Why a One-Line Change Can Break Your Whole Stack - Cole Gannaway, Qodo

Code generation is moving faster than ever, and the bottleneck has moved to review.

Cole Gannaway, a solutions engineer at Qodo, shows how a one-line data model change that passes every test can quietly break web, mobile, CLI and MCP clients, and how a software graph of your repos reveals that blast radius. He covers turning tribal knowledge and PR comments into custom rules, bringing review context in before code is written, why the agent that wrote the code shouldn't grade it, and checking PRs against the original ticket. Chapters: 0:00 Intro 0:59 Review is the new bottleneck 2:03 A one-line change that passes every check 3:35 The hidden blast radius 4:15 Building a software graph 4:56 Custom rules and tribal knowledge 5:47 Context before code is written 6:29 Don't let the writer grade its own code 8:20 Turning PR comments into rules 10:06 Q&A: catching the wrong intent 13:55 Wrap-up Cole Gannaway https://www.qodo.ai Join us in SF for the second annual AIE CODE summit: https://aie.codes our last flagship summit of 2026. Applications live now!

Mer att läsa

DeepSeek open sources Super-Agent as a research prototype, a proactive coding agent it says can monitor group chats for coding issues and suggest solutions

Techmeme · för 1 tim sedan

Insurance software maker Guidewire agrees to acquire Hyperexponential, which makes AI-powered insurance underwriting and pricing software, for $1.7B in cash

Techmeme · för 1 tim sedan

One word for AI agents in 2027

Nate Herk · för 5 tim sedan

Tests: chatbots rely on three obscure AI-built voter sites for US midterm answers; Copilot cited the error-prone Ballot Brief in 75% of tests and ChatGPT in 22%

Techmeme · för 6 tim sedan