GenAI and Java: A One-Year Retrospective - GeeCON 2026

One year ago at GeeCON (2025), I presented “Say ‘Hi!’ to Spring AI and LangChain4j”, introducing these tools as the new frontier for Java developers. But 12 months in the AI space feels like an eternity. Since then, the landscape has exploded with the Model Context Protocol (MCP), Agentic Systems, and a wave of new tools. Once again, let’s look beyond the buzzwords. It is time to verify if we are ready to take these shiny new toys out of the safe haven of conference demos and into the harsh reality of production environments. Join me as we seek answers to critical questions:

- How has the GenAI landscape truly changed over the last year?
- Are GenAI solutions ready for enterprise-grade systems without keeping architects up at night?
- Has a clear leader emerged among AI frameworks?
- Has the industry finally addressed security, performance, and testability concerns?
- How do we design systems where deterministic logic meets probabilistic models?

All of this will be backed by real-world stories, examples, and lessons learned from the trenches.

Transcript

1. GenAI and Java: A One-Year Retrospective Piotr Łaskawiec
2. Say ‚Hi’ to Spring AI and LangChain4j YouTube
3. SLI.DO #geecon
4. Dual challenge of AI revolution
5. Building with AI vs Building for AI
6. • Pragmatic Software Architect • Creating software for nearly 20 years • Founder of • Helping companies to deliver real value • Occasional speaker and trainer @piotrl a sk a wiec @piotrl a sk a wiec.bsky.soci a l COMSENITY LET'S CONNECT Prompt: „Describe me in 5 concise bullet points” COMSENITY
7. Completion REST API Prompt Roles User/System Not st a nd a rdized St a teless Ch a t Memory Structured Output Pre-tr a ined System Inter a ctions Context D a t a V a rious Input Types V a rious Output Types Request/Response Stre a ming Fr a mework Integr a tion Observ a bility Test a bility … Security
8. LangChain4j
9. • From pre- f in a l in M a y 2025 to st a ble 1.1.6, Spring AI 2.0.0 M6 a lre a dy a v a il a ble • Deep integr a tion with Spring ecosystem • Out-of-the-box support for building MCP servers • Spring AI Community GitHub org a niz a tion • Agents, Skills, gu a rdr a ils (vi a a dvisors) LangChain4j • From pre- f in a l in M a y 2025 to st a ble 1.14.1 • Spring Boot, Qu a rkus, Helidon integr a tions • Focused on MCP client-side, possible e.g. vi a Qu a rkus MCP Server • L a ngCh a in4j Community • Agents, Skills, gu a rdr a ils, E a syRAG
10. Demo #1
11. modelcontextprotocol.io
12. • Don a ted to the Agentic AI Found a tion (hosted by the Linux Found a tion) • ~9400 public MCP servers a s of April 2026 (~1200 in Q1 2025) • 78% of enterprise AI te a ms report a t le a st one MCP-b a cked a gent in production • 41% of enterprise AI te a ms h a ve a t le a st one custom intern a l MCP server • MCP Register, MCP Bundles, MCP Apps… • 2 m a jor spec revisions since M a y 2025 (June a nd November 2025) • Structure tool output • Elicit a tion • OAuth overh a ul (MCP servers a re now OAuth Resource Servers) + OpenID Connect Discovery • T a sks (still experiment a l) Source of st a ts: https://www.digit a l a pplied.com/blog/mcp- a doption-st a tistics-2026-model-context-protocol
13. • C a p a bilities • Resources - generic text/bin a ry d a t a ( f ile content, API responses, UI etc.) • Tools - execut a ble function a lities • Prompts - reus a ble templ a tes for users • Elicit a tion (new) - servers c a n p a use a nd a sk the user for missing input mid-c a ll • T a sks (new) - c a ll now, fetch l a ter - a sync h a ndles for long-running server work • S a mpling - f lips the f low - MCP server a sks the client's LLM for a completion, with the hum a n in the loop • Tr a nsports • Stdio • Stre a m a ble HTTP (new) • HTTP/SSE (leg a cy) • D a t a form a t - JSON-RPC 2.0
