Brian Stevens

Have you heard of the llm-d project? It improves LLM performance and drives down costs of inference serving on Kubernetes. It's based around a few key projects including vLLM and kgateway. If you want a deep dive into how it works with a detailed step-by-step "packet flow" through llmd, take a look at this blog I wrote recently. 👉 https://lnkd.in/g2mbEh3m

44

3 Comments

AI chips, models, and agents are redrawing the map of technology ecosystems. Ashesh Badani breaks down the new @Forrester report to help you architect a stable, controllable AI stack: https://red.ht/418FsKx

37

The more autonomous AI becomes, the more binaries it will create. The more binaries created, the more security is required at the gate, and the more governance is needed before deployment to production. 🐸 https://bit.ly/4seEMPq #JFrog #LiquidSw

5

MCP servers are quickly becoming a practical way to connect LLMs to real production systems. In this demo, software developers Shalin Mehta and Samuel Wilt, walk through how we’re using MCP at Plainsight to automate deployment for real-time video AI pipelines. Agents handle the full lifecycle: detecting new pipelines, creating Kubernetes runs, monitoring readiness, and confirming that inference is actually running in production. The walkthrough by Shalin Mehta and Sam Wilt covers: • MCP as a control plane for video AI • Automated deployment and verification • Kubernetes orchestration with feedback loops • LLM agents interacting with live infrastructure If you’re interested in what MCP looks like beyond toy examples, watch the full walkthrough. #MCP #VideoAI #Kubernetes #LLMs #AIInfrastructure How MCP Powers Agentic Workflows for Production Vision Applications https://lnkd.in/gRrR4_md

14

According to Gil Luria, head of technology research at investment bank DA Davidson, these companies benefit from the growing demand for #AI #software tools, offering essential services for expanding AI capabilities. https://lnkd.in/gUgiQVHU Snowflake Datadog JFrog

94

AWS to Demo VirtualZ Computing's Lozen™ Integration with Rocket Software® Enterprise Developer in its November 11, 2025, PartnerCast. https://lnkd.in/geJ47yu6 The Amazon Web Services (AWS) and VirtualZ Computing collaboration is also highlighted in the recent AWS blog post, Transforming Hybrid Mainframe Data Access with VirtualZ Lozen and AWS: https://lnkd.in/eS8q9Xbc

7

Today let's talk about Parallel Fan Out/ Concurrent Agentic Design pattern and when parallel agents go rouge What’s the Concurrent Orchestration Pattern? Imagine a scenario where multiple AI agents—each with its own lens or specialty—tackle the same task simultaneously. Instead of a single, step-by-step chain, tasks fan out to different agents in parallel. Then their outputs are merged or aggregated for the final answer. It’s the AI equivalent of a brainstorming session where everyone chips in together. This pattern thrives when you need diverse insights or speed—think ensemble reasoning or reaching a verdict faster. This pattern is commonly used in agentic RAG. Here’s how you can apply it in a Retrieval-Augmented Generation (RAG) system: Step 1: Break the user’s query into smaller sub-queries (e.g., “Define concept X,” “List use cases,” “Give examples”) and map out their dependencies. Step 2: Run those sub-queries in parallel—agents fetch context or process each in isolation (e.g., document retrieval, summarization, external tool usage). Step 3: Once all agents have results, aggregate the findings into a single, coherent response. This technique lets you parallelize independent parts, reducing latency while maintaining clarity—especially effective when sub-queries don’t depend on each other. Super Important : Try to avoid this pattern and use sequential execution even if it's slow, but it might yield a good result, below is the reason As Cognition [the company behind devin] warns in a famous blog post “Don’t Build Multi-Agents”, things can go sideways fast if agents don’t share context or coordination is weak. When agents operate in isolation—making decisions based solely on their own view—the final result might be fragmented, contradictory, or just plain incoherent. Think two agents building different puzzle pieces that don’t fit. The core issues: Context fragmentation: Each agent works in a silo, leading to mismatched assumptions. Implicit decisions: Agents’ outputs reflect unspoken choices that may clash when merged. Coordination complexity: Without strong orchestration, integration becomes error-prone. References : 1. Concurrent Execution Pattern : https://lnkd.in/gZybgm2s 2. LLM Compiler whitepaper : https://lnkd.in/gWwGJhbi 3. Coginition blog Don't build multi agents which shows parallel execution can yield agent drift : https://lnkd.in/gkDKC4TP

14

3 Comments