Tags

Multi-Tenant

Multi-Tenant

0 lessons
3 problems
1 system design
6 AI Engineering questions

multi-tenant

Practice Problems

3 problems

Leakage-Safe Context Selection

Free
Not Started
Medium

Select the documents a user may see from trusted identity alone, rank them by query terms in the title and body, and return at most maxItems minimized context items without ever exposing an internal note.

AI Engineering
Data Privacy
Authorization
Multi-Tenant
Intermediate

6

RAG Chunk Eligibility

Free
Not Started
Medium

Return the first reason a retrieved chunk is excluded for a user (tenant, deletion, publication state, revision, or department), or null when the chunk is eligible.

AI Engineering
RAG (Retrieval-Augmented Generation)
Authorization
Multi-Tenant
Intermediate

10

Validated Tool Adapter

Free
Not Started
Medium

Validate a model-proposed get_ticket call (tool name, exact arguments, ID format), take the tenant and read permission from trusted context, and return a copy of only that tenant's ticket or a controlled error code.

AI Engineering
Tool Calling
Authorization
Multi-Tenant
Intermediate

6

System Design

1 article
System Design
Premium

Multi-Region, Multi-Tenant Architecture

Going from one region to many is one of the largest architectural commitments a company can make. The motivations are real (latency for global users, regulatory data residency, disaster recovery, regional uptime SLOs) and so are the costs (cross-region replication latency, conflict resolution, deployment complexity, blast-radius management, double or triple infrastructure spend). Multi-tenancy adds another orthogonal axis: how do you share the same infrastructure safely across hundreds or thousands of customers without one of them noisy-neighboring everyone else? This lesson covers active-active vs active-passive deployments, the data layer (replication, conflict handling, GDPR-style data residency), DNS and traffic routing, deployment topology, and the tenancy patterns (silo, pool, bridge) along with when each is the right answer.

multi-region
multi-tenant
system-design
advanced
premium
distributed-systems

1k

8

Hard

AI Engineering

6 questions
AI Engineering
Premium

Design hybrid retrieval within a latency budget

Design hybrid retrieval with reranking for a multi-tenant help center, choose a configuration from measured quality and latency gates, and keep access rules intact through timeouts and model migrations.

ai-engineering
hybrid-search
reranking
vector-search
latency
multi-tenant

0

Hard
AI Engineering
Premium

Design multi-tenant RAG with deletion

Design a private multi-tenant policy assistant whose answers and citations stay correct through asynchronous updates, retries, permission changes, and deletion.

ai-engineering
rag
multi-tenant
authorization
citations
consistency

0

Hard
AI Engineering

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.

ai-engineering
tool-calling
ai-agents
authorization
multi-tenant
error-handling

6

Medium
AI Engineering

Extend a tool adapter with a search tool

Extend the validated ticket adapter with a paginated search_tickets tool behind a tool registry under a 3-hour cap, hand in tests and a README, then review a sample submission as the interviewer would.

ai-engineering
tool-calling
pagination
multi-tenant
testing

4

Medium
AI Engineering

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.

ai-engineering
data-privacy
authorization
multi-tenant
security
testing

4

Medium
AI Engineering
Premium

Threat-model an agent with private data

Threat-model a multi-tenant assistant that reads private documents, keeps conversation summaries, and sends approved notifications, naming where each control is enforced and what risk remains.

ai-engineering
security
prompt-injection
ai-agents
data-privacy
multi-tenant

0

Hard