Backlinks
Park et al.: the work behind delegating to coding agentsSTALE: clean parallel merges can break a shared invariantDoes instruction make AI-assisted coding more effective, and what must humans know unaided?Role shifts across the agentic software lifecycleWhen can an agent close an internal request without a manager?GitHub gh-aw: an agent’s failure-investigation ticket is not resolved by closing itTrio study: code finished, understanding deferredPlanning and tracking agent work beyond ticketsFaire’s five-PR preview-build tool: planning beyond the ticket, outcome still unmeasuredAgentic coding adoption is social: testing a manager-and-team-artifacts hypothesisAnthropic’s Claude Code team: manager practice, pod autonomy, and review gatesSQLFluff Redshift GRANT: Copilot’s “safe to merge” fix underwent human rewriteSQLFluff’s DuckDB MAP literal: agent PR, recognized review gap, next-day human fixOpenAI Symphony: ticket-level planning replaces session babysitting, not outcome checksLinear’s March 2026 permission regression: a review/test-coverage failure without AI authoringAmplitude via Cursor: risk-tiered agent review in a customer-feedback pipelineLinear’s review habit: recover the customer problem before reading agentic diffsAfter merge: do agent PRs need more follow-up fixes?