Code Monkey

Parts three and four gave me candidate translations.

In part three, I translated short fields and checked that the model returned the fields and placeholders I asked for.

First off...

In part one, I translated one sentence.

For those who don't know, I am Canadian.

In part one, we loaded the AWS software development kit and created reusable service clients.

In part two, we allowed a browser to upload a file directly to a private AWS S3 bucket.

In 1992 (fuck I'm old), when I was working in terrestrial broadcast radio, an engineer named Michael Liles told me something that has stayed with me ever since: “David, Engineering isn't about being able to fix every problem.

In part one, we loaded the Amazon Web Services software development kit into ColdFusion and built a factory capable of creating service clients.

ColdFusion has always been able to call Java classes directly.

In Part 1, we registered a passkey.

In parts one and two, our passkey ceremonies ran inside the same application that registered and authenticated the user.

In part one, we registered a passkey for an authenticated user.

I have been building authentication systems since HTML introduced forms in HTML 2.

AWS Cost Explorer kept nagging me.

If you’ve made it this far, congratulations, and thanks for putting up with my ramblings..

By the end of the last article we had something that felt remarkably polished.

By this point in the series we’ve accomplished something pretty satisfying.

I’ve been part of the ColdFusion community for a long time.

We have spent five articles carefully controlling every request leaving our application.

Tell someone you used a spelling checker and nobody cares.

One of my biggest pet peeves with integration tutorials is that they all seem to start in the middle.

This article is pure venting.

If you ask ten developers how to build a real-time application, approximately eleven of them will tell you to use WebSockets.

The main rule The LLM is not your application.

If you’ve been building ColdFusion applications for any length of time, you’ve probably had this conversation.

In the last few articles, we have been steadily building a ColdFusion AI assistant with more and more capability.

In the last article, we built the ColdFusion AI version of “Hello World.”

In the last few articles, we have been building our ColdFusion AI assistant one layer at a time.

In the last few articles, we have been gradually building up a ColdFusion AI assistant without giving it enough rope to rappel into production and start making architectural decisions.

In the last few articles, we have been slowly teaching ColdFusion how to talk to AI without immediately causing a production incident.

In the previous article, we talked about the basic AI vocabulary: LLMs, prompts, tokens, context windows, temperature, statelessness, hallucinations, tools, RAG, MCP, and guardrails.

Artificial intelligence is suddenly everywhere.

By this point we’ve decided two important things.

At long last... we get to write some ColdFusion.