What you’ll build in 2 days
Day 1 · From Vibes to a Spec That Holds
Build the fun way, find where it quietly goes wrong, and fix it at the source.
You will work on:
-
Building a working app from a plain-language description, using the AI tool you already use
-
Spotting code that works but solves the wrong problem
-
Turning vague prompts into a lightweight spec – clear intent, explicit constraints, checkable \”done when\” criteria
-
Driving the same build from your spec, and comparing the results
-
Reading the difference between a spec that holds and one that drifts
Focus:
Stop guessing what the AI will produce. Say what you mean precisely enough that it builds the right thing with any tool.
Day 2: Guardrails You Build Yourself
Turn a working app into one you’d actually deploy.
You will work on:
-
Mapping the \”certainty ladder\”: an instruction the agent might follow, versus a check that runs every time whatever wrote the code
-
Choosing what earns your trust in a commit, then turning each one into an enforced check
-
Building your own preflight check by working with your AI tool – the lasting skill is making guardrails, not being handed them
-
Enforcing checks across the whole codebase, and holding the agent to your standard — no self-granted exceptions, no \”good enough\”
-
Using an AI agent to review for design issues like duplicated logic and weak structure
-
Optional advanced step: pointing an adversarial agent at your own app, as one more check you can build
Focus:
The guardrails are what let you ship code you didn’t read line by line — and you leave with a portable setup you can drop into any repository.
Lead Trainer
Ben Dechrai
Ben Dechrai is a technologist with a strong focus on security and privacy, recognised as an MVP for his exceptional contributions to the community. Known for his ability to distil complex technical concepts into engaging, digestible portions, Ben empowers developers through a deep understanding of design principles, security considerations, and coding practices. With over two decades of experience in software engineering, security, and architecture, Ben is a published author and has consulted for companies and investors across numerous industries. He is deeply involved in the tech community, running technology conferences and workshops to share his expertise.
Learning Format & Materials
Hands-On, Code-First Learning
Your AI assistant wrote the feature. The tests pass. It looks correct. But you didn’t read every line, so how do you know it does what you meant? Maybe the model got it right the first time. Maybe not. From where you sit, those two outcomes look identical. That uncertainty, not the quality of any one tool, is the real distance between ‘I built something’ and ‘I can put this in production.’
This hands-on, two-day workshop closes that distance. Day one is about aim: build fast and loose, hit the moment the assistant confidently produces something other than what you intended, and learn that the specification, not the code, was always the hard part. You’ll leave with an app that does what you actually meant.
Day two is about confidence. You’ll build your own pre-commit checks for quality, security, dependency vulnerabilities, and your own design standards, and wire them into a gate that blocks bad commits across the whole codebase.
For developers who already code with AI and want to move from ‘it works on my machine’ to ‘I’d put my name on this.’ Bring a laptop and the AI tool you already use.
Vibecoding Bootcamp — Dates & Tickets
*incl. 10% Team Discount when buying 3 or more tickets
