--- title: The Self-Building Agent: A LangChain4j Experiment description: An experiment where a code assistant was prompted to design and implement a multi-agent coding system using LangChain4j documentation. The resulting system... canonical: https://daily.dev/posts/the-self-building-agent-a-langchain4j-experiment-wwvoelmj0 twitter:card: summary_large_image twitter:site: @dailydotdev og:type: website og:site_name: daily.dev og:title: The Self-Building Agent: A LangChain4j Experiment | daily.dev og:description: An experiment where a code assistant was prompted to design and implement a multi-agent coding system using LangChain4j documentation. The resulting system... og:url: https://daily.dev/posts/the-self-building-agent-a-langchain4j-experiment-wwvoelmj0 og:image: https://api.daily.dev/og/posts/wWVoElmj0.png og:image:alt: The Self-Building Agent: A LangChain4j Experiment og:image:width: 1200 og:image:height: 630 og:locale: en --- > ## Documentation Index > Fetch the complete documentation index at: https://daily.dev/llms.txt > Use this file to discover all available pages before exploring further. # The Self-Building Agent: A LangChain4j Experiment **[InfoQ](https://daily.dev/sources/infoq)** · 15 min read · 1 upvotes · 0 comments ## Summary An experiment where a code assistant was prompted to design and implement a multi-agent coding system using LangChain4j documentation. The resulting system used a supervisor pattern with four specialized sub-agents (explorer, planner, implementer, executor) to autonomously fix bugs in a Java Calculator class, passing all 11 tests. A second workflow-based implementation was then built, proving three times faster than the supervisor approach by eliminating LLM coordination overhead. The article also covers LangChain4j's new MonitoredAgent interface for observability, and highlights how model quality matters — an older model got stuck in a tool-calling loop while a newer one succeeded. ## Full article daily.dev links to this article rather than hosting it. Read it at the original source: ## Questions this post answers ### Which agentic pattern is faster in LangChain4j, supervisor or workflow? The workflow pattern executes roughly three times faster than the supervisor pattern in a debugging task comparison, completing in about two minutes versus more than six minutes. The speed difference comes from eliminating LLM-induced coordination overhead, since the workflow pattern relies on a deterministic, predefined sequence of steps rather than an autonomous agent generating invocations on the fly. _daily.dev surfaces comparisons like this for developers choosing between agentic coding architectures._ ### What does the MonitoredAgent interface do in LangChain4j? MonitoredAgent, introduced in LangChain4j agentic version 1.12.2-beta22, lets a root agent interface expose a report of agent invocations alongside the system topology when the interface extends it. This gives developers visibility into how a multi-agent system actually executes, useful for debugging and understanding complex agent orchestration. _track new LangChain4j observability features on daily.dev as agentic tooling keeps evolving._ ### Why did an LLM-based coding agent get stuck in a tool-calling loop with gpt-4o in LangChain4j? Using OpenAI's gpt-4o as both supervisor and coding agent caused the system to exceed LangChain4j's default limit of 100 sequential tool invocations, throwing an AgentInvocationException. Switching the same agent design to the newer gpt-5-mini model resolved the issue and let the system complete the bug-fix task successfully, suggesting model capability affected tool-calling reliability. _developers debugging agent tool-calling loops can follow model-specific findings like this on daily.dev._ ## Similar posts on daily.dev - [Agent Orchestration with LangChain4J – Inside.java](https://daily.dev/posts/agent-orchestration-with-langchain4j-inside-java-mu9edr4zb) · Inside Java · 1 upvotes · 0 comments --- Tags: [#llm](https://daily.dev/tags/llm), [#java](https://daily.dev/tags/java), [#ai-agents](https://daily.dev/tags/ai-agents), [#langchain4j](https://daily.dev/tags/langchain4j) [View this post on daily.dev](https://daily.dev/posts/the-self-building-agent-a-langchain4j-experiment-wwvoelmj0) ```json {"@context":"https://schema.org","@graph":[{"@type":"Organization","@id":"https://daily.dev/#organization","name":"daily.dev","url":"https://daily.dev","logo":{"@type":"ImageObject","url":"https://daily.dev/apple-touch-icon.png","width":180,"height":180},"sameAs":["https://twitter.com/dailydotdev","https://github.com/dailydotdev","https://www.linkedin.com/company/daily-dev-ltd"]},{"@type":"WebSite","@id":"https://daily.dev/#website","url":"https://daily.dev","name":"daily.dev","publisher":{"@id":"https://daily.dev/#organization"},"potentialAction":{"@type":"SearchAction","target":{"@type":"EntryPoint","urlTemplate":"https://daily.dev/search?q={search_term_string}"},"query-input":"required name=search_term_string"}}]} {"@context":"https://schema.org","@type":"TechArticle","headline":"The Self-Building Agent: A LangChain4j Experiment","url":"https://daily.dev/posts/the-self-building-agent-a-langchain4j-experiment-wwvoelmj0","mainEntityOfPage":{"@type":"WebPage","@id":"https://daily.dev/posts/the-self-building-agent-a-langchain4j-experiment-wwvoelmj0"},"datePublished":"2026-07-24T09:06:05.852Z","dateModified":"2026-07-25T04:18:42.715Z","description":"An experiment where a code assistant was prompted to design and implement a multi-agent coding system using LangChain4j documentation. The resulting system...","image":"https://media.daily.dev/image/upload/f_auto,q_auto/v1/posts/fd59cbd0def1d65f31a0179b2c630cab?_a=AQAEuop","thumbnailUrl":"https://media.daily.dev/image/upload/f_auto,q_auto/v1/posts/fd59cbd0def1d65f31a0179b2c630cab?_a=AQAEuop","isAccessibleForFree":true,"articleSection":"InfoQ","inLanguage":"en","publisher":{"@type":"Organization","name":"daily.dev","url":"https://daily.dev","logo":{"@type":"ImageObject","url":"https://daily.dev/apple-touch-icon.png","width":180,"height":180}},"author":{"@type":"Organization","name":"InfoQ","logo":"https://media.daily.dev/image/upload/t_logo,f_auto/v1/logos/afc3bced3e1e4b188dd9127017a60e0c","url":"https://daily.dev/sources/infoq"},"commentCount":0,"discussionUrl":"https://daily.dev/posts/the-self-building-agent-a-langchain4j-experiment-wwvoelmj0","interactionStatistic":[{"@type":"InteractionCounter","interactionType":{"@type":"LikeAction"},"userInteractionCount":1},{"@type":"InteractionCounter","interactionType":{"@type":"CommentAction"},"userInteractionCount":0}],"keywords":"llm,java,ai-agents,langchain4j","timeRequired":"PT15M"} {"@context":"https://schema.org","@type":"BreadcrumbList","itemListElement":[{"@type":"ListItem","position":1,"name":"Home","item":"https://daily.dev"},{"@type":"ListItem","position":2,"name":"InfoQ","item":"https://daily.dev/sources/infoq"},{"@type":"ListItem","position":3,"name":"The Self-Building Agent: A LangChain4j Experiment"}]} ```