Point and Call: Why Your AI Agent Forgets What You Told It Not To Do

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”

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”

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”

Trending Topic: Deepseek R1

The Rise of DeepSeek R1: A Game-Changer in AI Landscape The AI world is a buzz, and right at its center is DeepSeek R1. But that is where the frenzy lies, not just in the amazing things it can do but also in how it’s redefining the entire landscape of AI. Cut to the chase:Continue reading “Trending Topic: Deepseek R1”