Applied learning
Practicums
Go beyond reading: build an artifact, pass validation, and produce evidence of readiness.
Resilient AI API Client
Build a production-ready LLM API client with structured output, validation, retries, timeouts, idempotency, tracing, and tests.
Evidence-first Knowledge Assistant
Build a RAG assistant that answers only from verified evidence, shows citations, and measures retrieval quality.
Governed Operations Agent
Build a governed AI agent with tools, explicit state, approvals, cost and time limits, an audit log, and a rollback path.
AI Quality Gate in CI
Build a regression gate for an LLM feature with deterministic checks, model graders, safety cases, and release thresholds.
Production Observability for an AI System
Build monitoring and an incident workflow for an AI workload with latency, cost, quality, fallback, and rollback evidence.
Verified AI Analytics Workflow
Build an analytics workflow for CSV and SQL with verified calculations, provenance, privacy controls, and a reproducible executive report.
Production AI Assistant Interface
Build a production AI assistant frontend with streaming, citations, approvals, cancellation, error states, and accessibility.
AI-assisted Requirements Audit
Audit requirements with traceability, ambiguity detection, gap and risk analysis, and verified acceptance criteria.
AI Feature Discovery Dossier
Prepare a decision-ready AI feature dossier covering the problem, capability fit, UX, metrics, risks, economics, and experiment plan.
AI Threat Model and Control Plan
Build an AI-system threat model covering abuse cases, controls, security tests, residual risk, and an incident playbook.
AI Process Automation Map
Turn an as-is process into an evidence-backed automation map covering bottlenecks, controls, AI candidates, deterministic alternatives, human checkpoints, and measurable acceptance criteria.
AI Use-Case Scoring Board
Build an AI use-case portfolio with evidence-based scoring across value, frequency, data readiness, capability fit, automation potential, failure impact, controls, and experimentability.
AI Business Case Evidence Pack
Build a decision-ready AI business case where ROI, risk, controls, and quality evidence remain separate instead of being collapsed into one attractive number.
Prompt Injection Source-Sink Lab
Build a red-team lab for direct and indirect prompt injection where risk is measured by the actual path from attacker-controlled sources to sensitive sinks and side effects, not only by instruction bypass.
Agent Capability Supply-Chain Audit
Audit Agent Skills, plugins, MCP servers, and tool catalogs as an executable capability supply chain covering provenance, install boundaries, schemas, authorization, caching, version drift, and revocation.
AI Security Incident Containment Drill
Exercise an AI-specific incident where prompt injection or a compromised tool has already affected a production workflow. Build evidence-preserving containment, reconciliation, scoped rollback, and regression closure.
AI Metric Reconciliation Lab
Validate AI-generated SQL and metrics with a semantic contract, deterministic controls, authoritative reconciliation, and regression cases before a number reaches a dashboard or decision.
Analytics Privacy & Lineage Gate
Build a privacy-aware AI analytics pipeline with data minimization, permission checks, lineage, egress controls, retention, and negative tests before sensitive context reaches a model.
Decision-Ready AI Analysis Dossier
Turn AI-assisted analysis into a decision artifact with verified metrics, an evidence ledger, uncertainty and sensitivity analysis, counter-analysis, reproducibility, and refresh/change controls.
AI Serving Release Envelope Lab
Build a governed release contract for an AI runtime: exact model/config fingerprint, readiness checks, bounded retries, canary, rollback, and runtime verification instead of assuming that green CI already means production truth.
AI Capacity, Cost & Chaos Lab
Stress-test an AI workload across concurrency, token/tool budgets, queues, backpressure, 429/5xx/timeouts, load shedding, degraded mode, and cost per successful verified task.
AI Incident Recovery & Reconciliation Drill
Run a production drill for provider outages, model regressions, and uncertain side effects: containment, evidence preservation, reconcile-first recovery, known-good rollback, failback, and incident-to-regression conversion.
AI Observability, SLO & Runtime Evidence Lab
Build an observability contract for an AI workload: end-to-end traces, risk-sliced SLI/SLOs, quality and cost signals, privacy-aware telemetry, authoritative postconditions, and runtime evidence that distinguishes real production state from a polished dashboard.
AI Grader Calibration & Reliability Lab
Build an evaluation workflow in which a model-based grader is calibrated against human-reviewed evidence, with a disagreement policy, risk slices, and a version-bound release gate.
Agent Side-Effect Test Oracle Lab
Test an agent workflow by its trajectory, permissions, tool calls, side effects, and authoritative system-of-record state—not merely by its final text.
AI Incident → Regression Forensics Lab
Turn a production incident into a minimized reproducible testcase, a root-cause slice, a permanent regression, and a verified release/rollback gate.