Blog
Blog
Engineering notes on AI agents, automation, and the infrastructure behind them.
May 19, 2026 · 4 minSplitting Grounding from Reasoning in Browser-Agent Stacks
Browser-agent stacks bundle grounding and reasoning. A local 2B parser splits them, beats GPT-4o on ScreenSpot-v2 by 2.5x, costs $4 to train.
May 12, 2026 · 4 minContext Engineering Is Just File Naming
Context engineering sounds new. It is the file-naming hygiene developers always had, load-bearing now because LLMs read what you point them at.
May 5, 2026 · 9 minYour AI Workflow Doesn't Need Better Prompts. It Needs Less AI.
Prompting is discovery. Skills are repetition. Gates are how AI workflows become reliable.
May 2, 2026 · 8 minAgentic Knowledge Base — Karpathy's LLM wiki, with adapters
A framework that turns whatever task or note app you use into a Karpathy-style LLM wiki. Pluggable adapters, parallel retrieval with RRF.
April 30, 2026 · 3 minWhat Anthropic's April 23 Postmortem Reveals About Your Agent Harness
Three bugs over two months, one usage-limit reset for every Pro subscriber. The postmortem reads like a free audit checklist for any production agent harness.
April 23, 2026 · 4 minVoice AI in Production: From RunPod to Hosted Kubernetes
One pod serves one user at a time. Production serves thousands. Here's what that gap actually costs, and why voice AI companies keep asking for hosted Kubernetes.
April 21, 2026 · 4 min95% of PII Redaction Doesn't Need an LLM. The Other 5% Does.
When to use deterministic masking and when a fine-tuned LLM earns its compute on SAP production data copies. A hybrid architecture.
April 15, 2026 · 11 minAI Automation for Freelancers: 8 Workflows I Run Daily
Ai automation for freelancers, broken down into 8 concrete workflows I run on a €15/mo VPS. Proposals, invoices, briefings, CRM, content, all with Claude. Download the free AI Automation Checklist.
April 14, 2026 · 15 minBuild Your Own Claude Telegram Bot: 30 Lines of Bash, No Plugin Needed
Build your own Claude Telegram bot instead of installing the official plugin: a 30-line bash long-polling daemon you fully control. Full script, MCP tools, attachments, allowlisting.
April 14, 2026 · 4 minWhat llama.cpp's Pace Tells You About On-Prem LLM Readiness
Your team asked for GPU budget for self-hosted inference. You said not yet. The tooling moved, the org didn't, and the delay is costing you leverage you don't know you're losing.
April 13, 2026 · 14 minMCP Servers Explained: What Model Context Protocol Does
MCP servers explained without the marketing. What Model Context Protocol is, how the architecture works, and when to write your own server. Download the free AI Automation Checklist.
April 12, 2026 · 15 minn8n AI Agent Workflow Examples: 5 Production Patterns
Five real n8n ai agent workflow examples with Claude, RAG, and human-in-the-loop. Node graphs, prompts, costs, and production hardening tips. Download the free AI Automation Checklist.
Your agents answer from whatever the retriever finds, and too often that is last quarter's truth. I build the context layer they answer and act from: a temporal knowledge graph that keeps every fact with its source and the time it held, reads with each person's own permissions, and writes nothing without a person's approval. On your own tenant, billed by the hour, step by step.