AI Operations

Opening — Why this matters now AI agents are leaving the demo cage. They are no longer just politely completing prompts; they are planning workflows, calling tools, reading files, coordinating intermediate steps, and accumulating context like a bureaucrat hoarding PDFs. This is useful. It is also expensive. The paper “QuantClaw: Precision Where It Matters for OpenClaw” studies a problem that sounds technical but is really managerial: agent systems often run every task at a fixed numerical precision, even though not every task deserves the same computational budget.1 A safety-critical terminal command and a lightweight retrieval summary are not the same species of work. Treating them identically is the infrastructure equivalent of sending a limousine to deliver printer paper. ...

Routes look clean on a dashboard. A line leaves the depot, touches a sequence of customers, maybe bends toward a charging station, and returns home. The illusion is that route planning is still mostly about drawing the shortest useful line. Electric fleets ruin that illusion rather quickly. A diesel truck can treat refueling as an annoying but usually minor detail. An electric vehicle cannot. Battery capacity turns distance into feasibility. Charging stations turn geography into detours. A route that looks efficient before charging may become expensive after charging; a route that looks wasteful may avoid a much uglier charging pattern. This is why the Electric Capacitated Vehicle Routing Problem, or E-CVRP, is not merely the old vehicle-routing problem wearing a green jacket. It is a coupled routing-and-energy problem, and coupling is where algorithms go to lose their innocence. ...

The failure usually arrives after the demo A workflow agent looks excellent in a controlled demo. It reads the instruction, drafts the plan, calls the tool, produces a coherent result, and explains itself with the calm confidence of a consultant who has not yet met production data. Then the environment shifts. A document is stale. A permission boundary changes. A retrieved note is relevant but from the wrong project phase. A tool call succeeds technically while violating the user’s real constraint. A checker approves the output because the checker was never asked the right question. Nothing explodes. The system simply becomes expensive in the most boring way possible: it needs human rescue after looking competent. ...

Prompts are now office furniture. Everyone has them. Everyone complains about them. Nobody is quite sure who owns the standard version. One team keeps a Notion page of “best prompts.” Another hides theirs in a spreadsheet. A third tells new staff to “just ask clearly,” which is not a method, but it does have the administrative elegance of doing nothing. ...

A chatbot does not need a philosophy seminar to answer “Who directed Oppenheimer?” That sentence sounds obvious. Yet a large part of today’s AI infrastructure behaves as if every user query deserves a carefully staged internal drama: retrieve facts, reason through them, verify the logic, produce a chain of intermediate steps, and finally deliver the answer the system could have produced with a simple lookup. It is impressive in the same way using a crane to move a coffee cup is impressive. Technically capable. Operationally absurd. ...

Write-Back to the Future: When Your RAG Starts Learning A RAG system usually fails in a very ordinary way. The retriever finds something relevant, but not quite enough. The generator receives five passages, three of which are useful, one of which is decorative furniture, and one of which looks relevant only because it shares the right vocabulary. The answer is then expected to emerge from this little committee of half-helpful paragraphs. Sometimes it does. Sometimes it does what committees do. ...

Memory is supposed to be the practical part of an AI system. A model answers badly, the system records what happened, and next time the agent avoids the same trap. Neat. Sensible. Almost managerial. Then the organization does what organizations always do: it adds more people. In AI terms, that means more agents, more models, more task routes, more specialized components, and more silent assumptions about who should learn from whom. A small model handles routine work. A larger model handles hard reasoning. A coding model writes scripts. A tool-using agent interacts with apps. Suddenly, “memory” is no longer a notebook. It is institutional infrastructure. ...

A prompt fails. The optimizer reflects. The prompt changes. The score moves. This is the part where everyone is supposed to feel comforted. A self-improving system has looked at its mistake and revised itself. Very modern. Very agentic. Very convenient. The less comforting possibility is that the system has not understood the mistake at all. It has simply rewritten the prompt around the nearest explanation it can imagine. The score may improve, stagnate, or fall, but the optimizer still cannot answer the most basic operational question: what exactly did we just fix? ...

Routing is the unglamorous part of agentic AI. Which is exactly why it matters. A company can assemble a neat little digital workforce: one agent plans, one agent searches, one agent codes, one agent critiques, one agent writes the final answer. It looks sophisticated on a diagram. Then production traffic arrives, and the system discovers a more ancient truth: a committee is not useful if every request goes through the wrong people in the wrong order. ...

Updating a model sounds harmless until the old parts of the system start reading the new representations incorrectly. That is the less theatrical version of catastrophic forgetting. Not the dramatic story where a neural network “forgets everything” like a distracted intern. The more useful story is quieter: a deployed AI system adapts its backbone to new data, the feature space shifts, and classifiers trained for earlier tasks are left calibrated to yesterday’s geometry. ...