Tagged architect
14 pieces
- · 7 min read
Tracker or Model: The Wearable Fork
Two wearables can look identical and be different products. One computes a quantity the sensing can actually resolve; the other infers a quantity it cannot, and covers the gap with a model. The fork is decided when the sensing is chosen, months before there is data, and it determines what you are allowed to claim.
- · 7 min read
Build or Buy Your Agent Infrastructure
Almost every agent platform sells the part that is easy and leaves you the part that is hard. The loop, the tool dispatch, and the trace viewer are commodity. Whether your system knows it made progress, what it does when it gives up, and what stops a call tree are yours regardless of what you buy.
- · 6 min read
Edge or Cloud Inference: A Decision Table
This is usually argued on latency and cost, which are the two least decisive inputs. The questions that actually settle it are whether the system must work with no connectivity, whether the data can legally or contractually leave, and whether you can reach the device to fix what you got wrong.
- · 6 min read
Retrieval or Fine-Tuning: How to Actually Decide
The decision is not about quality and it is not close. Retrieval changes what the model knows; fine-tuning changes how it behaves. Almost every team asking this question has a knowledge problem and is being sold a behaviour solution, and the tell is whether the right answer changes when your documents change.
- · 7 min read
Multi-Tenant Retrieval: Leakage Is a Design Decision
Cross-tenant leakage in a retrieval system is not an accident that happens to careless teams. It is the default outcome of a design that treats tenancy as a filter applied at query time, because a filter is something that can be forgotten, bypassed, or applied one layer too late.
- · 7 min read
Perception to Control: The Handoff Nobody Owns
The perception team ships a detector that meets its accuracy target. The controls team builds a controller that is stable given its inputs. Both are right and the robot behaves badly, because what crosses between them is not a detection, it is a detection with a latency, a coordinate frame, a timestamp, and an uncertainty, and only one of those five is usually specified.
- · 7 min read
Idempotency for Money Movement
An idempotency key is not a header you add. It is a claim about what constitutes the same operation, and almost every double-charge traces to that claim being wrong: the key was generated per attempt instead of per intent, or the deduplication window closed before the retry arrived, or the key covered the request and not the effect.
- · 7 min read
Ship It Once, Reach It Never: Designing for Hardware You Cannot Touch
When a unit leaves the building, the set of decisions you can still change shrinks to almost nothing. The design question becomes which properties must be right at manufacture and which can be deferred, and getting that split wrong is the most expensive mistake in connected hardware because it is discovered across an entire production run at once.
- · 7 min read
Fleet Scale Changes the Failure Mode, Not Just the Number
A platform that works at a hundred nodes and fails at twenty-five thousand did not run out of capacity. It met failures that do not exist at small scale: monitoring that damages what it monitors, silence that no poller notices, and heterogeneity that only appears once the sample is large enough to contain it.
- · 7 min read
What a Minute of Line Downtime Buys You in Architecture
Downtime on an automated line runs from hundreds of thousands to millions of dollars an hour. Convert that to a per-minute figure and it becomes an engineering budget, which changes what is worth building. The interesting consequence is not that you should spend more. It is that the false-positive and false-negative costs are wildly asymmetric, and almost nobody sets the operating point from the plant's economics.
- · 7 min read
Change the Model, Restart the Submission
In most software, retraining is a Tuesday. In a regulated device it can be a regulatory event, and the cost is not the retraining but the clearance cycle it can trigger. That asymmetry should change your architecture, not just your paperwork, because the decisions that determine how often you must retrain are made long before the first submission.
- · 7 min read
Why Air-Gapped Changes Every Assumption in Your ML Pipeline
An air gap is usually treated as a deployment constraint, something to solve at the end with a USB drive and a procedure. It is not. It invalidates assumptions at every stage of the pipeline: how you get data, how you version artifacts, how you know what is running, how you evaluate, and how you find out anything went wrong.
- · 7 min read
AI at the Edge With No Network and No Retry
Every convenience in a cloud AI stack is a form of retry: call again, fall back to a bigger model, log it and fix it tomorrow. Remove the network and all of them go at once. What remains is a system that has to be right the first time, inside a power and latency envelope decided by hardware choices made months before anyone wrote inference code.
- · 7 min read
When Not to Ship an Autonomous Agent
There is a test that decides it, and it is not about model quality. If you cannot compute, in code, a number that tells you whether the task is closer to done, you cannot build a reliable agent for it yet. The honest move is a bounded assistant with a human terminal state, which is not a lesser product. It is the same capability with the failure mode removed.