Five-day tracks
5 Days of Agent Infrastructure
The runtime underneath agents: autonomy, isolation, scaling and failure.
5 of 5 published
- 01
Part 1 · Explainer · 2 min read
Autonomy is a runtime decision, not a model decision
Agents get more capable by default. They only get bounded on purpose.
On the map: Agent - 02
Part 2 · Explainer · 2 min read
Your tool registry is an access control list wearing a different name
A list of tools is documentation. A registry decides who may act, as whom, and leaves proof behind.
On the map: Tools - 03
Part 3 · Explainer · 2 min read
Four kinds of agent state, and only one of them is memory
Conversation, task, artifacts and product data end up in one store. Then a deletion request arrives and applies to all of it.
On the map: Memory - 04
Part 4 · Explainer · 2 min read
A retried agent job is a second chance to send the same email
Retries are the first thing teams switch on and the last thing they design for.
On the map: Tools - 05
Part 5 · Explainer · 2 min read
The 3am agent run that nobody is watching
Scheduled agent work fails quietly by default. Traces, release gates and a runbook are what make it fail loudly.
On the map: Observability