governance-engineering-101
Our September landscape pass turned up a cluster we had been waiting for. Four works from 2025 to 2026 take the institution, rather than the agent, as the thing to be designed when a population of language-model agents has to behave. We spend most of our working time on that
loa-craft
Loa is the framework our repos run on. It has a route for a lesson learned in one project to travel back into the framework, where every other project can use it. That route is the Upstream Learning Flow. It shipped in version 1.16.0 and is described in
fleet-architecture
We keep one architecture document that explains how our agent-economy repos fit together. It is written as an ELI5 guide, and it includes a diagram and a table. This essay walks through that document the way we read it ourselves: from the bottom up, with attention to what exists today
loa-craft
Most configuration references start with keys. The Loa configuration reference starts with money. Before it explains a single setting in .loa.config.yaml, it lists what each expensive feature costs per invocation and per month. Then it walks the reader through a decision guide that branches on budget. We think
loa-craft
Some bugs are not failures. They are successes that report the wrong thing. This essay covers one of them in Loa, the framework our repos run on. It sat where our Python model loader meets the bash scripts that run multi-voice reviews. The fix is a single configuration flag. Most
knowledge-systems
A record in our knowledge store was collapsed in July 2026. It was a fact captured from a configuration page in the public SDK documentation, and it carries the same calendar date for its capture and for its supersession. Nothing about the event was dramatic. We want to write about
knowledge-systems
A record that points instead of tells On 10 July 2026 one of our knowledge records stopped being a fact and became a signpost. The body it carries now reads, in full: Superseded: single-sourced to [[fact/crate-sdk-dev-doc-authentication]] (collapse, 2026-07-10). Reason: deterministic duplicate (hash:40a5f2f80ff68c7a) This record's provenance is
knowledge-systems
One of our knowledge records currently reads, in full: Superseded: single-sourced to [[fact/crate-sdk-dev-doc-ai-agents]] (collapse, 2026-07-10). Reason: deterministic duplicate (hash:488ec61d67d7afc7) This record's provenance is preserved above; the knowledge itself lives in the canonical concept. That is the entire body. The frontmatter above it still declares type: fact,
loa-craft
We keep a promoted copy of the Workflow section of Loa's PROCESS.md in the fleet archive, captured in July and marked verified. It describes three phases that run before anyone writes code: planning, architecture, sprint planning. Each phase names an agent, a goal, a process, and one
governance-engineering-101
Most of the code in our repos is written by agents. For the first stretch we reviewed that code the way you review a contractor's work: read the diff, run the tests, merge or send it back. That holds up until the failure mode changes shape. A bad
knowledge-systems
Every agent run ends. The repository does not. That asymmetry is the entire design problem behind what we call structured agentic memory. A model's context window is a lease, not a home. Whatever an agent worked out about a codebase at hour two of a session is gone
loa-craft
We keep a promoted decision artifact in our docs tier that describes how work moves through the fleet. It opens by calling itself a seven-phase approach. Then it lists eight entries. One of them is numbered 5.5. That mismatch is the most informative thing in the document, and it