Beyond AI-Assisted Coding: Engineering the AI-Powered SDLC
Luis Vieira
Staff Software Engineer
Your team adopted AI. Delivery speed barely moved. Here's why:
Most engineering teams adopting AI coding tools see a quick win: writing code speeds up, number of commits and pull requests go up. But that hits a ceiling fast.
Cycle time barely moves, throughput doesn't 10x as promised, and often, things actually get worse, code piles up in review, releases grow bigger and more issues reach production.
The reason for this is that writing code is just one part of the job. The real constraints now sit everywhere around the act of writing code:
-Requirements clarification and task decomposition
-Code review
-Testing and validation
-Deployment and release
This workshop will shift your mental model from using AI as just a coding assistant, to understanding and implementing autonomous agents across the full SDLC, with verification, guardrails, and improvement loops.
You'll learn to encode your team's way of working, make agent output verifiable, and build feedback loops that improve the system over time.
You'll leave with patterns and examples based on real use cases you can apply to your team's workflow immediately.
A faster engine doesn't help if half the road is blocked. The most important work now isn't improving the engine, it's clearing the road.
What you’ll learn
Go from using AI as a coding assistant to designing agentic workflows across the full SDLC.
Explain what agentic engineering is and how it differs from interactive, prompt-driven coding.
Identify the ceiling of AI-assisted coding agents
Understand the shift shift toward specification, orchestration, verification, and improvement
Understand where the new bottlenecks are when throughput increases
Enable autonomous agents<
Create agents for task execution, code review, validation and monitoring
Turning failed runs into system improvements
Choose the right improvement lever (rules, skills, hooks, sub-agents)
Build evals to measure whether outcomes are improving.
Workshop agenda
Module 1 — From AI-Assisted Coding to Agentic Engineering
Shift your mental model from AI-assisted coding to agentic engineering. Understand the ceiling of interactive agents, and what the engineer's new role looks like
Module 2 — Designing the Agentic SDLC
Understand how autonomous agents can pick up work from existing team workflows, follow repository-defined rules, and produce reviewable proof of work across the SDLC.
Module 3 — Improvement Loops and Evals
Learn how agentic workflows improve over time. Turn failed runs into system improvements using the right levers: rules, skills, hooks, sub-agents. Build a small eval set to measure task outcomes.
Who this workshop is for
Software engineers using AI coding tools who want to design autonomous agentic workflows can help them move faster
Tech leads and engineering managers who want to understand how to increase engineering output using AI
Engineering leaders who adopted AI tools but aren't seeing it in delivery speed or business outcomes and want to understand why and fix it
What's included
Live sessions
Learn directly from Luis Vieira in a real-time, interactive format.
Lifetime access
Go back to course content and recordings whenever you need to.
Community of peers
Stay accountable and share insights with like-minded professionals.
Certificate of completion
Share your new skills with your employer or on LinkedIn.
Maven Guarantee
Your purchase is backed by the Maven Guarantee.
Frequently asked questions
Maven for Teams
Reimbursement
Get your company to pay
Everything L&D needs: email template, receipts, and certificate of completion.
Get reimbursedTeam discount
Learn with your teammates
Save 20%+ when 2 or more teammates enroll in the same cohort.
Save 20%+ with a teamPrivate cohort
Run a cohort for your org
A dedicated cohort with a custom schedule and curriculum, tailored to your team.
Book a private cohort€300
EUR
5–9am EDT