Your cart is empty.
Keep shoppingAI-Assisted Development: Coding Agents & Workflows & SDLC
New
112 students
AI-Assisted Development: Coding Agents & Workflows & SDLC
Master AI-assisted development using custom agents to automate workflows, debug code, and optimize pipelines instantly.
Created byACHRAF ER-RAYA
Last updated 8/2026
English
English [Auto],
What you'll learn
- Master context window engineering to securely inject massive legacy codebases into AI prompts without losing accuracy.
- Design and deploy deterministic, custom AI agents tailored to specific engineering roles using LangChain and CrewAI.
- Embed autonomous AI bots directly into your CI/CD pipelines to automate complex code reviews and staging deployments.
- Build an automated issue-resolution pipeline that parses error logs, writes patches, and submits pull requests.
Explore related topics
Course content
6 sections • 8 lectures • 1h 26m total length
Requirements
- Intermediate proficiency in a modern programming language (Python or JavaScript preferred). You will also need a basic understanding of REST APIs, Git workflows, and a free GitHub account to build and deploy the final autonomous pull-request project. No prior AI engineering or machine learning experience is required.
Description
“This course contains the use of artificial intelligence.”
Build AI-assisted development workflows that ship faster without sacrificing engineering quality.
Who this course is for
Developers who use AI coding tools but do not trust the output.
Full-stack developers who want repeatable AI workflows.
Technical leads creating practical AI standards for their teams.
Freelance developers who want to deliver faster with lower rework.
QA engineers and DevOps engineers improving AI-assisted delivery quality.
What you will learn
Define context packets that reduce AI hallucinations and scope creep.
Write plan-first prompts that reveal assumptions before coding.
Build specialized Builder, Reviewer, Tester, and Release agent modes.
Set boundaries that prevent AI from modifying protected areas.
Orchestrate ticket-to-pull-request workflows with clear evidence.
Generate useful test strategies and regression tests.
Add quality gates for linting, testing, security, and release readiness.
Create safe automated bug-fix workflows with human approval.
Measure cycle time, review time, rework, and escaped defects.
Produce a portfolio-ready AI-assisted SDLC case study.
Requirements
Basic programming experience in any modern language.
Familiarity with Git, pull requests, and software testing basics.
Access to an AI assistant and a practice or real code repository.
Final project
Create an AI-assisted delivery workflow for a realistic feature or production bug. You will submit a context packet, agent-mode specifications, workflow diagram, tested pull request, quality-gate evidence, and rollback plan.
Who this course is for:
- Mid-to-senior software developers, DevOps practitioners, and tech leads who are tired of generic AI chatbots hallucinating code. This course is specifically designed for engineers who want to stop writing repetitive boilerplate and scale their output by orchestrating autonomous, multi-agent AI teams directly within their existing development pipelines.