Guardrails
Deterministic checks on input and output that fail closed.
4 to work through
-
intermediate
An AI feature needs guardrails on inputs and outputs. Where should they run, and what is the latency and reliability consequence?
2 min answer -
intermediate Multiple choice
Your output safety classifier blocks 0.3% of responses in English and 6% in Portuguese and Turkish. Complaints arrive only from those two markets. The vendor confirms the same model version serves every region and reports no incident. Where do you look first?
3 min answer -
advanced
A platform must prevent harmful outputs in a user-facing AI feature. Where should guardrails sit, and what does each layer catch?
2 min answer -
advanced
An insurance company wants an LLM to draft claim decision letters. What is your architecture?
2 min answer
3 terms in this topic
Guardrail Availability Policy
The decision, made in advance and per action class, about what the system does when a safety check cannot run - because the alternative is that a tim…
patternGuardrails
Deterministic checks applied to model inputs and outputs, enforcing constraints that the model itself cannot be relied upon to respect.
patternOutput Validation Layer
A deterministic check applied to model output before it is used, treating the model as an untrusted component.
Neighbouring topics
AI-Era Architecture
General material on architecting systems that include models.
LLM Application Architecture
The shape of a production system with a model in the request path.
RAG Architecture
Retrieval, grounding, citation and the permissions RAG can enforce.
Vector Databases
Approximate nearest-neighbour search, filtering and re-indexing.
Embeddings
Dense representations, model coupling and the migration they imply.
Chunking & Retrieval
Structure-aware splitting, hybrid search and why chunking dominates quality.
Reranking
Cross-encoders improving precision more than a bigger embedding model.
Model Selection
Capability, latency, cost and the evaluation that decides between them.
AI Gateways
Centralised routing, keys, quotas, caching, logging and safety policy.
Prompt & Version Management
Prompts as reviewed, versioned, evaluated production configuration.
Agent Architectures
Loops, planning, memory and the boundaries an agent must not cross.
Tool Calling
Typed tool interfaces, narrow parameters and per-tool authorisation.
Multi-Agent Systems
Coordination, hand-off and whether more agents actually help.
LLM Evaluation
Held-out sets, rubric judging, CI gates and production sampling.
AI Observability
Logging prompts, versions, retrieved context and cost per request.
Prompt Injection Defence
Breaking the private-data, untrusted-input, outbound-channel combination.
AI Cost Management
Token accounting, routing, caching and the context-window budget.
Human in the Loop
Gating by reversibility and blast radius, and avoiding approval fatigue.
ML Platform
Feature stores, training pipelines, registries and deployment.