Platform and reliability engineering for AI workloads.
Platform & SRE engineer. Nine years running production platforms across banking, defense, healthcare and blockchain. I write about the infrastructure AI agents need.
More about me →Writing
All Writing →- Read
Review Is the Capacity Plan for Coding Agents
Spotify's coding agent went from 1,000 merged PRs in three months to the same number in ten days, and the team's own talk names what happened next: a pile of PRs nobody had time to review. Once agents write the changes, the capacity worth planning is CI and human review, and the first fix is moving verification out of the agent's sandbox.
- Read
The Validator Is the Platform
An InfoQ playbook cut an LLM system's hallucination rate from 15% to 1.5% without touching the model, and the article credits most of that to plain code that checks the output before anything uses it. That code is the part a platform team should own, and what it's worth depends on whether it checks the model's word or checks the world.
- Read
Proxy Variables Are Not an Egress Policy
Injecting HTTPS_PROXY into every pod at admission works fine for apps that cooperate, and an agent is a workload you can't count on to cooperate. Two recent OpenAI incident reports show an agent getting told no and going looking for another way out, so the egress decision has to be enforced below the workload by something it can't read or route around.
- Read
Forking a Sandbox Clones Its Secrets
Snapshot and restore gets sold as a cold start fix, and Firecracker's own docs call the same operation insecure if you do it more than once. VMGenID reseeds the kernel's random pool and that is where the mitigation ends. Machine IDs, cached tokens and anything userspace seeded before the snapshot ride into every copy, and the layers above Firecracker do not mention it at all.
- Read
Scale to Zero Is a Queue Feature
Kubernetes v1.37 shipped scale-to-zero autoscaling as a default-on beta, and the release post names its own precondition in one sentence: this works when the work can wait in a durable queue. An agent parked on a human approval has no queue holding it, so the saving has to be bought somewhere else. Three teams have shipped three different answers, and only one of them has a number attached.
- Read
Per-Call Authorization Cannot Bound an Agent Run
An allowlist answers one question: is this single call permitted. The risk of an unattended agent accrues across the sequence, in spend, in repetition, in the fourth write to the same file. AWS shipping temporal conditions in a policy language is the first mainstream admission that a bound has to be stateful over a run, and the example they ship with it already has a concurrency bug in it.
No writing matches this filter.
Selected projects
All projects →2022
-
Polyglot Microservices Webshop
A cloud-native webshop on Kubernetes — independent services in Swift, TypeScript, Java, Go and Python behind a single API gateway, fronted by an iOS storefront.
2021
2019
-
Kubernetes CI/CD Webhook
A Kubernetes webhook consumer for CI/CD — a Helm chart that fires pipeline jobs to build images with Uber's Makisu and continuously deploy GitHub/GitLab projects via Helm.
2018