Claude Code: Ready to Merge
Two hands-on days, from your first prompt to a pull request your team trusts.
- Format
- 2-Day Intensive
- Duration
- 2 days
- Group size
- 12 to 25
- Level
- All levels
Claude Code can write a feature in minutes. That’s the easy part now. What it doesn’t tell you is whether the change fits your codebase, passes the right tests, or is safe to merge. Someone still has to decide what context to give it, how to break the work down, and how to check what it hands back.
Over two days your team works in a shared codebase with tests, a database and conventions of its own. They start with the fundamentals, then move through planning, building, verifying and reviewing. By the end of the second day they take a GitHub issue to a reviewed pull request, using the skills, hooks and subagents they built along the way.
This isn’t a tour of features. The features are free, and they date fast. What’s worth two days in a room is the judgement. What to hand over, what to check, and where your own review still matters.
Running a conference? The same two days work as a pre-conference workshop. Write to [email protected] and tell us about the event.
What your team leaves with.
Outcomes · 5- A working picture of how Claude Code works, and how the context it gets shapes what comes back
- Practice planning and slicing work so every change is one you can check and review
- Skills, hooks and subagents shaped around your codebase and the way your team already works
- A GitHub issue taken all the way to a reviewed pull request, with Claude doing the typing
- A shared read on what to automate, what to delegate, and where a human review still matters
How the days run.
2 daysThe fundamentals
Start with a real task on a shared codebase, then find out what's going on underneath. Context, planning and review, in that order.
- How Claude Code works, what belongs in its context, and choosing a model with an eye on cost
- Preparing a codebase with useful project instructions, tests and a short spec
- Breaking a feature into small steps, then planning, building and verifying each one
- Reading Claude's diffs, not its summaries, with tests and linters as the feedback
Into the team's workflow
Turn what worked on day one into something the whole team can install. Then take one issue from the backlog to a pull request ready for review.
- Skills, hooks, subagents and MCP connections for the team's recurring work
- Packaging them as a plugin the team installs
- Claude Code in the development cycle, through GitHub issues, pull requests and Actions
- Permissions that fit the job, and when to stay involved or let Claude run
Who it's for.
Hands-on- Engineers who build or maintain software that runs in production, in any language
- Teams getting started with Claude Code, and teams who use it daily and want to go deeper
- Anyone comfortable with Git and the command line
- A laptop with their usual IDE or editor
- Git and a GitHub account, for the issues, pull requests and Actions in the exercises
- A Claude Pro plan or above, or an Anthropic API key. Pro works, but its limits can run out on a heavy day
- The runtime for the shared repo. Setup steps go out before the workshop
Adapted to your team.
Before the dayWhat's above is the shape, not a script. We start with a 30-minute call about your codebase, your stack and what your team has already tried. The exercises get rebuilt around that, and anything that doesn't apply to you gets cut.
- The examples, moved into your domain
- The depth, tuned to the room
- The length, from 2 days to what your calendar allows
Questions we get.
FAQ · 5Does the team need to have used Claude Code before?
No. Day one starts from how it works, so nobody is left behind. Engineers who already use it every day tend to get the most out of day two, where it gets shaped around the team rather than used out of the box.
Is it only for .NET teams?
No. The practices carry across languages. The exercises run on a shared repo, and its stack gets agreed on the call, so it can sit close to what your team writes every day.
Which Claude plan does everyone need?
A Claude Pro plan or above, or an Anthropic API key. Pro works, but a full workshop day is heavy use and its limits can run out by the afternoon. If that's a worry, say so on the call and we'll work out the access before anyone arrives.
We can't send our code to an AI provider. Does that rule it out?
Not necessarily. The exercises run on a shared repo, not on your codebase, and permissions are part of day two. Tell us what your security policy allows and the day gets built around it.
Can it be run remotely?
Yes, on site or remote. It's a build-along, so remote works as long as everyone's setup is ready before day one starts. The steps go out ahead of time.
Who runs it.
In the roomGui Ferreira facilitates start to finish. He's been writing software since 2006 and is a Microsoft MVP. There's no junior trainer and no handover.
guiferreira.meThe other workshops.
Catalogue · 3Build Your First AI Agent in .NET
Two days building an agent that reasons, uses tools and holds a conversation, in your stack.
03Designing Tests That Survive Refactorings
Half a day on why the test suite breaks every time someone refactors, and what to do instead.
04Mastering Test-Driven Development in C#
Two hands-on days turning TDD from a thing the team has read about into a thing the team does.
Request this workshop.
10 questions, 3 optionalTell us about the team who'd be in the room. We read every one of these. If it's a good fit, we'll set up a 30-minute call and send a proposal within 48 hours of it. If it isn't, we'll say so.
