Agentic Software

19 notes since September 2026
Agentic Software — programme#programme · updated todayFrom customer need to maintained feature: where does agentic software hand off?#topic · updated todayCursor Projects: persistent coordinator across feature, migration and gardeningupdated todayOpenAI Symphony: ticket-level planning replaces session babysitting, not outcome checksupdated todayLinear’s March 2026 permission regression: a review/test-coverage failure without AI authoringupdated todayGrab designers’ agent-assisted UI fixes: boundary moves, approval remainsupdated todayAmplitude via Cursor: risk-tiered agent review in a customer-feedback pipelineupdated todayLinear’s auto-fix boundary is task-shaped: dead flags versus failed background jobsupdated todayLinear’s cross-functional support-to-code path (April 2026)updated todayLinear’s review habit: recover the customer problem before reading agentic diffsupdated todayAfter merge: do agent PRs need more follow-up fixes?#topic · updated todayRole shifts across the agentic software lifecycle#topic · updated todayPlanning and tracking agent work beyond tickets#topic · updated todayAgentic code review: from human gate to evidence and bounded autonomy#topic · updated todayUnit economics of a maintained agentic change#topic · updated todayWhat do productivity studies of coding agents actually measure?#topic · updated todayThe 2026-published Copilot RCTs studied 2022–23 autocomplete#topic · updated todayMETR’s 2026 repeat: an apparent reversal with a missing denominator#topic · updated todayMicrosoft’s 2026 CLI-agent rollout: more merged PRs, not yet measured value#topic · updated today