From beginner to production-ready with agentic AI
Every session is 3:00 PM – 6:00 PM NZDT, led by Bhaskar Reddy Marrikunta. Concepts build week over week, and every hands-on lab runs on Copilot Studio or Microsoft Foundry — the same tools used in real deployments.
Sessions are not recorded
Every session is delivered live and is not recorded, so active participation matters. Please take your own notes each week, complete that week's task, and email it to media@sirisapps.com before the next session. Consistent, active participation is how you get the most out of the 8 weeks and qualify for recognition.
Weekly audience spin
Each week we will spin from the joined audience. The winner gets 10 minutes to present an idea, use case or lesson learned to the group. Bring your best thinking and stay actively involved — strong ideas and useful use cases will be rewarded.
What actually makes a system 'agentic', how LLMs work under the hood, and getting your environment ready.
Concepts covered
- •LLMs vs agents: reasoning, planning and acting in a loop
- •Tokens, context windows, temperature and cost basics
- •The perceive -> plan -> act -> observe agent loop
- •Prompt vs system message vs tool definitions
In detail
- We start from zero — no prior AI experience assumed. You'll see the difference between a single prompt/response call and an agent that can decide what to do next.
- We cover how context windows and tokens affect both cost and quality, so you can reason about tradeoffs later when you design agents.
- By the end of the week you'll have Copilot Studio and Microsoft Foundry access working end to end.
Lab 1: Your first Copilot Studio agent
- 1.Sign in to Copilot Studio with your trial account and create a new agent.
- 2.Give it instructions describing a simple assistant (e.g. an FAQ bot for a fictional product).
- 3.Test it in the built-in test chat pane and iterate on the instructions until responses feel on-topic.
- 4.Publish the agent to a Teams or web channel and share a screenshot in the WhatsApp group.