Automation on René Zander | AI Automation Consultant

Telegram Bot with Claude API: 30-Line Bash Daemon

Tue, 14 Apr 2026 11:00:00 +0200

I have a Telegram bot wired to Claude Opus 4.7 that I talk to from anywhere. Train, couch, cafe, bed. It reads my TickTick tasks, writes code against my repos, runs shell commands on my VPS, and sends me a morning briefing at 06:30 Madrid time. The whole thing is a bash script and a systemd unit. No frontend. No hosting bill. No auth pages to build.

This guide walks through exactly how to build one. Two architectures (bash long-polling and a TypeScript webhook server), full runnable code, attachment handling, MCP tool integration, and the security steps most tutorials skip. The primary stack is a Telegram bot Claude API wiring that runs on any Linux box with a few hundred megs of RAM.

Zapier vs Make vs n8n Pricing at Scale (2026)

Tue, 14 Apr 2026 08:00:00 +0200

Every automation platform counts usage differently, and that is not an accident. Zapier charges per task, Make.com charges per operation, n8n charges per execution. Those three words look interchangeable on a pricing page. They are not. The same workflow can cost $208 on Zapier, $20 on Make, or the price of a VPS on self-hosted n8n.

This guide is a practitioner walkthrough of how each platform counts, where the hidden costs hide, and which platform actually wins at each volume band. I run production workflows on Make and n8n for my own products (Teedian, a content operations engine), so the examples below reflect real wiring, not marketing math.

n8n AI Agent Workflow Examples: 5 Production Patterns

Sun, 12 Apr 2026 14:00:00 +0200

I run n8n in production for content ops, email triage, and invoice parsing. The visual canvas is not the point. The point is that triggers, retries, queues, and credentials are free, and I can hand a workflow to a non-engineer to edit prompts without them breaking the integration layer.

This post is five n8n ai agent workflow examples I actually ship or have shipped for clients. Each one includes the node graph, the Claude prompt, the cost per run, and the production gotchas. No toy demos.

AI Agents: Build vs Buy (2026 Decision Framework)

Sat, 11 Apr 2026 07:00:00 +0000

Every week, a client asks me some version of this question: “Should we build our own AI agent or just use [product]?”

The answer is never simple, but after building custom AI agent systems for production use, I have a clear framework for when each path makes sense.

What Is an AI Agent? (Not What You Think)

Most businesses asking about AI agents want one of three things:

1. An AI chatbot that answers questions about their product, knowledge base, or internal docs. This is the most common request. It is also the one most likely to be solved by buying, not building.

Claude API vs OpenAI API in 2026: Which One Ships Faster?

Sat, 11 Apr 2026 07:00:00 +0000

Claude API vs OpenAI for business automation in 2026: Claude produces cleaner structured output and follows instructions more literally, making it safer for extraction and content tasks. OpenAI ships parallel function calls, a wider model lineup, and more capacity at peak. Pick Claude when output quality matters; pick OpenAI when ecosystem and tool fan-out matter.

I integrate LLM APIs into business automation systems. Content pipelines, document processing, customer communication flows, data enrichment. Not chatbots. Production systems that run unattended and need to work every time.

Make.com vs n8n 2026: Which Survives Production (Real Data)

Sat, 11 Apr 2026 07:00:00 +0000

Most comparison articles list features side by side and call it a day. This is not that article.

I run both Make.com and n8n in production for clients. Content pipelines, data enrichment flows, CRM sync jobs, AI agent orchestration. Some of these run thousands of executions per week. Here is what actually matters when you move past the tutorial phase.

Make.com vs n8n in 2026: which one wins?

In 2026, n8n wins on cost (self-host = $20/month server vs Make.com’s $500+ at high volume), data residency (your VPC vs their servers), and AI-agent orchestration (native LangChain). Make.com wins on first-week ergonomics for non-developers and node-level error handlers. Pick n8n for production scale, Make.com for fast learnability under low volume.

Migrate Zapier to n8n: A Practitioner's Playbook for 2026

Fri, 10 Apr 2026 12:00:00 +0200

Most teams that want to migrate Zapier to n8n hit the same wall: pricing crosses a threshold around 10,000 tasks per month, or a data sovereignty requirement lands on the roadmap, and Zapier’s per-task model becomes a liability. n8n fixes both, but only if you pick the right deployment and plan the cutover properly.

