AI agents remember what you told them to do. Over a long task, they forget what you told them not to do. In February, a director of AI alignment at a large technology company gave her agent a narrow job: look through her inbox and suggest emails to delete. She added a condition in plainContinue reading “Point and Call: Why Your AI Agent Forgets What You Told It Not To Do”
Tag Archives: technology
The Lot Number Pattern: Provenance for AI Output
Go look at the painkillers in your medicine cabinet. Somewhere on the box, in small print next to the expiry date, there is a lot number. Nobody reads it. It does not help you take the pill. It exists for one day — the day a manufacturer discovers a bad batch of an ingredient andContinue reading “The Lot Number Pattern: Provenance for AI Output”
The Margin Call Pattern: Budgeting Risk for Autonomous Agents
Your AI agent asks for approval forty times a day. The first few you read carefully. You check the recipient, you skim the draft, you think about it. Somewhere around the tenth you stop reading and start clicking, and by the afternoon the dialog has become a keystroke — a muscle movement between you andContinue reading “The Margin Call Pattern: Budgeting Risk for Autonomous Agents”
MCP Servers in the Enterprise: Identity, Policy and Blast Radius
A model summarising an incident for us once pulled the contents of a Kubernetes Secret into a transcript. Nothing was compromised. No attacker involved. The MCP server had been given a read-only role, somebody had written that role the way you write roles for humans — broad read across the API, because reading is harmlessContinue reading “MCP Servers in the Enterprise: Identity, Policy and Blast Radius”
Multi-Cluster Calico Enterprise on eBPF: Notes From the Deep End
Flipping the dataplane took about forty seconds. Dealing with what it broke took three weeks. That ratio is the honest summary of an eBPF migration, and almost nothing written about eBPF networking tells you about it. The posts are about throughput graphs and iptables rule counts. The work is about conntrack, kernel versions, asymmetric returnContinue reading “Multi-Cluster Calico Enterprise on eBPF: Notes From the Deep End”
A Software Supply Chain That Survives a Regulator: SLSA, Sigstore and SBOMs in Practice
The question that reorganised our entire supply chain programme took about eleven seconds to ask. Not “do you sign your images.” Not “do you scan for vulnerabilities.” It was: for the container that was running in production on that date, show me the commit it came from, show me the build that produced it, andContinue reading “A Software Supply Chain That Survives a Regulator: SLSA, Sigstore and SBOMs in Practice”
Policy as Governance: What OPA and Kyverno Actually Buy You at Audit Time
The question that matters is never “do you have policies.” It is closer to this: on 3 March, a workload ran in this cluster with a mutable image tag. Name the control that should have prevented it. Show me that the control was in effect on that date. Show me every exception that was openContinue reading “Policy as Governance: What OPA and Kyverno Actually Buy You at Audit Time”
The Confused Deputy Is Back, and This Time It Has an LLM
A junior analyst on a reporting team has access to her team’s shared drive. Not finance. Not HR. She opens the internal assistant and asks it to summarize the company payroll spreadsheet by department. The agent resolves the document. The retrieval service fetches it using the platform’s service credential, because that is the only credentialContinue reading “The Confused Deputy Is Back, and This Time It Has an LLM”
Beyond the API Key: Workload Identity Federation for AI Agents
We had migrated our agent workloads off static API keys. Federation configured, issuer registered, rules scoped, documentation updated, ticket closed. Then someone ran ant auth status inside a pod and found the static API key was still the credential winning every request. A leftover ANTHROPIC_API_KEY sat in the container environment, and it sits above federationContinue reading “Beyond the API Key: Workload Identity Federation for AI Agents”
Hosted Control Planes in Production: Rebuilding Ephemeral Kubernetes Environments with Kamaji
The ticket said the test platform was broken. It wasn’t. Every worker node across four environments had been reclaimed inside roughly ninety seconds, mid-test-run, because I had pinned one instance family in one availability zone and handed AWS exactly one capacity pool to take back. That is the kind of mistake you only make once,Continue reading “Hosted Control Planes in Production: Rebuilding Ephemeral Kubernetes Environments with Kamaji”
