Spec a Product Before AI Builds It
From vague idea to actionable product plan
10 lessons33 minFree Oct 10 to 11
Lesson 1 is free now. Free Oct 10 to 11 (opens Fri 22:00 CEST) with a free account.
What's inside
- Why specification-first development matters
- How AI changes the requirements process
- What you'll build in this workflow
What you'll gain
Create specs and plans AI can execute against, without wasting cycles on rewrites.
- You'll take a raw product idea and systematically build a complete specification — requirements doc, feature definitions, tech stack rationale, and validated spec — all using AI to accelerate each step.
When to use it
- Starting a new project or feature from scratch
- Turning stakeholder conversations into actionable specs
- Need a structured approach to requirements gathering
You'll reach for it: Every new project or feature
What you leave with
1
Template
1
Checklist
21
Prompts
Syllabus
10 lessons · 33 min1
Why Planning Beats Vibe Coding
In this lesson, you'll see why a bit of time spent planning up front pays off far more than jumping straight in and asking AI to build whatever you think you want in the moment.
4 minFree
2Turn a Vague Idea Into a Structured Spec
In this lesson, you'll learn how to take a raw idea, whether that's a single sentence, a collection of notes, diagrams, or even meeting transcripts, and feed it into an LLM to generate a rough but structured specification that you can then refine and iterate on.
6 min
3Shaping the Specification
In this lesson, you'll take your rough specification and turn it into something far more solid by removing assumptions, adding missing details, cutting out anything unnecessary, and introducing the right technical information. By the end, you'll have a refined, easy-to-read specification that's much clearer to understand and ready to iterate on or build from.
3 min
4Give AI Technical Constraints from Day One
In this lesson, you'll add light technical details to your spec. Why? Because these may define what our features look like later.
1 min
5Tell AI What It's Not Allowed to Build
In this lesson, you'll refine the spec by clearly defining what the system should not do, setting firm boundaries so AI knows exactly where to stop.
3 min
6Use AI Mockups to Expose Gaps in Your Spec
In this lesson, you'll generate wireframes or example designs from your specification, using AI.
2 min
7Have AI Poke Holes in Your Plan
In this lesson, you'll test the plan against real user journeys and technical scenarios to make sure the system holds up, the flows make sense, and it actually meets the needs it was designed for.
2 min
8What Might We Have Missed?
In this lesson, you'll test the plan against real user journeys and technical scenarios to make sure the system holds up, the flows make sense, and it actually meets the needs it was designed for.
3 min
9From Spec to Features
In this lesson, you'll use the refined specification to generate a high-level list of features. This gives you a clear starting point for development, without diving into low-level technical decisions just yet.
3 min
10Scaffolding the Boilerplate
In this lesson, you'll scaffold a simple starter project to create a clean base for development, revisiting assumptions and using the process to spot gaps or questions in the specification.
6 min
Access
Yes, Oct 10 to 11. It's one of the 6 courses free to watch with a free account that weekend (opens Fri 22:00 CEST).
Every lesson of every course, the full notes, transcripts and prompts, and the Unlearn-built tools. Blog posts and the tools that are public on GitHub stay free for everyone.
It shows as Completed on your profile and counts toward its role. Finishing every step of a role earns the role certificate.
Yes. Team plans can assign this course, or a whole role, and follow progress in Team.
Next step
Next in Product Engineer
Spec-Driven Development with OpenSpec
Deep dive · 9 lessons · 56 min