Authorization

Authentication & Authorization (OAuth2, JWT, RBAC)

Authentication answers 'who are you?'. Authorization answers 'what are you allowed to do?'. Most systems get both wrong in subtle ways: rolling their own crypto, treating JWTs as a session store, copying RBAC into every service, or never thinking about how to revoke a leaked credential. This lesson covers the standard building blocks: password storage with adaptive hashing, session vs token authentication, OAuth2 and OIDC flows, JWTs and their honest trade-offs, RBAC vs ABAC vs ReBAC, multi-tenant authorization at scale, machine-to-machine auth (API keys, mTLS, workload identity), and the operational concerns (key rotation, revocation, audit). The goal is to leave you able to design and defend the auth architecture for any system, from a single product to a federated multi-tenant platform.

Retrieve evidence for a follow-up question

Turn a follow-up message into a standalone retrieval query, keep access filters tied to the signed-in session on every turn, and decide which turns should not retrieve at all.

Diagnose a missing document

Trace a missing policy exception through ingestion, eligibility, and context packing without weakening access rules.

Trace a tool call from request to answer

Follow one ticket lookup from tool declaration to answer: what the model proposes, what the application validates and executes, and what the assistant says when the result is unavailable.

Implement a validated, tenant-scoped tool adapter

Implement a get_ticket adapter that validates model-proposed arguments, takes tenant scope from trusted context, and passes a fixture table, then explain how a bounded orchestrator handles timeouts, invalid calls, and parallel lookups.

Contain an indirect prompt injection

Explain why a retrieved document cannot grant itself authority, and name the controls in trusted code that still hold when the model follows an injected instruction.

Prove a context selector cannot leak data

Implement a context selector that enforces tenant, group, and deletion rules before ranking, then design tests proving that forbidden records and internal notes never reach the model-bound payload.

Specify a review and escalation workflow

Specify how disputed AI feedback is re-reviewed, corrected, and escalated, with server-side authorization, artifact-bound approval, deadlines, and concurrency rules, then prove the rules with acceptance fixtures.