Backlinks
Agentic Software — programmeWhen agents become the interface, who maintains the software underneath?Stratechery — Ben Thompson’s technology-strategy writingTeotti’s AI-first title-software team: evidence into a plan, and a review lesson that did not travelA living shared plan is not an acceptance recordTalwrn foundation: stable current decisions without treating status as acceptanceCodex wiring Datasette traces is not an agent supervision traceLinear’s workflow telemetry: more PRs and coordination, not measured requester valueVinod Kurien Alex: an agent-driven engineering layer and the missing active-hour ledgerStratechery on Meta enterprise: separate contexts or one work-and-life agent?Anghami Mikrowave: versioned decisions across agents, and bugs after reviewParallelPilot: faster ticket coordination did not establish better steeringWideSWE: a repository can pass while the feature still failsParallel coding agents: coordination, integration and human attentionSTALE: clean parallel merges can break a shared invariantRole shifts across the agentic software lifecycleWhen can an agent close an internal request without a manager?Do disposable interactive prototypes improve agent-built product decisions?Faire’s five-PR preview-build tool: planning beyond the ticket, outcome still unmeasuredlowtouch.ai’s founder-led rollout: shared deal context and human CRM approvalCursor Projects: persistent coordinator across feature, migration and gardeningOpenAI Symphony: ticket-level planning replaces session babysitting, not outcome checksLinear’s auto-fix boundary is task-shaped: dead flags versus failed background jobs