This Week in AI & Systems #4: Memory, Intent, and the Infrastructure Around Agents
Agent memory, behavioral security, Git at agent scale, and the evaluation and runtime controls that make autonomy useful.
Agent memory, behavioral security, Git at agent scale, and the evaluation and runtime controls that make autonomy useful.
Four themes from Oct 23–29, 2026: agent platform design, enforced agent permissions, trusting evals before models, and systems at scale.
Three themes from Oct 17–23, 2026: a dense security week, agent runtimes and control planes becoming products, and the cost of each agent step.
Four themes from Oct 1–17, 2026: source control and review at agent scale, the agent control plane, agent verification and measuring AI-assisted work.
The skill surface of platform engineering is too wide for any team to cover well by treating everyone as a generalist. The teams that deliver build deliberate specialisation with overlapping breadth.
Team Topologies is not an org chart pattern — it is a cognitive load management strategy with architecture as a side effect. Design teams to produce the architecture you want, not the other way around.
An industry primer on platform engineering, covering organisational vocabulary (Team Topologies, Platform-as-a-Product, paved roads, SRE) and the technical building blocks of a modern Internal Developer Platform.
Delivery teams are your customers. The moment you stop treating them as a captive audience and start competing for their adoption, your platform becomes something engineers choose rather than endure.
An IDP is an opinionated, product-managed abstraction layer that converts developer intent into provisioned, policy-compliant cloud infrastructure — without the developer needing to understand Kubernetes, Terraform, or security policy.
A golden path is not a mandate — it is the best available answer to a question most teams will eventually ask, shipped before they get lost. The difference between a paved road and a mandate is who bears the cost.