Building and Modernising Apps with Agentic AI - Julia Kordick

Is your AI assistant more frustrating than helpful? The problem might be your prompts, not the tool.

#1about 3 minutes

Introducing spec-driven development for agentic AI

The open-source project 'spec' helps structure developer intent, shifting the focus from writing code to writing effective specifications for AI agents.

#2about 4 minutes

Overcoming common adoption challenges with agentic AI

Developers often struggle with effective prompting and defining quality gates, leading to a divide between organizations with disciplined processes and those adopting AI naively.

#3about 6 minutes

How to structure prompts and specifications for LLMs

Use tools to translate natural language brain dumps into structured Markdown and bulleted lists, which are the most effective formats for AI agents to follow.

#4about 4 minutes

Why low-effort prompts fail and code should be iterated

Vague prompts like 'fix it' produce poor results regardless of the AI tool, and iterating on generated code is more efficient than constantly regenerating it from scratch.

#5about 6 minutes

Create internal prompt libraries to scale AI usage

Successful teams build inner-sourced libraries of effective prompts and specs to improve consistency, reduce token costs, and avoid overwhelming projects with massive pull requests.

#6about 11 minutes

The reality of AI adoption and how to keep up

A significant gap exists between the hype around agentic AI and the reality that most organizations are still at the very beginning of their adoption journey.

#7about 2 minutes