Tag: #ai-agent
Writing on GPUs, LLMs, MLOps, Kubernetes — and mindset · 66 posts
The Plugin Kernel Architecture of DeepSeek Harness — What Makes an Agent You Can Rewind
Harness, the open source coding agent DeepSeek released, makes the model, the tools, and even the UI into plugins. But the interesting part is not the word plugin. It is two design decisions: representing every execution
2026-08-14 · 7 min read #ai-agent#architecture#plugin-system#observability#open-sourceOpen 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#ragDid Context Engineering Replace Prompt Engineering — What's Measured and What Isn't
"Prompt engineering is dead" appears in none of the primary sources that coined the term. Karpathy listed few-shot examples and task descriptions as components of context engineering, and Anthropic called it "a natural p
2026-07-17 · 20 min read #llm#context-engineering#prompt-engineering#long-context#ai-agentHow AI Agent Memory Is Actually Built — Four Designs, and What the Benchmarks Really Prove
"Agent memory" is not a single technique but a blur of at least four distinct designs — a file scratchpad, summarization/compaction, vector retrieval, and knowledge graphs. This post pins down what each actually does fro
2026-07-17 · 21 min read #ai#ai-agent#agent-memory#llm#benchmark2026 IAM Trends — AI Agent Identity, MCP Authentication, Verifiable Credentials
The 2026 IAM landscape is being reshaped by passwordless-by-default, an explosion of non-human identities in the form of AI agents, and the OAuth 2.1-based standardization of MCP authorization. From on-behalf-of delegati
2026-06-12 · 16 min read #iam#oauth2#mcp#ai-agent#keycloakCan an Imitation Machine Discover — The Sutton Provocation and the RL Counterattack
Rich Sutton, the godfather of reinforcement learning, set the community ablaze in June 2026 by arguing that generative AI trained with supervised learning is an imitation model and therefore limited for genuinely new sci
2026-06-12 · 22 min read #ai#reinforcement-learning#llm#research#ai-agentContext Engineering — How to Design Memory for AI Agents
The era of prompt engineering is fading, and context engineering has emerged as the core skill. This post covers the economics of the context window, memory tier design, patterns for automatically extracting facts from c
2026-06-12 · 17 min read #ai#context-engineering#llm#ai-agent#memoryHow to Review AI-Written Code — Redesigning Code Review
The surge of AI-generated code has made code review the biggest bottleneck in the development pipeline. This post covers how defect patterns differ between human and AI code, redesigning review strategy around spec compa
2026-06-12 · 18 min read #ai#code-review#ai-agent#engineering-culture#open-sourceLoop Engineering — Design the System That Prompts Your Agent
The era of manually prompting an agent every turn is ending. This post covers plan-act-verify-self-correct loop design, verification loops that wire tests and linters into agent feedback, how to design repo-level guide f
2026-06-12 · 16 min read #ai#loop-engineering#ai-agent#claude-code#devopsBuilding MCP Servers in Practice — How to Connect Your Tools to Every AI Agent
A hands-on guide to building MCP (Model Context Protocol) servers, the de facto standard of 2026. We implement an internal wiki search server in TypeScript and Python, and cover tool design principles, OAuth 2.1 authenti
2026-06-12 · 17 min read #mcp#ai-agent#typescript#python#oauth2RPA Platforms 2026 Complete Guide - UiPath, Automation Anywhere, Blue Prism, Power Automate, Tungsten, ABBYY, Rocketbot Deep Dive
In 2026, "traditional RPA" is dying fast — and evolving faster. UiPath Autopilot, Automation Anywhere AARI, Blue Prism Decipher IDP, Power Automate Copilot, Tungsten TotalAgility, ABBYY Vantage, Rocketbot, Japan-leading
