IBM Developer reposted this
The terminal executes commands. Bob Shell understands systems. That’s the difference. #IBM #Bob #IBMBob #Java https://ibm.com/bob
IBM Developer
IT Services and IT Consulting
New York, NY 48,777 followers
Welcome to a global community of builders, thinkers, and problem-solvers.
About us
Join a global community of builders and problem-solvers. IBM Developer is your space to explore the latest in AI and DevOps through tutorials and expert insights
- Website
-
https://ibm.biz/BdepWm
External link for IBM Developer
- Industry
- IT Services and IT Consulting
- Company size
- 10,001+ employees
- Headquarters
- New York, NY
- Founded
- 1911
- Specialties
- developers, cloud, artificial intelligence, blockchain, nodejs, Swift, Data science, AI, and serverless
Updates
-
-
IBM Developer reposted this
What happens when AI agents reason and take action over real-time events instead of working from delayed snapshots? Excited to share our latest hands-on tutorial: "Building an event-driven agentic AI system with Apache Kafka on Confluent Cloud, IBM watsonx Orchestrate, with the help of IBM Bob" on IBM Developer, co-authored with Moisés Domínguez. Real-time events change the game. When agents can observe what is happening as it happens, they can reason with the freshest operational truth and respond with the right business context. This tutorial shows a practical pattern for that: ⦿ Apache Kafka topics on Confluent Cloud as the real-time event backbone. ⦿ ksqlDB stream processing to keep an always up-to-date "current state" topic as events arrive. ⦿ watsonx Orchestrate multi-agents to consume live signals and coordinate decisions. ⦿ Agentic RAG to enrich real-time events with context from enterprise documents. ⦿ Bob as software development partner to speed up everything from Kafka and ksqlDB configuration, to publishing events, to building MCP tools and watsonx Orchestrate agents This unlocks agent behavior that is faster, more explainable, and more context-aware, especially for retail (as shown in the tutorial), operations, risk, supply chain, banking, insurance, customer service, and IT. Thank you to Ela Dixit, Monisankar Das, Sreelakshmi Aechiraju, and Michelle Corbin for the reviews and contributions.
-
Enterprise Java isn’t about typing faster. It’s about understanding the system first. Markus Eisele shares a technical perspective on how IBM Bob supports planning and controlled change in real Java codebases: https://ibm.co/604487DhG
-
-
IBM Developer reposted this
✨ Excited to share that I’ll be speaking at IBM Dev Day with Mingxuan Z. about Docling! We’ll dive into how Docling can be used in AI workflows, and how IBM's CIO used Docling to unlock previously inaccessible data for IBM internal tooling. 👉 Please register here: https://lnkd.in/ekPc_RCw
-
-
IBM Developer reposted this
“I’m testing Bob currently, and it saves so much time and effort. Where do you stand?”
-
In 2026, we expect a meaningful shift in how AI systems are designed and applied – a transition towards reasoning-first architectures, domain-specific models, and a more global open-source ecosystem. Rather than bigger, generalized models, momentum is building around systems tailored to real domains and real constraints. What changes are you most looking forward to building toward in 2026? 👀
-
-
IBM Developer reposted this
Why AI Proofs of Concept Fail in Production Most AI proofs of concept fail for the same reason. They assume large language models behave like stateless services. Enterprise systems don’t. LLMs can produce correct-looking responses even when context is incomplete, inconsistent, or wrong. That’s dangerous in production systems that rely on determinism, identity, transactions, and history. When AI lives outside the application lifecycle, teams lose: - control over inputs - predictability of outputs - observability of behavior This is an integration problem. The architectural shift is simple but non-negotiable: AI must be treated as an application component, not an external service. With Quarkus and LangChain4j, AI logic runs inside the Java application boundary, alongside REST APIs, messaging, and databases. Prompts, memory, and tools participate in the same lifecycle, security model, and operational controls as the rest of the system. That’s how AI becomes production-ready. Learn more: ibm.biz/quarkus-ai #QuarkusWithMarkus #EnterpriseAI #JavaArchitecture #CloudNative #LangChain4j IBM Esau Betancourt IBM Developer
-
IBM Developer reposted this
🚀 Exciting Collaboration Announcement at CES: NVIDIA × Docling 🚀 We’re thrilled to share that NVIDIA and Docling are collaborating to deliver best-in-class performance for high-quality document conversion. This collaboration has already led to significant optimizations in Docling, leveraging batch processing to achieve up to a 4× speed-up compared to CPU-only workloads. ️Thanks to the close partnership with the NVIDIA RTX AI team, we were able to develop, test, and benchmark across multiple NVIDIA systems, including the powerful RTX 5090—pushing the limits of document conversion performance on RTX PCs. Learn more about the NVIDIA RTX optimizations: https://lnkd.in/dpsHq7af Get started with Docling on RTX: https://lnkd.in/dsN4KHwt We’re excited about what’s ahead and look forward to enabling faster, higher-quality document processing for the community. Stay tuned for more Docling news! Many thanks to our awesome collaborators at Nvidia: Aslı Sabancı Demiröz, Douglas O'Flaherty, Sean Sodha and many more! cc: Abdel Labbi, Sriram Raghavan, Shankar Ramaswamy, Ed Anuff, Milan (Marquez) Higginbotham, Alejandro Cantarero #CES #IBM #NVIDIA #Docling #RTXAI #OpenSource #DocumentAI #Performance #AIInfrastructure
-
-
IBM Developer reposted this
https://lnkd.in/efqRppzd Docling + Go + Bob: The Modern Document Stack
-