Blog //

Notes from the overlay.

Writing on code-level context, effect propagation, and keeping agent-authored code accountable. A new post lands each week.

September 4, 2026 · The ASD team

Policy gates: who's allowed to change what

File-backed rules that allow, deny, or require approval per action and actor — evaluated on every ledger mutation and emitted to the audit stream.

Read more →
August 28, 2026 · The ASD team

Hash-chained audit for agent-authored code

Every ledger mutation and policy decision, appended to a tamper-evident log where each entry references the prior one's hash — replayable and independently verifiable.

Read more →
August 21, 2026 · The ASD team

A decision ledger that outlives the author

Append-only decisions, hazards, and rationale attached to a symbol — surviving renames, file moves, and the person who wrote them leaving.

Read more →
August 14, 2026 · The ASD team

Effects, propagated: the blast radius before you edit

Seventeen effect categories, declared per symbol and pushed transitively through the call graph, so an agent knows what a change reaches before it makes it.

Read more →
August 7, 2026 · The ASD team

The diff isn't enough for agents

A diff tells you what changed. It never tells you why the code exists, what it touches, or who approved it — and that's exactly the context an agent needs.

Read more →