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.
Blog
Insights and opinion from the Sakura Sky team.
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 …
Tollgate v0.2.3: What Long-Context Pricing Does to a Spend Cap
11 minutes
Some models bill the whole request at a higher rate above a size threshold. What that does to a spend cap, and what changed in Tollgate …
Evidence That Looks Like Closure: Fuzzing, Fault Injection, and the GATE PARTIAL Checks
16 minutes
gate-fuzz v1.0.0 emits an artefact filed under Check15 that does not close Check15. Working out why is a useful way into which conformance …
GATE v1.5 Roadmap
10 minutes
A preview of the next GATE release: a per-control ISO/IEC 42001 mapping with the asymmetry written down, streaming-aware output validation, …
Tollgate: Open-Source Hard Limits for LLM Spend
7 minutes
Tollgate is an open-source AI gateway and spend-control proxy. It prices every LLM request by token, reserves budget before the call, and …
GATE v1.4: Output Validation, a Rust Companion, and the Conceptual Layer as OKF
10 minutes
GATE v1.4 adds C20 output validation at the delivery boundary, formalises break-glass as a signed contract, adds informative mappings to …
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 …
Your System Prompt Is Not a Trust Boundary
16 minutes
A text-to-SQL agent's system prompt cannot enforce a data rule. sql-guard v0.2.0 puts the rule in a parser instead, and closes eight …
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 …
Your Managed Providers Are About to Be Regulated. Here Is What to Ask Them.
11 minutes
The UK Cyber Security and Resilience Bill and NIS2 both regulate managed service providers directly, wherever they are established. Seven …
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 …
Identity Is the Bank Now
10 minutes
Fraud, financial crime, KYC, and customer experience have collapsed into a single engineering question about who the customer is. This final …