Posts about agents
-
What We Know About Multi-Agent Orchestration (And Why It Might Not Matter)
The research on multi-agent AI systems was mostly done on cheap models. Now that frontier models are the ones people actually use, we might be optimising for the wrong game.
-
The Lethal Trifecta: What OpenClaw's Security Crisis Teaches About AI Agent Architecture
OpenClaw's 245 CVEs weren't caused by malice — they were caused by a missing circuit breaker. The pattern applies to every AI agent you'll ever evaluate.
-
Model Risk Management Was Not Built for This
SR 11-7 assumes models are tools that produce outputs for human review. AI agents are actors that take actions autonomously. Every assumption breaks.
-
Human Oversight Doesn't Scale
Every AI governance framework demands human-in-the-loop. Nobody does the maths on what that means at enterprise scale.
-
Progressive Disclosure for AI Agents
Search returns summaries. Get returns detail. The model decides what to expand. 75% context savings.
-
The Four Layers of Every AI Agent
Interaction, inference, orchestration, tooling. The boundaries between them must be enforcement points, not design principles.
-
Enterprise AI Agents: The Transformation Is Organisational, Not Technical
The companies that win with AI agents aren't deploying the most agents — they're redesigning their organisations to work with them.
-
What If Your Vault Had Residents?
Not tools that search your notes — personalities that live in them, form opinions, and disagree with each other.
-
When to Make Your Pipeline Agentic
Most LLM pipelines don't need agents. The ones that do share a specific pattern — the step needs to decide what to do next, not just process what it's given.
-
The CLI Boundary
Which parts of an AI dev workflow can be wrapped in a CLI, and which can't — learned the hard way by building the wrong thing and measuring it.
-
The Loop Is the Product
Karpathy's autoresearch and every useful AI tool share the same pattern: the code is trivial, the feedback loop is the product.
-
Why Nobody Builds Cross-Vendor AI Orchestration
Every AI lab builds single-vendor orchestration. The cross-vendor layer is a gap — and it's a gap for a reason.
-
The Orchestration Layer Is Knowledge, Not Code
Multi-agent AI orchestration frameworks are commodity. The competitive advantage is knowing which agent to use when, what breaks, and how to recover.
-
Guardrails Beat Guidance
Prompt instructions are suggestions. Hooks are constraints. One survives a model swap.
-
RAG Solved the Wrong Problem
The retrieval pipeline was built for systems that couldn't reason about their own information needs. Agents can.
-
The Personalised System Era
AI coding agents didn't just make developers faster. They changed who gets to have a bespoke system.
-
The Queue Should Live Where Your Thoughts Live
AI agent results should be push, not pull. The feedback loop should close on mobile. Most tools miss all three — not from ignorance, but because dashboards photograph better.
-
I Made the AI Remind Me of My Own Blind Spots
I kept missing things at the end of AI sessions. So I stopped relying on willpower and systematised the nudge instead.
-
The AGI Question Nobody Is Asking Correctly
Sequoia says AGI is here. Dan Shipper says we're not there yet. They're both right — they're measuring different things. The question that actually matters is Sholto Douglas's "nines of reliability."