Staff Software Engineer

AI coding tools make implementation faster. But typing code is only one part of getting software safely from idea to production.
Teams still need to turn ambiguous requests into clear plans, understand how changes affect an existing system, verify that they are safe, and make sound decisions about what reaches production.
When code becomes cheap to produce, context, judgment, and verification become the limiting factors.
This is why faster coding does not automatically mean faster delivery. Improving one part of the workflow has limited impact when the rest of the system continues to create bottlenecks.
This workshop gives you a practical method for improving delivery with agents. You’ll learn to find the constraints slowing down your SDLC, design agents that can safely take on bounded work, and improve them over time using proof of work, feedback, and evals.
Learn how to find delivery constraints, design trustworthy agent workflows, and improve them through evidence, feedback, and evals.
Understand why faster code generation does not automatically mean faster delivery.
Identify how constraints shift to context, judgment, review, verification, and release decisions.
Recognize the engineer's role in specifying work, shaping workflows, and verifying outcomes.
Identify common constraints across planning, implementation, review, testing, release, and operations.
Decide where an agent can safely reduce waiting, rework, or uncertainty.
Define bounded workflows for use cases such as triage, code review, validation, release risk, and monitoring
Give agents the right context through repository rules, task information, and MCP-enabled tools.
Define permissions, execution boundaries, and clear paths for human escalation.
Require proof of work: evidence, checks performed, confidence, and next actions.
Use traces and failed runs to understand where a workflow breaks down.
Improve the right part of the harness: rules, skills, context, hooks, subagents, or tools.
Build a small eval set to measure whether changes make the workflow more reliable.
AI makes implementation faster, but not necessarily delivery. Learn why bottlenecks move elsewhere in the SDLC and how to identify the constraint limiting your team.
Explore common bottlenecks from planning to production. Learn where agents can safely help, where human judgment remains essential, and how to spot a worthwhile workflow.
Learn how to design an agent harness: context, tools, permissions, proof of work, verification, and human escalation paths.
Use failed runs and traces to improve rules, skills, context, hooks, subagents, and evals. Ensure that agent workflows become more reliable through evidence, not guesswork.
Software engineers using AI coding tools looking to improve their team SDLC
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

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.
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
5–8am EDT