2026-05-16 · 28 min read #rpa#uipath#automation-anywhere#blue-prism#power-automateRPA 2026 Deep Dive - UiPath vs Automation Anywhere vs Blue Prism vs Power Automate Desktop vs WinActor vs Brity Works and the Agentic AI Invasion
Spring 2026, and the RPA (Robotic Process Automation) industry stands at a crossroads. UiPath stock trades at about a quarter of its IPO price, Microsoft now bundles Power Automate Desktop into Windows for free, and Auto
2026-05-16 · 25 min read #rpa#uipath#automation-anywhere#blue-prism#power-automateAI Agent Frameworks 2026 Deep Dive — LangGraph, AutoGen, CrewAI, Semantic Kernel, OpenAI Agents SDK, Claude Agent SDK, Pydantic AI
A May 2026 deep dive into the ten frameworks that dominate production agent systems — LangGraph 0.3, AutoGen 0.4, CrewAI Flows, Semantic Kernel Agent Framework, OpenAI Agents SDK, Claude Agent SDK, Pydantic AI, Smol Agen
2026-05-16 · 17 min read #ai-agent#langgraph#autogen#crewai#semantic-kernelAI Agent Frameworks 2026 Deep Dive — LangChain, LangGraph, LlamaIndex, CrewAI, AutoGen, PydanticAI, Mastra, DSPy, MCP Complete Guide
A complete picture of the AI agent framework market as of May 2026. LangChain holding share despite brand fatigue, LangGraph state-graph pattern, LlamaIndex RAG depth, CrewAI/AutoGen multi-agent, PydanticAI type safety,
2026-05-16 · 18 min read #ai-agent#langchain#langgraph#llamaindex#crewaiAI Agent Frameworks in 2026 — A Deep Dive on LangGraph, AutoGen, CrewAI, OpenAI Agents SDK, Anthropic Agent SDK, and More
In 2026 the AI agent framework landscape has exploded into a dozen camps. Vendor SDKs from OpenAI and Anthropic, orchestration frameworks like LangGraph and AutoGen and CrewAI, minimalist contenders like smolagents and M
2026-05-15 · 19 min read #ai-agent#langgraph#autogen#crewai#smolagentsWriting Great Tickets: The Craft of Issues for Humans and AI Agents
The ticket is the single highest-leverage written artifact in software. The anatomy of a great ticket, acceptance criteria as checkboxes, the 'one ticket = one reviewable PR' rule, bug and feature templates, and what mak
2026-05-14 · 22 min read #tickets#issues#writing#communication#ai-agentBuilding an AI Teammate with a Slack Bot — Wiring Up Claude, Gemini, OpenClaw + Extending Tools with MCP (2026 Hands-On)
The highest-leverage surface for deploying AI isn't the IDE — it's Slack, where the whole team uses it, right where the work happens. This is a follow-along hands-on. Create a Slack app, stand up a minimal bot that respo
2026-05-14 · 16 min read #slack-bot#llm#claude#gemini#openclawThe 2026 Rising Open-Source Map — A Practitioner's Survey of OpenClaw, n8n, Langflow, Dify, and Ollama
A practitioner's survey of the open-source projects that exploded on GitHub in 2026. What OpenClaw, n8n, Langflow/Dify/Flowise, and Ollama are, why they're trending, when to use them, what the risks are — and how to vet
2026-05-14 · 16 min read #open-source#github#trending#openclaw#n8nWorkflow Automation 2026 — Zapier, n8n, Make and RPA (UiPath, Power Automate): The Line Between iPaaS and RPA, and the AI Agent Crossover
Zapier sends an email. UiPath clicks a button in an ERP. They look similar, but they're not the same. This post draws the line between iPaaS (Zapier, Make, n8n) and RPA (UiPath, Power Automate, Automation Anywhere, Blue
2026-05-14 · 20 min read #workflow-automation#zapier#n8n#make#rpaHow to Review AI-Generated Code: The Verification Discipline for Agent Output and Filtering 'AI Slop'
When AI writes the code, the bottleneck moves to review. Reviewing a human PR and reviewing agent output are different skills. The characteristic ways AI code is wrong, a verification loop that filters hallucinated APIs
2026-05-14 · 21 min read #code-review#ai-generated-code#verification#ai-slop#quality