Tom HundleyPart 3 of 4
🤖 Ghostwritten by Claude · Curated by Tom Hundley
This article was written by Claude and curated for publication by Tom Hundley.
Just because you have a hammer (LLM), doesnt mean everything is a nail.
As an AI consultancy, it is against our short-term interest to tell you this: You probably dont need AI for that.
We once had a client who wanted an AI Agent to scrape competitor pricing from websites and put it into a spreadsheet. They budgeted $50k.
We told them: We can build this with a Python script and a cron job for $5k. No AI needed.
They were disappointed. They wanted the magic. But we saved them $45k and a lifetime of maintenance headaches.
Before you reach for an LLM, check the hierarchy:
Problem: I need to calculate the average sales by region.
Solution: Do not use AI. Use a Pivot Table. It is 100% accurate, free, and instant. AI will hallucinate the math.
Problem: When an email comes in with Invoice in the subject, save it to Dropbox.
Solution: Do not use an Agent. Use a rule. If Subject contains Invoice - Save. It works every time.
Problem: Scrape this specific HTML table every morning.
Solution: Use BeautifulSoup or Selenium. It is fragile, but predictable.
Problem: Read this angry email and decide if we should offer a refund or a polite decline, based on our 50-page policy document.
Solution: THIS is for AI.
Use AI only when the task involves:
Using an LLM for a deterministic task isnt just expensive (tokens); its dangerous.
The most impressive AI architecture is the one that uses the least amount of AI necessary to get the job done.
We pride ourselves on being AI Minimalists. We use the nuclear reactor (LLM) only when the battery (Script) wont suffice.
This article is a live example of the AI-enabled content workflow we build for clients.
| Stage | Who | What |
|---|---|---|
| Research | Claude Opus 4.5 | Analyzed current industry data, studies, and expert sources |
| Curation | Tom Hundley | Directed focus, validated relevance, ensured strategic alignment |
| Drafting | Claude Opus 4.5 | Synthesized research into structured narrative |
| Fact-Check | Human + AI | All statistics linked to original sources below |
| Editorial | Tom Hundley | Final review for accuracy, tone, and value |
The result: Research-backed content in a fraction of the time, with full transparency and human accountability.
Were an AI enablement company. It would be strange if we didnt use AI to create content. But more importantly, we believe the future of professional content isnt AI vs. Human—its AI amplifying human expertise.
Every article we publish demonstrates the same workflow we help clients implement: AI handles the heavy lifting of research and drafting, humans provide direction, judgment, and accountability.
Want to build this capability for your team? Lets talk about AI enablement →
Discover more content:
