Overview: four ways to run recurring tasks with Claude Claude can now execute tasks on autopilot, and there are four practical approaches you can choose from depending on how long you want the automation to run, how reliable you need it to be, and how much technical setup you want to manage. I break each … Read more

I created an automation that lets powerful cloud language models answer questions about private company documents without ever seeing real sensitive data. The cloud model only ever receives surrogate values. Real names, passport numbers, financials and other secrets stay inside my network. This article explains how I put that together, the challenges I ran into, … Read more

Agent skills have become one of the most useful design patterns for building practical AI agents. I created an automation that combines agent skills with code execution sandboxes inside a custom Python and React agent. The result is an agent that can not only answer questions but follow step-by-step workflows, execute code safely, and produce … Read more

I created an automation that dramatically reduces unnecessary LLM context and lets the model orchestrate complex workflows with real code. The two design patterns at play are simple in concept but powerful in practice: tool search and programmatic tool calling. Both solve problems that crop up as agents grow: tool definitions bloating the context window, … Read more

Overview Claude Cowork brings powerful automation and agent orchestration to a simple desktop interface. I built automations with it that read folders, extract data from invoices, control a browser to interact with web apps, and generate deliverables like Excel sheets, PowerPoint decks, and Word reports. The underlying engine borrows the same planning and sub-agent approach … Read more

I created an automation that treats a knowledge base more like a living file system than a static set of vectors. Instead of relying only on semantic search, this approach lets an AI agent actually explore folders and files, form hypotheses about where answers live, and then dig deeper—just like a developer reading a codebase. … Read more

I built a set of agentic workflows to see how far coding agents can take routine automation. I wanted to answer a practical question: when should you use a coding agent like Claude Code to generate Python workflows, and when should you stick with visual workflow tools such as n8n? I tested real examples, deployed … Read more

Overview I built a full-featured Agentic RAG application that lets an LLM interact with private company data safely, efficiently, and transparently. The stack is intentionally simple: a React frontend, a Python FastAPI backend, and Supabase for storage, vectors, and auth. I used DocLing for document parsing and LangSmith for observability. The result is a multi-user … Read more

I created an automation that turns short lived AI calls into long running, reliable agents. These agents can research, synthesize, and produce reports that span hours and many data sources. The trick was adding a control layer, which I call an agent harness, around the AI so it can plan, persist progress, and resume work … Read more

I built an automation that lets AI agents answer questions about structured data without hallucinating. It uses natural language query, not just vector stores. The result is a database agent that learns useful SQL patterns over time and reuses them when similar questions come up again. Why vector stores alone often fail for tabular data … Read more