I run n8n self-hosted in production for Teedian, alongside Make.com blueprints for clients who do not want to operate their own infrastructure. This is the zapier to n8n migration playbook I wish I had: concept mapping, pattern translation, a six-step rollout, the cost math that decides Cloud vs self-hosted, and the gotchas that burn people in week two.

GitHub Issue Management AI: Build Claude-Powered Triage That Works

Thu, 09 Apr 2026 14:00:00 +0200

Maintainers do not ship software on Tuesday mornings. They triage. They read a new issue, check whether it is a duplicate of something filed three weeks ago, decide whether it is a bug or a question, pick a priority, add two or three labels, and sometimes write a polite comment asking for a repro. Then they do it again for the next issue in the queue. The job is pure admin, and on any active repo it eats real hours every week.

Migrate Zapier to Make: A Practitioner's Migration Guide (2026)

Wed, 08 Apr 2026 11:00:00 +0200

I’ve migrated several client workflows from Zapier to Make.com over the last two years, mostly running Teedian content pipelines where the branching and iteration logic outgrew what Zapier could comfortably handle. The pattern is always the same: Zapier works fine until it doesn’t, and then it doesn’t in expensive, awkward ways.

If you’re reading “migrate zapier to make” as a query, you’ve probably already hit one of three walls: a task-based pricing bill that keeps climbing, a workflow that needs real branching or loops, or a debugging session where Zapier’s logs told you nothing useful. This guide walks the full migration: why it’s worth doing, when it isn’t, how concepts map between the two platforms, and a 6-step strategy that won’t break production.

Claude Code SDK Agents: Build Production Agents Without the Loop

Wed, 01 Apr 2026 12:00:00 +0200

Most “build an agent with Claude” tutorials hand you a while-loop around client.messages.create, a hand-rolled tool dispatcher, and a promise that you’ll wire up file reads and shell execution yourself. That works. It also means you spend two weeks rebuilding the same plumbing that Claude Code already ships with.

The Claude Code SDK, sometimes called the Claude Agent SDK, is the shortcut. Same runtime as the claude CLI, exposed as a library in TypeScript and Python, plus a print mode you can call from a bash cron job. You get file tools, bash, MCP client, subagents, hooks, and permission modes without writing any of it.

AI Skills Are the New Boilerplate: They Fix Nothing

Tue, 24 Mar 2026 11:13:17 +0000

Everyone’s sharing their skill libraries right now. “Here are my 20 custom slash commands.” “Check out my prompt template collection.” “This skill saves me 2 hours a day.”

I use skills too. I have about a dozen. They handle cover letters, content pipelines, code review, commit messages. Repeatable workflows where the input and output are predictable.

They cover maybe 10% of what my AI system actually does.

The other 90% is the part nobody shares on social media because it’s ugly. It’s API integrations that break when headers change. It’s state management between sessions. It’s error handling for when the third-party service returns garbage. It’s monitoring that pages you at 6 AM because a cron failed. It’s human-in-the-loop workflows where the AI proposes and you approve before anything touches production.

How I Built a Business Email Agent with Compliance Controls in Go

Sat, 21 Mar 2026 12:49:31 +0000

Every few weeks another AI agent product launches that can “handle your email.” Dispatch, OpenClaw, and a dozen others promise to read, summarize, and reply on your behalf.

They work fine for personal use. But the moment you try to use them for business operations, three problems show up:

No spending controls. The agent calls an LLM as many times as it wants. You find out what it cost at the end of the month.
No approval flow. It either sends emails autonomously or it doesn’t. There’s no “show me the draft, let me approve it” step.
No audit trail. If a client asks “why did your system send me this?”, you have no answer.

I needed an email agent for my consulting business that could triage inbound mail, draft replies, and digest threads. But I also needed to explain every action it took to a client if asked. So I built one.

I Run 10 AI Agents in Production. They're All Bash Scripts.

Thu, 12 Mar 2026 14:29:44 +0000

A week ago I wrote about shipping AI agents the right way. That piece was about the harness: quality gates, token economics, multi-model verification. The stuff that separates demos from production.

A lot of people resonated with it. But I left out the part that actually eats most of my time: keeping the boring stuff running.

So let me walk you through what production AI agents actually look like when the conference talk is over.