Only-Knowing-Code Developers at Risk as the Agentic Software Factory Reshapes Engineering
Pavan_Belagatti · x · 2026-11-23
Developer Pavan Belagatti argues that writing code itself has become cheap and AI assistants now often outperform humans, so companies want engineers who understand the full software lifecycle — build, test, deploy, monitor, maintain — plus AI agent workflows.
His accompanying diagram, "The Agentic Software Factory," lays out a six-stage workflow: Plan (ticket becomes a spec, human approves), Build (agent-only, isolated sandbox with no prod access), Test (CI, AI judges, security scans, agent-only), Review (AI review tiered by risk, low-risk changes auto-merge, owner sign-off), Deploy (PR → merge → canary → prod, human release approval), and Operate (agent-only monitoring of errors/alerts/usage, looping new issues back to planning). Shared catalog, ownership, standards and AGENTS.md serve as context throughout, with humans gating three checkpoints.
More from coding & agent
- MCP Tool Gateways Should Fail Loudly: A Plausible Answer From a Missing Dependency Is the Real Bug — Emergency-Tutor-7 · 2026-11-23
- Codex Can't Route PCB Traces: Devs Still Lack a Workable AI Tool for Hardware's Last Mile — goldvenetianmask · 2026-11-23
- Uncensored 26.4B model runs on a 12GB Mac at 85 tok/s with 8 parallel agents via Locals — SumitGup · 2026-11-23
- spaCy creator Honnibal shares a cheap-LLM ensemble recipe for building NER data with coding agents — honnibal · 2026-11-23
- 398M tokens, 98% cached: how one dev ran 12.5h of agent game dev on 3% of a $200 Claude plan — Yamapama · 2026-11-23
- Harvard paper: higher SWE-Bench scores didn't translate into more merged pull requests — rohanpaul_ai · 2026-11-23