Agentic AI Buildcamp for Engineers
Paramanantham Harrison
Engineering leader, Agentic AI educator
Your agent demo works. Make it production-grade in four weeks.
Your agent demo works. Then come the questions that decide whether it ships. Who is this agent acting as? What stops it obeying an instruction hidden in an issue? What does each task cost? How do you know a prompt change did not make it worse?
The answers are the system around the agents, where most agent projects stall: auth, guardrails, governance, caching, token cost, evals, observability and durable work.
You build that system around one project: AI Mission Control, a board where agents with roles pick up work from GitHub and Linear, ask a human before anything risky, and log every run with its cost.
Week 1, Architect. Outcome: a board with one agent that answers from your company's tools, inside a token budget.
Week 2, Build. Outcome: a team of agents that takes an issue to a pull request after a human approves.
Week 3, Secure and deploy. Outcome: an identity per agent, guardrails against prompt injection, and a deploy behind an LLM gateway with traces.
Week 4, Govern and extend. Outcome: approval rules as code, an eval gate on every model change, and demo day.
What you’ll learn
Design, build and deploy a production-grade agentic AI system in four weeks: your own AI mission control, secured, measured and team-ready.
Draw the loop, the harness, the roles and the board before writing code.
Choose a model for each role on quality, latency and cost.
Lay out context and memory so prompts hit the cache.
Split the work across agents with tools scoped through an MCP gateway.
Make long-running work durable with retries and idempotent writes.
Keep a human in the loop for every action that cannot be undone.
Give each agent its own identity and check every action against the user's permissions.
Block prompt injection and keep secrets out of the model.
Deploy behind an LLM gateway with caching and a budget per tenant.
Write approval rules as policy in code.
Gate every prompt or model change on evals in CI.
Trace every run in Langfuse and add new agent roles from reviewed skills.
Learn directly from Paramanantham
Paramanantham Harrison
Engineering leader, Agentic AI educator
Who this course is for
Software engineers whose agent demo now has to pass a security review (you learn identity, permissions and guardrails)
Tech leads and architects choosing models and gateways for their team's agents (you learn to design for cost, quality and failure)
Platform and backend engineers asked to run agents for many teams or customers (you learn tenants, budgets, traces and evals)
Prerequisites
You write code every week
The sessions build in Python, and you can read TypeScript.
You know Git, Docker and HTTP APIs
You can clone a repository, run containers and call an API.
You have an LLM API key
Any major provider works; budget some API credit for the weekly projects.
What's included
Live sessions
Learn directly from Paramanantham Harrison in a real-time, interactive format.
Live build sessions
Every session is hands-on. You build the next part of your AI mission control while I build it alongside you.
Weekly office hours
A live hour each Friday to get unblocked on that week's project.
Starter repo and sandbox
The AI mission control starter, ready to run from the first session, so your time goes into the system rather than setup.
Capstone demo and live feedback
Demo your secured, deployed system on the final Friday for feedback from me and the cohort.
Recordings you keep
Every live session is recorded, so a missed session or a second look is always there.
Cohort community
A space to compare designs and get help from engineers building the same system.
Certificate of completion
Share what you built with your employer or on LinkedIn.
Maven Guarantee
Your purchase is backed by the Maven Guarantee.
Course syllabus
12 live sessions • 8 lessons • 4 projects
Week 1
Week 1: Architect
Nov
16
Design the System
Nov
18
Context Engineering and Memory
Nov
20
Office Hours
Week 2
Week 2: Build
Nov
23
A Team of Agents
Nov
25
Durable Work and Approvals
Nov
27
Office Hours
Schedule
Live sessions
4-4 hrs / week
Two build sessions a week on Mondays and Wednesdays, recorded in case you miss one
Mon, Nov 16
5:00 PM—7:00 PM (UTC)
Wed, Nov 18
5:00 PM—7:00 PM (UTC)
Fri, Nov 20
5:00 PM—6:00 PM (UTC)
Office hours
1-1 hr / week
Fridays, live Q&A where each week's project is due
Projects
3-5 hrs / week
One part of your AI mission control each week
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$997
USD