Agent Architectures
Loops, planning, memory and the boundaries an agent must not cross.
4 to work through
-
advanced
A platform builds an agent that plans and executes multi-step tasks against business systems. Which architectural constraints are non-negotiable?
2 min answer -
advanced
A team is building an agent that plans and executes multi-step tasks. What architectural bounds must exist, and what usually goes wrong?
2 min answer -
advanced
An agent that researches and summarises occasionally runs for 40 minutes and costs £30 for one request. How do you contain it?
2 min answer -
advanced
Review this design. A finance team's invoice processor uses a planner agent that decomposes each invoice into subtasks, a critic agent that reviews the plan, a vector store of the last 50000 processed invoices as episodic memory, a 40-step tool loop, and a human queue for anything the critic flags. The task is to extract six fields and post them to the ledger. What would you remove and what would you keep?
3 min answer
2 terms in this topic
Agent Loop
The cycle in which a model observes state, selects an action, executes a tool and observes the result, repeating until a goal or a limit is reached.
patternAgent Transcript Compaction
Replacing the resolved middle of a long agent loop with a short summary while preserving the original goal and constraints verbatim, so token cost st…
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.
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.
Guardrails
Deterministic checks on input and output that fail closed.
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.