Tag: #ai-platform
Writing on GPUs, LLMs, MLOps, Kubernetes — and mindset · 51 posts
Open Source Worth Watching Right Now (1) AI Agents and LLM Tooling
The LLM application stack has split into layers: inference servers, orchestration, gateways, agents, and RAG. This post introduces 12 open source projects that are actually used at each layer, grouped by role rather than
2026-08-12 · 6 min read #open-source#llm#ai-agent#ai-platform#ragInside vLLM (1) — The Full Path From One Request to One Token
Follows the full path a single request takes through vLLM, from arrival to the first token out. Covers what the API server, scheduler, KV cache manager, worker, and sampler each do, and how the process layout splits afte
2026-08-12 · 6 min read #vllm#llm#inference#gpu#ai-platformManaged Agent Platforms Comparison Guide: OpenAI AgentKit vs Azure AI Foundry Agent Service vs Amazon Bedrock AgentCore
A practical comparison of three managed agent platforms as of 2026-04-12, including product fit, governance, tooling, deployment, and rollout checklists grounded in official docs.
2026-04-12 · 5 min read #ai-platform#managed-agents#agent-platform#comparison#openaiOpenAI RFT with Custom Graders: A Practical Guide for Product and Platform Teams
A practical guide to OpenAI reinforcement fine-tuning with custom graders, including when to use it, how to prepare data, how to evaluate checkpoints, and how to roll it out safely.
2026-04-12 · 5 min read #ai-platform#openai#rft#reinforcement-fine-tuning#custom-gradersCloudflare AI Gateway Practical Guide: Observability, Reliability, and Cost Control for AI Traffic
A practical, current guide to Cloudflare AI Gateway as of April 12, 2026, covering observability, caching, retries, rate limiting, model fallback, and Dynamic Routing.
2026-04-12 · 5 min read #ai-platform#cloudflare#ai-gateway#observability#cachingGemini CLI Practical Guide: How Developers Should Decide Whether to Adopt a Terminal-First AI Agent
A practical 2026 guide to Gemini CLI for developers who want to understand where it fits versus IDE-first tools, how plan mode, hooks, MCP, and scripting work, and how to roll it out safely on a team.
2026-04-12 · 7 min read #gemini-cli#google-gemini#terminal-ai#ai-agent#mcpOpenAI AgentKit and the New Agent Evaluation Workflow: A Practical Guide to Datasets, Trace Grading, and Prompt Optimization
A practical guide for engineering, product, and platform teams on how OpenAI AgentKit changes agent evaluation, with a rollout framework for datasets, trace grading, and automated prompt optimization.
2026-04-12 · 8 min read #ai-platform#agentkit#agent-evals#trace-grading#prompt-optimizationAmazon Bedrock AgentCore Practical Guide: How to Build Secure Production Agents in 2026
A practical guide to Amazon Bedrock AgentCore for teams that need secure, production-ready agents, with clear coverage of Runtime, Memory, Gateway, observability, and rollout checks.
2026-04-12 · 6 min read #aws#bedrock#agentcore#ai-agent#mcpAI Gateway Platforms Comparison Guide: Vercel AI Gateway vs Cloudflare AI Gateway vs Amazon Bedrock AgentCore Gateway
A practical comparison of AI gateway layers as of 2026-04-12, showing where Vercel AI Gateway, Cloudflare AI Gateway, and Amazon Bedrock AgentCore Gateway belong in the stack.
2026-04-12 · 4 min read #ai-platform#ai-gateway#comparison#vercel#cloudflareOpenAI Responses API and Agents SDK Practical Guide: How Teams Should Redraw Their Architecture in 2026
A practical guide to OpenAI Responses API and Agents SDK based on the March 11, 2025 launch, focused on architecture choices, when to keep Chat Completions, when to move off Assistants API, and how built-in tools plus tr
2026-04-12 · 10 min read #openai#responses-api#agents-sdk#ai-agent#chat-completionsBuilding Multi-Model Apps with Vercel AI SDK 6 and AI Gateway: A 2026 Practical Guide
A practical guide to building multi-model AI apps in 2026 with Vercel AI SDK 6 and AI Gateway, covering agents, MCP, provider routing, fallbacks, human approval, and a Next.js adoption checklist.
2026-04-12 · 7 min read #ai-platform#ai-sdk#ai-gateway#multi-model#fallbacksPydanticAI Practical Guide: Why Python Teams Adopt It for Production Agents in 2026
A practical guide to PydanticAI for teams that need Python-first agent systems, model portability, durable workflows, observability, and evaluation in production.
2026-04-12 · 6 min read #pydantic#pydantic-ai#python#ai-agent#mcpGoogle Agent Development Kit Practical Guide: When ADK Is the Right Choice for Enterprise Agents
A practical guide to Google Agent Development Kit for teams evaluating agent frameworks, with a focus on context management, callbacks, multi-agent composition, and rollout decisions.
2026-04-12 · 6 min read #google-adk#agent-development-kit#ai-agent#multi-agent#session-stateMastra Practical Guide: Why TypeScript Teams Adopt It for Production AI Agents in 2026
A practical guide to Mastra for TypeScript teams that need agents, memory, workflows, observability, evals, and production deployment in one open-source stack.
2026-04-12 · 6 min read #mastra#typescript#ai-agent#mcp#memoryBrowser and Computer-Use Agents in Practice: Architecture, Guardrails, and an Adoption Checklist for 2026 Teams
A practical guide to browser and computer-use agents for developers and product teams, covering why the category matters now, which architectures work, where the risks are, and how to adopt safely.
2026-04-12 · 9 min read #ai-platform#ai-agent#browser-agent#computer-use#automationAzure AI Foundry Agent Service Practical Guide: Enterprise Deployment Decisions for 2026
A practical, current guide to Azure AI Foundry Agent Service for enterprise teams, focused on why managed agents matter, how the tool catalog and remote MCP servers work, and how to make rollout decisions around tracing,
2026-04-12 · 5 min read #azure#azure-ai-foundry#agent-service#ai-agent#mcpLlamaIndex Workflows Practical Guide: How to Ship Event-Driven Agents and RAG to Production
A practical guide to LlamaIndex Workflows for event-driven agent and RAG design, with observability, human-in-the-loop patterns, and production rollout guidance through LlamaDeploy.
2026-04-12 · 5 min read #llamaindex#workflows#agent-workflow#rag#observabilityModel Context Protocol in Production: Server Boundaries, Tool Governance, and Transport Choices
A production-focused guide to Model Context Protocol covering server boundaries, tool and resource design, transport selection, authentication, token budgeting, and operational governance.
2026-03-17 · 7 min read #ai-platform#mcp#model-context-protocol#ai-agent#tool-governanceLLM Utilization Strategies in the 1M Context Window Era: A Practical Guide to Large-Scale Context Processing
In March 2026, Anthropic announced GA of the 1M token context window for Claude Opus 4.6/Sonnet 4.6. Covers the paradigm shift from 128K-200K to 1M context, 5 practical patterns, RAG trade-offs, and cost optimization str
2026-03-15 · 41 min read #ai-platform#llm#context-window#long-context#claudeAI Coding Agent Sandboxing: Secure Code Execution Isolation and Security Operations Guide
As AI coding agent autonomy increases in 2026, security isolation has become essential. Covers practical sandboxing technologies including macOS sandbox-exec, container-based isolation, MicroVM, and operations guides.
2026-03-14 · 23 min read #ai-agent#sandboxing#security#ai-platform#devops