Techmash
Menu
HomeClaudeWorkflowsReviewsNewsSubscribe

Newsletter

One email. One useful idea.

Practical Claude workflows and agent systems from people building real things. Read it in two minutes. Skip when you want.

Get the signal, not the noise.

Weekly Claude workflows and agent systems. No hype.

Subscribe on Beehiiv →

Recent articles

Claude Code: A minimal setup for everyday engineering work

Claude Code is Anthropic's command-line tool for software engineering tasks. This guide shows you how to install it, connect it to a project, and run your first few tasks — without configuring anything you don't need. If you want a practical AI coding setup that stays out of your way, this is the starting point. The whole setup takes under ten minutes and works on any project you already have running locally. No special scaffolding required.

5 min

How to use MCP to give Claude access to your own tools

The Model Context Protocol (MCP) is an open standard that lets you connect Claude to external data sources and tools — databases, APIs, file systems, or anything else you can wrap in a small server. This guide walks through what MCP is, how to set up a basic server, and how to connect it to Claude so your agents can call your own systems. You do not need deep infrastructure knowledge. If you can run a Node or Python script, you can build and connect an MCP server.

6 min

Build a 3-step research agent with Claude and a single prompt file

A research agent is a structured prompt system that breaks a broad question into smaller tasks, runs each one in sequence, and assembles the results into a usable output. This guide shows you how to build a three-step version using Claude and a single prompt file — no frameworks, no orchestration libraries. You define three prompts, run them in order, and pipe the output of each into the next. The result is a repeatable research workflow you can apply to any topic in under a minute.

6 min

A practical checklist for shipping multi-step Claude agents

Multi-step agents are Claude-powered systems that run a sequence of tasks with minimal human input between steps. They are useful and they break in predictable ways. This checklist covers what to verify before you call an agent production-ready: prompt isolation, error handling, output validation, cost controls, and logging. Work through the list before you hand any agent a live system to operate on. It takes about an hour and will save you several painful debugging sessions.

5 min

Claude Code vs. Cursor: which one ships faster for solo builders

Claude Code and Cursor are both AI coding tools aimed at developers, but they solve the problem differently. Claude Code runs in the terminal and works on your whole project. Cursor runs inside a fork of VS Code and focuses on the file you have open. For solo builders who move fast across multiple files, the differences matter. This review compares both tools on the tasks that come up most in a solo workflow: refactoring, writing tests, debugging, and generating boilerplate. No benchmarks — just real task results.

6 min

A week with Perplexity Pro: what it replaces and what it doesn't

Perplexity Pro is a subscription tier of the Perplexity AI search tool that adds access to more powerful models, higher daily query limits, and file upload for document analysis. After one week of using it as a primary research tool, here is an honest account of where it saves real time and where it falls short. This is not a feature list — it is a use-case breakdown for builders who are deciding whether the subscription is worth adding to their existing AI stack.

5 min