-
Close Search
This article introduces the simplest practical starting point for using AI in ColdFusion: ChatModel(). It walks through configuring a model, sending a prompt with .chat(), reading response.message, and safely displaying the result. Along the way, it explains provider settings, model names, API keys, temperature, max tokens, timeouts, prompt design, response validation, error handling, logging, and the tradeoffs between streaming and non-streaming responses. The central lesson is that ChatModel() is ideal for simple, stateless AI tasks like summarizing, rewriting, classifying, translating, and drafting, but it is only the front door. More advanced features like memory, tools, RAG, MCP, and guardrails require additional layers.
Artificial intelligence is quickly becoming part of everyday software development, but using it well requires more than adding a chatbot to an application. This article introduces AI fundamentals for ColdFusion developers, including large language models, prompts, tokens, context windows, temperature, Top-P, Top-K, statelessness, hallucinations, privacy concerns, and the role of application architecture. It also previews how ColdFusion 2025 Update 8’s native AI services can help developers move from simple chat model calls to more capable systems using memory, CFC tools, MCP, retrieval-augmented generation, and guardrails. The central theme is simple: the LLM is not your application. It is a reasoning engine your ColdFusion application supervises.
Update 5 of Adobe ColdFusion Builder is now officially supported on Cursor! Cursor has steadily grown into one of the most talked-about editors in the developer community. Its AI-native workflow — completions, codebase-aware chat, inline suggestions — has drawn developers across languages and stacks, and ColdFusion developers are no exception. Update 5 brings both together into a single development experience. […]
ColdFusion 2025 Update 8 added native passkey support, and I was genuinely excited to try it.
NOW LIVE — the June 2026 security updates for ColdFusion 2025 and ColdFusion 2023 have been released. This update includes important security fixes that mitigate vulnerabilities related to arbitrary code execution, arbitrary file write, information disclosure, stored cross-site scripting, and security feature bypass. What’s included The June 2026 release contains: Tomcat upgrades. See the respective tech notes for more details. Security fixes for multiple vulnerabilities (including remote code execution and privilege escalation vectors). Patches to harden request handling, deserialization paths, […]
I share here a table to try to make things clear.
Adobe has released Adobe ColdFusion 2025 Update 8, a major AI focused update that brings native AI capabilities directly into the platform.
The release adds built in support for:
LLM integrations like OpenAI, Anthropic, Gemini, and Ollama
Native RAG pipelines and vector databases
MCP support for AI agents and tools
AI guardrails and monitoring
Enhanced security with passkeys and Argon2
New CFML language and performance improvements
The core message of the update is that developers can now build enterprise AI applications directly inside existing ColdFusion apps without rewrites, separate AI stacks, or vendor lock in
NOW LIVE — the April 2026 security updates for ColdFusion 2025 and ColdFusion 2023 have been released. This update addresses multiple security issues and includes important mitigations we recommend you apply as soon as possible. What’s included The April 2026 release contains: Tomcat upgrades. See the respective tech notes for more details. Security fixes for multiple vulnerabilities (including remote code execution and privilege escalation vectors). Patches to harden request handling, deserialization paths, and template parsing logic. Updates to packages. Why […]
If you have ever asked an LLM a question and watched it respond with the calm confidence of a kid explaining quantum mechanics in terms of the latest Transformer movie (aka “Bruh… what?”), you already understand why Retrieval-Augmented Generation exists. Retrieval-Augmented Generation, or RAG, is an application pattern that pairs a generative model with a retrieval step so the model can pull relevant context from an external knowledge base before it answers. In the original RAG research framing, the big […]
