I built an AI software factory that turns GitHub issues into PRs on autopilot
Pavan_Belagatti · x · 2026-10-22
Pavan Belagatti shares how he built an "AI software factory" where coding agents pick up GitHub issues in isolated environments and return pull requests without babysitting.
His insight: the agent is rarely the bottleneck — the surrounding workflow is (copying issues into prompts, routing, waiting, opening PRs, judging quality). His goal: fully automated flow with human review only at the end.
The article lays out an Agentic SDLC platform architecture: Plan (Jira/Linear/GitHub Issues), Build (GitHub/GitLab/VS Code), Review (PRs, SonarQube/Snyk), Deploy (Docker/Kubernetes/Argo CD), Operate (Datadog/Grafana), with the platform orchestrating agents, workflows, and context. Screenshots show codex-02 auto-generating tests and opening a PR for issue #5.
More from coding & agent
- One-shot RL repro: training Qwen3.5-4B to paint watercolour flowers with a judge model — charles_irl · 2026-10-22
- Open-source Claude Duet alternative Open-Duet hits 5.9k stars on launch day — matchaman11 · 2026-10-22
- LGWM: A World Model That Verifies GUI Agent Transitions and Detects Hijacked Screens — Jiaming Zhang · 2026-10-22
- Tracing AI agents with OpenTelemetry: costs, P95 latency, and gaps in one pipeline — silksong_when · 2026-10-22
- New pattern: sync X bookmark folders to agents for intent-driven auto-pilot jobs — vincent_koc · 2026-10-22
- Towards AI builds writing benchmark: 4 LLM judges, 1000 human A/B tests on AI slop — AI Engineer · 2026-10-22