The Power of Prompting with AI Native Development - Simon Maple

Your code should be a disposable artifact. Discover how AI native development makes the specification, not the code, the true source of truth.

#1about 7 minutes

Demonstrating the limits of iterative AI prompting

A live coding demo shows how iterative, stateless prompts fail to build robust features, highlighting the need for a persistent specification.

#2about 5 minutes

Understanding when prompting fails and how LLMs process requests

LLMs struggle with overly large contexts, sub-token character manipulation, and math, and they process prompts sequentially, which impacts how they interpret constraints.

#3about 8 minutes

Advanced techniques for writing effective and structured prompts

Improve LLM outputs by using structured formatting like XML tags, framing tasks with constraints upfront, and using a 'say' operation to guide the model's thought process.

#4about 6 minutes

Why code-centric development becomes fragile and hard to maintain

In traditional development, code becomes the source of truth, coupling the 'what' with the 'how' and making the system brittle as requirements, bugs, and framework changes accumulate.

#5about 4 minutes

Moving to a spec-centric model with AI

A spec-centric approach makes the specification—combining requirements and tests—the long-lived source of truth from which disposable code is generated.

#6about 9 minutes

Key benefits of the AI-native development paradigm

AI-native development creates adaptable software through context, enables autonomous maintenance for security and performance, and makes development more inclusive for non-coders.

#7about 4 minutes

Exploring the future and community of AI-native tools

An overview of the Tessl platform, the AI Native Dev community, and a landscape of tools that are shaping the future of specification-driven development.