Sign InOpen Brain
AI EngineerVideoSource Linked

Building ambitious software — Jonathan Kelley, Dioxus Labs & Cognition

Dioxus found that generating more Rust was easy but merging it was not. Agents paid off on bounded research and maintenance work when architecture, real-device tests, and line-by-line review stayed human-owned.

AI Engineer · Sep 11, 2026
Open Source Open MarkdownOpen JSON
Source Summary

After generating **tens of thousands of lines of Rust**, the Dioxus team found that very little met its merge bar. A Kotlin and Swift plugin implementation arrived quickly, but the team spent **two to three weeks** building test cases and validating it on real devices.

Practical Implication

Use agents where patience and broad technical recall matter: documentation research, debugging specifications, release checklists, backports, and documentation consistency. Keep architecture explicit, communicate intent precisely, and review shipped code line by line.

Agent-Ready Context
After generating **tens of thousands of lines of Rust**, the Dioxus team found that very little met its merge bar. A Kotlin and Swift plugin implementation arrived quickly, but the team spent **two to three weeks** building test cases and validating it on real devices.

Use agents where patience and broad technical recall matter: documentation research, debugging specifications, release checklists, backports, and documentation consistency. Keep architecture explicit, communicate intent precisely, and review shipped code line by line.

Test generation remains a weak point: agents can cover an API while missing the behavior that matters. The experience is from one foundational open-source project, so its workflow may not transfer directly, but its core constraint is clear: **code is cheap; quality is not**.
Connected Context · Feed7 Judgment

This supplies project-level evidence that generation throughput does not remove the engineering bottleneck; it moves effort into architecture, behavioral tests, device validation, and meticulous review. It reinforces bounded, verification-heavy agent workflows while sharpening a specific weakness: API-shaped generated tests may miss product behavior. The result also conflicts with proposals to replace line-level review wholesale, at least for foundational code under a strict merge bar.

ExecCritic: Learn to Test, Test to Improve for Coding AgentsExecCritic provides a concrete control for the reported test weakness: qualify and freeze tests separately because weak generated tests can actively reduce repair success.How to Kill the Code Review — Ankit Jain, AviatorBoth move attention toward verification evidence, but they differ on review: Kelley retains line-by-line inspection, whereas Jain proposes reducing reliance on diff review as volume grows.How to Get Your Org to Adopt Coding Agents (Without Shipping Garbage) — Eyal Blum, FigmaThe costly validation experience reinforces Figma’s claim that cautious maintainers reveal missing safeguards and that adoption depends on reviewable plans, tests, and changes.Loop Engineering from First Principles — Kyle Mistele, HumanLayerThe low merge yield from large generated output supports incremental, reviewable agent loops over unbounded production, especially when validation is the scarce resource.
Context Map
agentcoding#coding-agents#harness-engineering#agent-reliability
Uncertainty
Test generation remains a weak point: agents can cover an API while missing the behavior that matters. The experience is from one foundational open-source project, so its workflow may not transfer directly, but its core constraint is clear: **code is cheap; quality is not**.