Projects built with Claude Code
Your app, portal or internal tool, built by our team with Claude Code and reviewed by people at every step.
Claude Code is Anthropic's coding agent: it reads your codebase, plans, edits files and runs commands from the terminal, the IDE or the web. It is the tool we build most of our own software with. We use it to deliver your project, and we set it up and teach it so your developers get the same speed.
Today
After
Three agents, one CLAUDE.md, every change reviewed
The tools and AI we work with
Tick what sounds familiar. Most AI-built apps hit the same walls on the way to real users.
Tick the ones that sound like you.
Your app, portal or internal tool, built by our team with Claude Code and reviewed by people at every step.
The instructions Claude reads in every session: your stack, commands, conventions and pitfalls, kept short and current.
What it may run without asking, what always needs approval, and hooks that format, test or block on their own.
Your docs, issue tracker, database or CRM made available to Claude through MCP servers, with the access you decide.
Specialised subagents for review, tests or migrations, and Claude Code running in your CI for routine work.
Hands-on sessions on your own codebase, in person in Québec or Cotonou, or online, in English or French.
A call about your codebase, your team and what you want Claude Code to take on.
CLAUDE.md, permissions, hooks and the first MCP connections, tested on real tasks.
We deliver the project ourselves, or work beside your developers on their own tickets.
A training session, then a look at what changed: time per task, review time, fewer regressions.
Which commands it may run alone and which always ask first, set once for the whole team.
Environment files and credentials excluded from what it reads, and production kept separate.
Changes go through pull requests and a human review, however good the agent is.
Each MCP connection gets only the access it needs, and you know what leaves your systems.
Both are valid. We recommend one after seeing your app, its users and where it is going.
Founders who built a first version in Claude Code and need it ready for customers
Companies whose internal tool, built by a manager with AI, is now used every day
Agencies and consultants who need a technical partner behind their AI builds
Development teams who want AI coding to speed them up without lowering quality
Apps rarely stay on one tool. Each platform has its own page.
No. TECHMA is an independent agency that builds with Claude and Claude Code and trains teams on them. Claude and Claude Code are trademarks of Anthropic.
A file in your repository that Claude Code reads at the start of every session: how to build and test the project, its conventions and what to avoid. A good one makes results much more consistent.
Yes, through MCP servers: documentation, issue trackers, databases, CRMs and more. We set them up with read or write access as you decide.
With the right setup, yes. Permissions decide what runs without approval, hooks can block risky actions, and every change still goes through review.
They overlap. Claude Code shines on larger tasks across a codebase and in automation; editors like Cursor and Windsurf shine inside the editor. Many teams use Claude Code with one of them.
Yes. In person in Québec or Cotonou, or online, in French or English, on your own codebase.
A free 30-minute call, in English or French. You leave with a clear next step.
What would you fix first?
On the call we walk through your sales process and find where leads and follow-ups get lost.
Ask TECHMA
Answers from our siteAsk in your own words. I answer from this site, tell you honestly when it is not something we do, and can book your free call right here.