Skip to content
Cursos/DeepSeek Harness (DSH)/DeepSeek Harness · Phase 5
Revisión pendiente desde 21 ago 20262 fuentes primarias

Workspaces, permissions and safety

The workspace is the agent's operating boundary. A well-defined boundary makes an experiment reviewable work.

Qué vas a conseguir ahora

Una decisión o prueba aplicada a «Workspaces, permissions and safety».

  1. 1Entiende el criterio
  2. 2Haz una práctica pequeña
  3. 3Guarda una evidencia
Evidencia

Una nota breve con qué hiciste, qué salió bien, qué falló y qué revisarías después.

Objetivos de aprendizaje
  • Separate a sandbox from valuable repositories.
  • Apply least privilege.
  • Prepare recovery before allowing edits.

Design the boundary

Create a dedicated working directory, limit the task to it and use Git before allowing writes. A workspace is not a complete security guarantee: review which tools the active profile can actually invoke.

Terminal
git status
git switch -c dsh/controlled-test
git add -A && git commit -m "State before DSH"

Operating rules

Define in advance what the agent may read, write, execute and communicate. Irreversible or external actions need a human approval.

  • Keep secrets out of prompts, logs and screenshots.
  • Do not connect production during early tests.
  • Review the diff before accepting changes.
  • Stop the session when it leaves the stated goal.
Comprueba que funciona. Save the initial commit hash and the granted permissions. You should be able to return to the starting point without losing work.
Guardar y reabrir el proyecto.
Useful safety is workflow design, not a warning at the end.

Si has guardado la evidencia de esta lección, continúa con «Plugins and custom profiles». Si no, repite la comprobación antes de avanzar.

Complete Aulafy mapSee how this lesson fits without leaving your path.

Complete Aulafy map

How all courses connect

This is not a checklist. Start with the foundation, choose an outcome, and go deeper only when your project needs more control.

  1. 1Understand
  2. 2Apply or build
  3. 3Operate with confidence
01

Choose an application

Turn the foundation into a visible outcome: a website, a business improvement, media, or an interactive experience.

Continue into the technical branch when you need to maintain code, data, or infrastructure.

02

Build with code

Prepare your environment, work with coding agents, and run models while keeping control of your projects.

This branch prepares you to design and operate reliable AI systems.

03

Take systems to production

Combine retrieval, agents, evaluation, security, deployment, and model adaptation when the problem requires it.

You do not need every course: choose the component your system needs and return as it grows.

View full catalogue