/ ENGINEERING SYSTEMS
Back to Field Notes

FIELD NOTE / ARCHITECTURE NOTE

Everything Around the Model: The Real Engineering of Production AI Agents

·7 min read·Updated 2026-09-15
READERS

Six weeks after a logistics team shipped a freight-exception agent, it began rerouting shipments from stale memory, retrying carrier calls until bookings duplicated, and planning against warehouse state that no longer existed. Nothing crashed. The agent kept running and kept being wrong. This note follows that incident to the boundary where production agents are actually built: planning, reasoning, execution, tools, memory, state, and the controls around them.

Public-safe engineering note · no client or confidential implementation details
01

The LLM is infrastructure, not the agent

The freight agent looked excellent in a controlled test because the model was given clean state and forgiving tools. Production added delayed carrier responses, partial warehouse feeds, and concurrent operators. The model was a reasoning substrate, like a CPU: useful, fast, and indifferent to whether the software around it was reliable. Calling the LLM the agent hid ownership. The planner, state store, executor, tool registry, memory policies, and release controls made the decisions observable or opaque. In logistics, 6.2% of exception runs touched stale state during week six, while model quality on the original test set remained unchanged.

The full agent architecture
Reasoning EngineLLM = inference substratePlannerMemory systemTool registryExecution layerGuardrails · Observability · Retries · Timeouts · Idempotency · Security
02

Planning is a changing graph

A planner decomposes a goal into a directed acyclic graph with dependencies, preconditions, and expected outputs. One-shot planning generated all eight freight actions before the first carrier observation; step-one accuracy was 96%, step-five 78%, and step-eight 61% in a financial workflow automation deployment. Iterative replanning repaired some drift, but the trigger was the hard part: abandon a plan when a precondition changes, not merely when a tool throws. The freight agent needed a replan when a carrier reservation changed, even though every API returned 200.

Share a thought

Comments appear immediately. Email is optional and never shown.

Markdown & code fences supported
AUTH VIA: PUBLIC FORM

No comments yet. Be the first to share a thought.