AI already writes codefaster than you.Learn to direct it
Build an agent-based workflow to research, develop and verify software with engineering judgment.
› add Google sign-in
→ reading AGENTS.md · specs/ · DESIGN.md
→ spec: specs/add-google-sign-in.md · 3 acceptance criteria
→ worktree ../add-google-sign-in · implementer + validator
→ implementing only the files in scope
✓ validator: tests 11/11 · lint ok
✓ PR #145 ready for your review
Enter to run · try help or rm -rf /
- developers trained
- 10,000+
- years building software
- 15+
- Google Developer Expert
- GDE
- of AI Expert, live
- 6th cohort
- 90 student testimonials
- ★★★★★
Where you may have seen us
From loose prompts to a working system
The same request, two very different outcomes. The difference isn't the model or better prompting: it's the environment around the agent.
make me Google login
→ reading AGENTS.md and context
→ spec: scope + acceptance criteria
→ implementing (only files in scope)
✓ tests 12/12 · lint ok
✓ PR ready for your review
Turn the harness on
- tests
- ✓ 12/12
- scope
- only what the spec says
- your role
- reviewing the PR
That environment has a name: harness engineering. It is what we teach, what we implement with teams and how we build software.
Six layers that turn an agent into a working system
Models change every few weeks. What makes agent work reliable is the environment around them: the harness. Keep scrolling and watch it come together, layer by layer.
layer 01 · research
Discovery
Before writing code, the agent researches with you. A discovery skill turns a fuzzy idea into an MVP with a clear scope.
discovery — idea.md
$ skill discovery "clinic bookings"
→ questions on users, limits and risks
→ research.md: competitors and constraints
✓ mvp.md: 5 features and what is out
layer 02 · context
Context engineering
Rules, architecture and decisions live in the repo. Every session starts knowing where it is, without you repeating yourself.
AGENTS.md
# AGENTS.md
- Domain free of framework dependencies
- Specs in /specs before implementing
- Nothing merges without green tests
✓ same context for people and agents
layer 03 · execution
Execution environments
The tool does not matter. Hooks and subagents with separate roles: one implements, another validates, each with clear limits.
agents — roles
$ agent run implementer specs/export-csv.md
→ implementer: only files in scope
→ validator: read-only, against the spec
✓ pre-commit hook: lint + tests
layer 04 · loop and verification
Loop engineering
Agents in parallel, each in its own worktree with its own PR. Work closes with evidence (tests, evals, Definition of Done), not promises.
loop — feature_list
$ git worktree add ../export-csv
→ 3 agents in parallel, no collisions
✓ tests 24/24 · evals ok
✓ PR #143 ready for your review
layer 05 · product
AI Product
AI stops living only around your code and moves into your app: APIs, function calling, RAG and local models where they make sense.
src/ai/rag.ts
await rag.search("return policy")
→ 4 relevant chunks · embeddings
POST /v1/chat/completions
✓ 200 OK · answer citing sources
layer 06 · orchestration
Your own agent
All together: an orchestrated agent that moves features from spec to merge. You decide where to review, and nothing merges without you.
orchestrator.ts
✏️ dark-mode → spec
⚙️ search-filter → implementing
👀 auth-login → waiting for your review
✅ 12 merged · human supervision
✓ harness complete
The agent is whatever comes next. The harness is yours.
It lives in your repo, works with Codex, Claude Code, Cursor or OpenCode and does not expire when the model changes. It is exactly what you build in AI Expert.
Build your harness in AI Expert (in Spanish)Learn to direct agents live, on your own project
Flagship program · in Spanish
AI Expert
Six weeks to build your AI development harness piece by piece, with live classes, weekly Q&A sessions and a private community.
- 6 live weeks
- 60 h in total
- 2 months of models included
- 40 seats per cohort
6th cohort · starts November 3
View the programIncluded with your seat
Android Legacy Vault
Kotlin Expert, Jetpack Compose and Testing Expert: the complete classic library, so you have judgment before you delegate.
Catalog
All programs
Architect Coders, Kotlin, Compose, Testing and Accessibility: the programs thousands of developers have trained with.
View catalogWhat changes when you stop asking and start directing
Their own words, as a diff: in red how they worked before, in green what they took away. Nothing rewritten, only trimmed.
diff --git a/alumnos/santiago-perez-barber.md b/alumnos/santiago-perez-barber.md
@@ AI Expert · +19 −8 @@
1−You start out just "tinkering" with AI tools…
2+…end up mastering a set of resources that are useful for your daily work…
3+…and exponentially increase your productivity.
Santiago Pérez BarberBytacora Soluciones Informáticas SL · ★★★★★
And the rest of the history
90 reviews · ★★★★★ · every program
Hover to pause · click a review to read it in full
The latest things we have tried with agents
We test tools, models and workflows on real projects and share what works and what does not. No hype.
Go to the blog$git log --oneline blog/
- 87e80122026-07-08What is Loop Engineering? A practical example with Codex
- 87a36e12026-06-24How to use 1Password to provide secrets to AI agents and desktop apps
- d7f572c2026-04-07How to Enable Thinking Mode for Gemma 4 in LM Studio and OpenCode
- c459df92026-03-26MCPs Aren't Dead—They're Just Out Partying
- 16bfc922026-03-16I Don't Think the Token Subsidy Is Going Away. And That Says a Lot About the Future of AI
$ git show 87e8012
commit 87e8012
Author: Antonio Leiva · 2026-07-08 · 11 min
People are starting to talk quite a lot about Loop Engineering. As always happens when a new label appears, part of it is hype, but another part is genuinely useful: once something has a name, we can discuss it more…
$ ▊
Training, implementation and software when the challenge belongs to the team
We help turn AI into real processes and tools your team can use and maintain.
Instructors who apply AI in real projects
Antonio and Nino combine software development, agent systems, automation, data and teaching experience. They work directly on both training and company projects.
antonio@devexpert
Antonio LeivaGDE
DevExpert founder · Google Developer Expert
nino@devexpert
Nino RuanoAI · Big Data
AI and Big Data specialist · Instructor
It is a real shell (well, almost). Type help to see the commands.
Stop fighting the agent. Start directing it.
Learn with us in AI Expert or tell us what your team needs. You build the harness once; what changes is everything you can do with it.