files, secret stores, and feature flags belong in one place operators can audit without reading the whole graph. Keep graph state flat and typed. Nested blobs hide which node wrote which field and break resume after interrupts.

public interface OrderWorkflow extends AgenticScopeAccess {

    @Agent
    String processOrder(@MemoryId String orderId, @V("order") String orderDetails);
}

AgenticScopeAction validateOrder = AgenticServices.agentAction(scope -> {
    String order = scope.readState("order", "");
    scope.writeState("validated_order", "VALIDATED: " + order);
});


HumanInTheLoop approvalGate = AgenticServices.humanInTheLoopBuilder()
        .description("Large orders require manual approval")
        .outputKey("approval")
        .responseProvider(scope -> new SuspendedResponse<>("manager-approval"))
        .build();
AgenticScopeAction shipOrder = AgenticServices.agentAction(scope -> {
    String validated = scope.readState("validated_order", "");
    String approval = scope.readState("approval", "");
    scope.writeState("result", "Order processed " + approval);
});
OrderWorkflow workflow = AgenticServices.sequenceBuilder(OrderWorkflow.class)
        .subAgents(validateOrder, approvalGate, shipOrder)
        .outputKey("result")
        .build();

ResultWithAgenticScope<String> result =
        workflow.processOrder("order-10001", "1000 units");

if (result.suspended()) {
    result = result.completePendingResponse("Manager approved");
}

AgenticScopePersister.setStore(new MyAgenticScopeStore());

A2A lets remote agents work as local building blocks

The A2A lets remote agents stage works best when treated as a measurable surface. Capture one golden transcript, one failure case, and the rollback note before expanding scope. Document the happy path and the recovery path together. Retries, human gates, and dead-letter handling are part of the product, not later polish. Keep graph state flat and typed. Nested blobs hide which node wrote which field and break resume after interrupts.

<dependency>
  <groupId>dev.langchain4j</groupId>
  <artifactId>langchain4j-agentic-a2a</artifactId>
  <version>1.19.0</version>
</dependency>

public interface RemoteRiskAgent {


@Agent
    String check(@V("transaction") String transaction);
}
UntypedAgent riskAgent = AgenticServices
        .a2aBuilder("https://risk.internal/a2a", RemoteRiskAgent.class)
        .outputKey("risk_result")
        .build();

public interface ChatAgent {


@A2AClientAgent(a2aServerUrl = "http://localhost:8080", outputKey = "response")
    ResultWithAgenticScope<String> chat(
            @V("question") String question,
            @A2AContextId @V("contextId") String contextId,
            @A2ATaskId @V("taskId") String taskId);
}
ResultWithAgenticScope<String> first = chatAgent.chat("Hello", null, null);
String contextId = (String) first.agenticScope().readState("contextId");
String taskId = (String) first.agenticScope().readState("taskId");
ResultWithAgenticScope<String> second = chatAgent.chat("Continue", contextId, taskId);

Three practical recommendations for Java teams

The Three practical recommendations for stage works best when treated as a measurable surface. Capture one golden transcript, one failure case, and the rollback note before expanding scope. Prefer small, testable units over sprawling scripts. When a step fails, the failure should point at a single responsibility rather than a tangled pipeline. Keep graph state flat and typed. Nested blobs hide which node wrote which field and break resume after interrupts. The Three practical recommendations for stage works best when treated as a measurable surface. Capture one golden transcript, one failure case, and the rollback note before expanding scope. Record timings and token or query cost next to functional results. Cost visibility early prevents surprise bills when the path moves from demo to shared environments.

Operational checklist

The Operational checklist stage works best when treated as a measurable surface. Capture one golden transcript, one failure case, and the rollback note before expanding scope.

Treat this stage as a contract between inputs and validated outputs. Name the artifacts, define success checks, and refuse silent partial completion.

Keep graph state flat and typed. Nested blobs hide which node wrote which field and break resume after interrupts.

Add a smoke test that exercises the critical path in CI with fixtures, not live paid APIs, whenever budgets allow.

Record timings and token or query cost next to functional results. Cost visibility early prevents surprise bills when the path moves from demo to shared environments.

Keep graph state flat and typed. Nested blobs hide which node wrote which field and break resume after interrupts.

Before promoting the stack, freeze versions, capture a golden transcript for the critical path, and confirm rollback steps. Shared environments need rate limits, tenancy checks, and a clear owner for secret rotation. Prefer boring reliability over clever one-off demos.

Batch note for cd02c3f21b63: keep provider keys out of the repo, set a per-session token ceiling, and store transcripts next to the eval fixtures so later model swaps stay comparable.