DEV Community: Raffaele Intorcia

Consideration on Intent-Driven Development

Raffaele Intorcia — Sat, 28 Feb 2026 11:18:08 +0000

In my in-depth study of hashtag#intent and hashtag#spec-driven development, I'm coming up with important insights regarding interactions between humans and AI. Thinking about intent, it's vague by nature, lacking technical details but ready to capture the needs of the customer (generally the person expressing the need).
The intent then evolves as knowledge increases, and the AI supports this process, reasoning, providing different perspectives, and stimulating conversation. The intent grows and improves.
In this sequence of phases, as well as during subsequent phases where code is discussed, there's a concrete risk to consider: hashtag#cognitiveoffloading, meaning the human losing in-depth knowledge of the system because someone else is making decisions.
A framework can help mitigate this problem by generating shared consensus on the issue and keeping all (human) stakeholders on the same page (and perhaps doing other things in parallel).
Then, whether the problem actually exists depends on what we're building: an MVP? A PoC? A complex application?
If we rely on the intent to create an application, we assume the risk that the #AI hashtag will make decisions we're not aware of. On a PoC, I can afford that, but elsewhere, not so much. I believe this is an example of why the importance of humans will be in the ability to govern the system.

Praxis meets AI Agents

Raffaele Intorcia — Sat, 14 Feb 2026 14:30:53 +0000

The development of Praxis, a hybrid IDD-SDD framework, is progressing, and embracing its dual nature as a framework/training project, I've begun working with #aiagents.

The first tentative approach involves activating an AI agent in the background, capable of responding to externally triggered tasks.

The initial functionality involves documentation production, which starts automatically when a #spec is archived. It's thrilling to put into practice what you've only seen with fascination in documents and YouTube videos. The approach is #choreography, but I'm already planning a major overhaul of the communication mechanism.

staytuned #praxisisalive

https://github.com/intoinside/Praxis

Intent and Spec driven development

Raffaele Intorcia — Tue, 03 Feb 2026 20:20:36 +0000

What is intent? What is a spec? Two terms that entered the SDLC after the arrival of AI. But what is it?
Intent is the expression of the purpose a system must have, the need it must satisfy, the objective it must achieve. It doesn't concern itself with the architecture, language, or parameters with which a system must be built. It simply aims to explain what you want to achieve.
With the intent in hand, you could choose to provide it to an AI and leave the entire implementation burden to it. It's convenient, simple, and quick, but it leaves you without control over aspects that could make a huge difference: for example, the AI creates a web app but you wanted a mobile one, or it chooses a local database but you wanted it in the cloud, etc.
This is where the spec comes in. From IDD, which speaks the language of the end customer, the game shifts to SDD, where the idea takes shape, is defined in terms of infrastructure, and defines how the elements must be implemented.
The AI reads the intent and formulates the spec (or specs) that the analyst and developer analyze and validate. Once validation is successful, the specs are passed to the AI, which creates the application.

This way:

the client consulted with the analyst, who identified the needs.
the analyst developed the system specs and consulted with the developer.
the developer orchestrated code generation based on the information contained in the spec.

This is what Praxis does; its first version contains the functionality to create the flow from intent to code.
Want to try it out? Click here!

Remember: the framework is under development; Praxis may contain bugs and has limited functionality, but it's growing!