Join Nahid Farady, PhD (Principal Tech Lead, AI Security & Privacy · Microsoft) for a free live session.

Nahid Farady, PhD
Principal Tech Lead, AI Security & Privacy · Microsoft
⭐ 4.9 / 5
The FDE Sprint starts straight at the distinctly-FDE skills — scope, build, deploy, and own real AI systems inside customer environments. Five weeks of craft plus a portfolio-grade capstone: no repetition of agent, RAG, or multi-agent foundations, and no interview prep. The shortest way to add the FDE layer to what you already build.
Take a customer engagement end to end — Scope → Build → Deploy → Operate — from discovery and SoW through enterprise wiring, RBAC, and handover.
Turn an ambiguous customer ask into an SoW with eval-anchored acceptance criteria, a pricing model, and a defensible solution architecture.
Ship inside customer environments: APIs as agent tools, hardened MCP servers, end-to-end RBAC, compliance (SOC 2, HIPAA, GDPR), and observability.
Deliver PriorAuth AI — a real customer-style engagement from discovery to production handover — across Azure, GCP, and AWS.
This sprint is designed for:
You've already built agents, RAG, multi-agent systems, and evals — now add the customer-facing FDE layer that makes you deployable.
You can already ship LLM / agent applications; add scoping, enterprise wiring, governance, operations, and customer handover.
Step out of the model lab and own production AI systems inside customer environments, not just demos.
Bring FDE-grade delivery discipline to your current team's AI projects — without a job switch.
6 weeks · 3 sessions per week
Leave with real work to show, not just a certificate.
Built live with the instructor: from customer discovery, SoW, and solution architecture to a multi-agent + MCP + RAG system that reads claim files (police reports, photos, repair estimates), surfaces high-confidence first decisions to adjusters, flags edge cases for human review, and deploys to production with a proper handover. Primary stack: OpenAI Agents SDK + Azure AI Foundry.
The Week 4 live project: build and harden an MCP server as the enterprise integration layer across two or more systems, exposing APIs as agent tools with OAuth2 / Entra and end-to-end RBAC.
Your learner-led FDE capstone: own a full engagement at a regional hospital network — run discovery, write the SoW, then build a multi-agent co-pilot that reads chart notes, retrieves payer policy and medical-necessity criteria, drafts citation-backed auth requests, and routes ambiguous cases to a human reviewer. Custom FastMCP server scoped per facility, end-user SSO, full audit logging. Shipped on Azure (primary) + GCP + AWS.

Principal Tech Lead, AI Security & Privacy · Microsoft
⭐ 4.9 / 5
Nahid leads AI security, privacy, and responsible AI engineering at Microsoft Copilot, with prior roles at Google Cloud and Capital One CyberML. She holds a PhD from Virginia Tech and brings 10+ years of applied experience in cybersecurity, threat modeling, and ML deployment at scale. She also teaches AI and security as adjunct faculty at UC Berkeley.
All sessions are instructor-led and live. Recordings available within 24 hours.
SUNDAY
9:00 AM PDT
Live ClassThe week's 3-hour live FDE craft session — taught live by a practicing FDE; recordings are backup for missed classes.
WEDNESDAY
6:00 PM PDT
Office HoursOptional instructor Q&A to unblock your weekly build and capstone work.
THURSDAY
Self-paced
Capstone BuildGuided, self-paced work on the PriorAuth AI capstone and weekly assignments (~4–5 hrs).
with Nahid Farady, PhD · Principal Tech Lead, AI Security & Privacy, Microsoft
What you'll walk away with:
🎁 Bonus for attendees:
Get "The FDE Engagement Starter Kit"
An SoW template with eval-anchored acceptance criteria, a scoping-question bank, and a reference solution architecture — ready to use on your next customer engagement.
Claim your free seat
Skills you can deploy on Monday morning.