14. Swimming in acronyms soup AG-UI ACP A2UI A2A MCP Apps (MCP-UI) MCP AP2 UPC AI-xD XD
15. AI meets UI MCP Apps (MCP-UI) AG-UI A2UI
16. https://geecon.mcpserver.pl
17. Demo #2
20. Agentic AI
21. Let LLM do the job Agentic AI • Agentic AI softw a re - pursue complex go a ls with a high level of a utonomy • Orchestr a tion str a tegies: • Work f low - LLMs a nd Tools a re progr a mm a tic a lly orchestr a ted (well-de f ined control f low) • P a tterns: sequenti a l, loop, p a r a llel, condition a l • „Predict a ble” output, e a sier to test, f its for well-de f ined t a sks, less f lexible • Pure Agents - LLMs fully control the f low • LLM is responsible for choosing how to solve a given problem using a v a il a ble tools • Flexible, even less predict a ble, h a rder to control
23. CPU:GPU ratio 1:4-1:8
24. CPU:GPU ratio 1:1-1:2
25. Hype is loud. Production is harder. Agentic AI in 2026 - Reality Check • 72% of enterprises a re a lre a dy using or testing AI a gents • 17% of org a niz a tions h a ve deployed AI a gents to prod, 60%+ pl a n to within two ye a rs • 46% s a y the #1 ch a llenge isn't model intelligence - it's integr a tion with existing systems • 38% still keep hum a ns-in-the-loop a s the def a ult control p a ttern Source of st a ts: G a rtner Hype Cycle for Agentic AI 2026 · Z a pier St a te of Agentic AI Adoption 2026 · 2026 St a te of AI Agents Report · Snyk 2026 St a te of Agentic AI Adoption
26. Journey in the search of complexity Monoliths Microservices Modul a r Monoliths Non- Deterministic Interconnected Agents Too E a sy Too H a rd Too E a sy
27. Agentic Frameworks Spring AI LLM-driven, Work f low P a tterns L a ngCh a in4j LLM-driven, Work f low P a tterns L a ngGr a ph4j Cyclic a l St a teful Gr a phs Google ADK LLM-driven, Hier a rchic a l Work f low/LLM Agents Emb a bel Go a l-Oriented Action Pl a nning (GOAP) a nd Observe-Orient-Decide-Act (OODA) Loop Koog LLM-driven, GOAP pl a nning, Finite St a te M a chines (FSMs)
28. Quality attributes • Security • Test a bility • Correctness • Perform a nce • Observ a bility
29. Security • Att a cks • Prompt Injection • Prompt Le a king • J a ilbre a king • DoS • Defense is in your h a nds • Gu a rdr a ils
30. CVE-2026-35568 CVEs CVE-2025-54994 CVE-2025-53967 CVE-2025-68143 CVE-2026-22743 CVE-2026-22738 CVE-2026-22730 CVE-2026-22742 CVE-2026-22744 CVE-2025-21604 CVE-2025-32711 CVE-2025-6514 Source: thephilosophersmeme.com
32. Access to Sensitive Data Exposure to Untrusted Content Ability to Externally Communicate Vulnerability Lethal Trifecta
33. Performance • Perform a nce-Oriented Prompt Engineering (sic!) • SLAs in non-deterministic world m a y be h a rd to re a ch • Lot of moving p a rts
34. Testability • Simple checks • All required inform a tion provided in the a nswer • Proper tools were invoked • Token counts • How to test something th a t is inherently not deterministic? • M a ke it more deterministic • Fight f ire with f ire - AI Model Ev a lu a tion - LLM- a s- a -Judge
35. Correctness • H a llucin a tions • Writing a good prompt is a n a rt • Provide qu a lity context to the model • Retries • Rollb a cks (Compens a ting Actions) • HITL (Hum a n in the Loop)
36. Observability • Support for metrics a nd tr a ces (Sem a ntic Tr a ces) • Follows OTel „Sem a ntic conventions for gener a tive AI systems” (still in development) • Cost-control
38. Demo #3
39. Thank you
 for your attention. Contact piotr.laskawiec@comsenity.com Social Media @piotrlaskawiec @piotrlaskawiec.bsky.social COMSENITY LET'S CONNECT
40. RATING FEEDBACK