fighting slop with slop — Vaibhav Gupta, Boundary
Boundary replaces blanket code review with stable architecture rules, agent-generated tests, transcript inspection, execution traces, and human triage—a concrete harness pattern, not a license to skip verification.
Boundary says its team uses **no code reviews**, lets engineers choose their AI tools, and anchors agents with a small **architecture.md** containing durable compiler-layer rules. Agents generate BAML programs, inspect transcripts, surface issues, propose fixes, and compare variants by tool calls, errors, and outcomes.
The reusable idea is to move assurance into executable invariants and observable agent behavior. Keep architecture context stable, record traces, generate adversarial usage, and let humans triage findings rather than manually reading every generated line.
Boundary says its team uses **no code reviews**, lets engineers choose their AI tools, and anchors agents with a small **architecture.md** containing durable compiler-layer rules. Agents generate BAML programs, inspect transcripts, surface issues, propose fixes, and compare variants by tool calls, errors, and outcomes. The reusable idea is to move assurance into executable invariants and observable agent behavior. Keep architecture context stable, record traces, generate adversarial usage, and let humans triage findings rather than manually reading every generated line. This is one team’s process for a programming language, not evidence that review is broadly obsolete. Agent findings can hallucinate or lack judgment, while claims such as effectively free tracing and deterministic A/B comparisons depend on Boundary’s underlying system.
This offers a strong version of assurance-through-invariants: stable architecture rules, executable validators, traces, and adversarial runs replace line-by-line review for one language team. It reinforces observability-driven agent improvement and model-independent comparison, but directly conflicts with candidates that retain human review for maintainability and larger changes. The evidence supports a bounded workflow, not the general removal of review.