Ai on René Zander | AI Automation Consultant

Your AI Workflow Doesn't Need Better Prompts. It Needs Less AI.

Tue, 05 May 2026 05:30:00 +0000

The first stage of AI work is prompting.

The last stage is removing the model from most of the workflow.

That sounds backwards.

It is not.

When a workflow is new, the LLM is useful because the work is still ambiguous. You are discovering what good looks like. You try a prompt, read the output, adjust the examples, change the tone, add constraints, and run it again.

That is a good use of AI.

What Anthropic's April 23 Postmortem Reveals About Your Agent Harness

Thu, 30 Apr 2026 08:00:00 +0000

The April 23 Claude Code postmortem dropped last week. Three bugs, two months of degraded output, one usage-limit reset for every Pro subscriber.

I read it twice. The second time I started writing notes for my own agent harness.

It is unusually candid for a company at this scale, and it reads like a checklist of failure modes any team running production AI agents will eventually hit. Worth treating as a free engineering review.

95% of PII Redaction Doesn't Need an LLM. The Other 5% Does.

Tue, 21 Apr 2026 10:00:00 +0000

A VP at an SAP shop told me recently: “Every time we copy production to our lower environments, PII leaks. And no, we’re not throwing an LLM at it. That’s a thousand times the compute of what we already run.”

He’s right.

Most of the PII redaction problem in enterprise data isn’t a neural network problem. It’s a lookup table problem. And the incumbents already solve it. SAP TDMS, Delphix, Informatica, IBM InfoSphere Optim. All schema-aware. All row-level. All deterministic.

What llama.cpp's Pace Tells You About On-Prem LLM Readiness

Tue, 14 Apr 2026 06:00:00 +0000

Your team asked for GPU budget for self-hosted inference. You said “not yet” because last time you checked, the tooling wasn’t production-grade. That was true 18 months ago. It’s not true now, and the delay is costing you leverage you don’t know you’re losing.

I’m writing this because most decision-makers I talk to are still running on an outdated mental model of what self-hosted LLM infrastructure looks like. The software moved. The org didn’t.

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.

Your AI Content Tool Knows Your Strategy. Do You?

Tue, 07 Apr 2026 06:00:00 +0000

Your team is using AI for content. Everybody is. LinkedIn posts, blog drafts, internal comms, maybe some customer-facing copy too.

And it works. The output is decent, the speed is real, nobody wants to go back to writing everything from scratch.

But have you thought about what you are actually pasting into these tools?

The Prompt Is the Product

Every time someone on your team writes a prompt, they are feeding context into a system they do not control. Brand voice guidelines. Competitive positioning notes. Messaging frameworks. That internal strategy deck someone summarized into a prompt last Tuesday.

Spend Your Human Thinking Tokens Where They Compound

Tue, 31 Mar 2026 08:00:00 +0000

More automations running. More agents deployed. More pipelines humming in the background.

I run about a dozen automated jobs. Daily briefings, proposal generation, content pipelines, data syncing, monitoring alerts. They handle a lot.

But the biggest improvement to my workflow this year wasn’t adding more automation. It was getting honest about where my thinking actually matters.

You Have a Token Budget Too

LLMs have context windows. Feed in too much noise and the signal degrades. The output gets worse even though you gave it more to work with.

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.

Your Vector Database Decision Is Simpler Than You Think

Tue, 17 Mar 2026 07:41:59 +0000

Every week someone asks which vector database they should use. The answer is almost always “it depends on three things,” and none of them are throughput benchmarks.

I run semantic search in production on a single VPS. Over a thousand items indexed, embeddings generated on the same machine, queries return in under a second. But that setup only works because of the constraints I’m operating in. Change the constraints and the answer changes completely.

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.

Lots Of People Are Demoing AI Agents. Almost Nobody's Shipping Them The Right Way.

Wed, 04 Mar 2026 10:56:24 +0000

Lots of people are demoing AI agents. Almost nobody’s shipping them the right way.

Conference stages are packed with live demos of agents writing Terraform, spinning up Kubernetes clusters, and generating Helm charts on command. The audience claps. The tweet goes viral. And then… nothing ships.

Here’s the uncomfortable truth: the gap between “look what my agent can do” and “this runs in production every day” is enormous. I’ve been on both sides. I spent years as an Enterprise Architect watching organizations spin up AI pilots that never graduated. Now I run my own infrastructure with Claude as the core agent — not as a demo, not as a proof of concept, but as the actual engine that keeps things moving.