1. Agent Architectures 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 agentsboundsauthorisationidempotency
  2. Agent Architectures 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 modalagentsboundstools
  3. Agent Architectures 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 agentscostcontrol
  4. Agent Architectures 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 agentsover-engineeringstructured-outputdeterminism
  5. AI Cost Management advanced

    A travel platform's AI feature costs vary enormously between interactions and the total is growing faster than usage. Which levers apply, in what order?

    2 min answer ai-costcachingroutingcontext
  6. AI Cost Management advanced

    An AI feature launched two months ago now costs more per month than the rest of the platform. What do you investigate?

    2 min answer aicostfinopsarchitecture
  7. AI Cost Management advanced

    An AI feature was modelled at £0.02 per interaction. Production shows £0.11. Where did the difference come from?

    2 min answer finopsllmunit-economics
  8. AI Cost Management advanced

    An inference platform receives a burst of expensive long-context requests that would starve short interactive ones. Design admission control, priority classes, token-based limits and batching so interactive latency SLOs hold.

    3 min answer inferenceadmission-controlprioritybatching
  9. AI-Era Architecture advanced

    An AI platform serves computationally expensive requests with unpredictable bursts, where one request can occupy an accelerator for seconds. What is the architectural shape, and which control is most often misplaced?

    2 min answer inferenceadmission-controlbatchingcapacity
  10. AI-Era Architecture advanced

    An LLM feature that worked last week now gives worse answers. Nothing was deployed. How do you find out what changed, and what should have been in place?

    2 min answer prompt-managementevaluationversioningllm
  11. AI-Era Architecture advanced

    An enterprise AI platform serves many customers on shared inference infrastructure. What isolation is required, and where is the hardest boundary?

    2 min answer coheremulti-tenancyisolationdata
  12. AI-Era Architecture advanced

    An inference platform receives computationally expensive requests in unpredictable bursts. Should it use admission control, request queues, dynamic batching, autoscaling, priority classes or pre-provisioned capacity?

    2 min answer together-aiinferencebatchingadmission-control