COURSE + TESTED REPOSITORY
AI Coding Guardrails
AI Coding Agents for DevOps: Production Guardrails Course + Lab
Build a coding-agent workflow you can check: task contracts, repository rules, CI gates and a reviewed handoff. Eight English video lessons with practical exercises.
Watch the free first lessonCZK 3,612
Secure checkout. Download links delivered by email.
- Format
- Video course + toolkit
- Language
- English
- License
- Individual
- 8 Full HD lessons · 2h 02m
- English subtitles, transcripts & chapters
- Practical exercises + original toolkit
AI CODING / FREE FIRST LESSON
Stop accepting “it works”.
Give a coding agent a task you can verify. Follow a Python validator example through a clear task contract, 16 acceptance cases and four deliberately broken implementations that challenge the evidence.
The downloadable course includes all eight lessons, exercises and the original toolkit.
INCLUDED VIDEO COURSE
From a clear task to a reviewed handoff.
2h 02m8 lessons · English
Watch in your own time. Eight Full HD MP4 videos in the download, with a local HTML course library. Extract the ZIP and open video-course/index.html.
Work through the examples. Eight video exercises complement the original toolkit and its four guided labs. Compare your attempt with the supplied reference solution.
Give AI Coding Agents a Verifiable Task19:40 minutes and seconds
Define an observable task, allowed changes and acceptance checks before an agent edits the repository.
One Repository Contract, Three Coding Agents13:48 minutes and seconds
Build a shared repository contract and distinguish file checks from verified agent instruction loading.
Permissions, Secrets and the Limits of Hooks13:32 minutes and seconds
Inspect hook and secret checks, then test where independent filesystem and credential boundaries are needed.
MCP: Inventory the Tools Before You Enable Them14:11 minutes and seconds
Document tool capabilities, data scope and revocation, and connect permission decisions to observable checks.
Terraform Without Apply16:26 minutes and seconds
Implement and verify a constrained Terraform change, inspect local plan evidence and stop before apply.
Turn Acceptance Criteria into CI Gates14:40 minutes and seconds
Make acceptance failures stop a local quality gate and map that gate to the supplied GitHub and GitLab examples.
Reviews That Converge14:51 minutes and seconds
Resolve a findings ledger, link duplicate findings and record evidence and a stopping rule.
The Production Handoff and Final Challenge14:59 minutes and seconds
Assemble a revision-specific handoff with test evidence, unresolved limits and the next human decision.
In the download
Approximately 278 MB. Includes MP4 videos, SRT subtitles, transcripts, chapter markers, exercises and the original toolkit.
Use the SRT files with a compatible media player. The included HTML player does not have an integrated subtitle switch.
Before you start
- Git, Bash 4+ and Python 3.9+; basic repository and command-line experience.
- A non-root POSIX environment, such as Linux, with symlink support for the permission exercises.
- Terraform 1.16.x for the supplementary plan-only video lab. No cloud credentials are required.
- Access to a coding-agent client is optional for vendor-specific practice.
The exercises use local examples. They do not deploy your production infrastructure.
The video edition includes eight English Full HD lessons (2h 02m), downloadable subtitles, transcripts and exercises, together with the original toolkit.
Your coding agent can propose infrastructure changes. It should not decide when they are safe to ship.
This practical course and tested repository help DevOps, platform and cloud engineers use Claude Code, OpenAI Codex and Gemini CLI with one shared control model: explicit repository instructions, executable acceptance criteria, least-privilege tools, plan-only Terraform, deterministic CI and human production approval.
The result
Turn an open-ended AI task into a bounded change with a reproducible finish line. Show what the agent could access, which checks passed, which findings remain and who owns any later apply or deployment.
What is included
- Eight implementation modules and four guided labs
- A canonical repository contract for Claude Code, Codex and Gemini CLI
- Executable task acceptance and findings-ledger validators
- Secret-path preflight and risky-command hook examples
- MCP inventory and cross-vendor tool-permission matrix
- A local-only Terraform lab with format, validate and saved-plan checks—never apply
- GitHub Actions and GitLab CI quality-gate examples without production credentials
- Implementation workbook, 25-case test catalogue and troubleshooting runbook
Built for real DevOps failure modes
Use the lab when agents miss acceptance criteria, multiple reviews fail to converge, a repository contains risky secret paths, or an MCP integration exposes more tools than the task needs.
Four hands-on labs
- One contract, three agents: keep shared rules in one canonical file.
- Terraform without apply: produce validation and plan evidence without cloud credentials.
- Convergent multi-agent review: deduplicate findings and enforce a stopping rule.
- MCP and secrets boundary: inventory tools and prove secret-like paths fail the preflight.
Who it is for
Individual DevOps, platform, cloud and infrastructure engineers; technical founders; freelancers; and small technical teams that already understand Git and basic CI/CD or Terraform.
What it does not do
The package does not deploy cloud resources, include credentials, guarantee compliance, replace IAM or certify AI output as safe. The included guardrails are defense in depth. You remain responsible for testing, change control and production decisions.
Original toolkit requirements
- Git, Bash and Python 3.9+
- Optional Terraform 1.5+ or OpenTofu 1.6+ for the full IaC exercise
- Optional Claude Code, Codex or Gemini CLI access for tool-specific practice
Need an organizational rollout? Scope an AI Coding Agent Readiness Assessment.
INSIDE THE DOWNLOAD
Inspect the workflow before you buy
QUESTIONS
Before you download
Is this a beginner coding course?
No. It assumes comfort with Git and basic DevOps or infrastructure-as-code concepts. It focuses on operational controls and reusable assets.
Do I need all three coding agents?
No. The shared workflow works with one tool. Cross-vendor files help you compare or add another tool without rewriting the repository contract.
Does the lab create cloud resources?
No. The supplied Terraform fixture is local-only and uses no cloud provider, backend or credential.
Is this an enterprise license?
No. The product uses an Individual license. Team, MSP or enterprise rollout requires separate terms.
Practical implementation guide: CI Acceptance Checks for AI Coding Agents →
Planning a team or company rollout? Talk to Cloudpeakify about enterprise delivery →