Atlassian workshop: building your own AI-driven SDLC with Jira coding agents and repo-level review rules
AI Engineer · youtube · 2026-10-11
Overview
AI Engineer published an Atlassian workshop (Andy Wong, Andrei Bocan, Shane Wolf) on building your own AI-driven SDLC, going beyond a coding assistant in an editor.
Key points
- Core idea: turn an engineering standard into a reusable code review rule applied across selected repositories, demonstrated live with a design token standard.
- End-to-end flow: work starts from a Jira item, draws on organizational knowledge (code, docs, past decisions—each with different authority and freshness), and produces a change for human review.
- Product chain: Jira coding agent, AI review, planning, autonomous development (AutoDev), and the AI context engine—code search, Jira/Confluence relationships, conflicting information, and favoring verified sources.
- Practical guidance: pick repositories for each rule, select suitable backlog work, cap cost and review volume, and have humans clarify underspecified tickets before an agent proceeds.
- Discussion (after network issues): sandbox verification, model selection and routing, deterministic checks, and breaking epics into smaller tasks.
Resource: Atlassian Rovo Dev. Full timestamps included.
More from coding & agent
- Claude Code Pushes Urgent Security Update Across All Installations — umeshonai · 2026-10-23
- Claude cut a 2.6-hour video export to 20 minutes — but only after being told to rebuild the server — byhewar · 2026-10-23
- 3 flight-booking rules my AI agent checks that I'd never do by hand — Efistoffeles · 2026-10-23
- OpenJet claims Qwen3.8-27B coding runs 1.9x faster than llama.cpp on one RTX 3090 — JeremyCMorgan · 2026-10-23
- Building an autonomous SEO agent in Hermes with three skills: programmatic pages, Keywords Everywhere, DataForSEO — EXM7777 · 2026-10-23
- Building a sports betting AI agent with onchain execution and human approval by default: architecture and lessons — Dry-Comfortable-2678 · 2026-10-23