The CTO Playbook for Agentic Systems
A 71-page operating manual for engineering leaders whose software has started to reason, decide, and write the software that carries out those decisions. Written by our CTO, Andrew Stevens.
Tag
Architecture
A 150B MoE on a Developer Laptop: An Upper Bound on What Faster Storage Buys You
18 minutes
A 150-billion-parameter mixture-of-experts model streamed from NVMe on an ordinary developer laptop with no usable GPU. Across a 200-token …
Protecting the IP in a Generative World
10 minutes
A studio can find its back catalogue inside a public model's training data and discover it cannot prove, from its own systems, when the work …
Launch Day Is Every Day
9 minutes
Subscription and on-demand media platforms still spend their engineering effort preparing for the scheduled launch, while the traffic that …
Arkhe: An Ontology Language for AI Systems
7 minutes
Two weeks ago I argued that your ontology is the asset and you should own it in a neutral, versioned form. Arguing is cheap. Arkhe v0.2 is …
Regulatory Evidence at Machine Speed
9 minutes
Regulators have moved from asking banks for periodic reports to asking for specific evidence, on demand, about decisions made months ago. …
Trust Is an Engineering Output
9 minutes
Being correct is not the same as being able to prove it. This final post in The Engineering Underneath argues that trust is an engineering …
Your Ontology Is the Asset. Stop Renting It Back.
10 minutes
Agentic AI post-mortems keep naming the same trio: determinism failures, hallucinations, and compliance gaps. An ontology retires all three, …
Multi-Cloud Versus Consolidation
9 minutes
Most enterprises already run several clouds, whether they chose to or not, so the real question is not whether to consolidate but how to …
HTTP QUERY Finally Settles the Argument. Your Infrastructure Gets the Next One.
8 minutes
RFC 10008 gives HTTP a method that is safe, idempotent, and carries a request body. It ends a design argument I have been having in API …
Peak Load Is the Steady State
11 minutes
Peak load used to arrive with a date on the calendar. It arrives now without warning, and the architectures built to survive named events …
Sovereignty Versus Efficiency
11 minutes
Regulated enterprises want hyperscaler economics and sovereign-grade data residency from the same platform, and most end up paying for both …
Data Costs: Are You a Victim of Your Own Success?
11 minutes
A high-frequency analytical query running against raw object storage scans the entire historical dataset every cycle. The cost compounds …