Architecture
Architecture
Notes and experiments on how systems fit together, mostly from my own hobby projects.
Do You Actually Need an Agent?
Same shop, same tools, four architectures, 4,480 runs. Simple and branching emails were handled at or near 100% without an agent. One model call coped with unexpected requests too. The agent won when something failed mid-way (74% against 42–50%), though two of those cases are simple fixes I left out of the fixed code. It cost about the same as the others, and with a cheap model it refunded a timed-out refund twice in 16 of 20 runs.
Closing the Gaps in My AI Agent's Identity Setup
A private key instead of a client secret closed the stolen-credential takeover; a confirmation the service insists on, given on the approver's phone, stopped the £4,800 invoice every time; agent capability checks, claimant details and a locked tool server closed three more gaps. A £900 claim with no receipt and a fake pre-approval was still approved in 4 of 5 runs.
Who Did That? Giving AI Agents a Proper Identity
Four common ways to give an AI agent access to company systems, tested with a local Keycloak and planted requests. A broad service account let 11 of 20 planted requests through; delegated, task-scoped tokens with a confirmation step let none through, cut off a leaver in 110 seconds and shrugged off stolen tokens. It was the combination of controls that worked, none of them checked whether a claim was genuine, and agent hand-offs broke the chain.
Agent Friction Loop: Getting Coding Agents to Tell Me What Slowed Them Down
Coding agents leave a one-line note when a repo slows them down, git hooks record it, and a weekly report shows the gaps worth fixing.
WebMCP: Why I'm Interested in Agents Sharing the Browser
Notes from building with WebMCP: humans and agents sharing the same browser state.