BEGIN:VCALENDAR
VERSION:2.0
PRODID:-//pretalx//pretalx.devconf.info//devconf-us-2026//talk//7TZHJF
BEGIN:VTIMEZONE
TZID:EST
BEGIN:STANDARD
DTSTART:20001029T030000
RRULE:FREQ=YEARLY;BYDAY=-1SU;BYMONTH=10;UNTIL=20061029T070000Z
TZNAME:EST
TZOFFSETFROM:-0400
TZOFFSETTO:-0500
END:STANDARD
BEGIN:STANDARD
DTSTART:20071104T030000
RRULE:FREQ=YEARLY;BYDAY=1SU;BYMONTH=11
TZNAME:EST
TZOFFSETFROM:-0400
TZOFFSETTO:-0500
END:STANDARD
BEGIN:DAYLIGHT
DTSTART:20000402T030000
RRULE:FREQ=YEARLY;BYDAY=1SU;BYMONTH=4;UNTIL=20060402T080000Z
TZNAME:EDT
TZOFFSETFROM:-0500
TZOFFSETTO:-0400
END:DAYLIGHT
BEGIN:DAYLIGHT
DTSTART:20070311T030000
RRULE:FREQ=YEARLY;BYDAY=2SU;BYMONTH=3
TZNAME:EDT
TZOFFSETFROM:-0500
TZOFFSETTO:-0400
END:DAYLIGHT
END:VTIMEZONE
BEGIN:VEVENT
UID:pretalx-devconf-us-2026-7TZHJF@pretalx.devconf.info
DTSTART;TZID=EST:20260924T112000
DTEND;TZID=EST:20260924T115500
DESCRIPTION:What if your backlog could shrink while your team focuses on hi
 gh-impact features? On the HyperShift team at Red Hat\, we built an AI-pow
 ered workflow using Claude Code that autonomously picks up Jira tickets\, 
 implements solutions\, opens PRs\, and even responds to peer review feedba
 ck — all without a developer lifting a finger.\n\nIn this talk\, we'll w
 alk through the key automations we built as Claude Code skills\, orchestra
 ted through OpenShift CI periodic jobs:\n\njira:solve — A four-phase pip
 eline triggered weekly by a periodic CI job. Given a Jira issue\, it fetch
 es the ticket details\, analyzes the codebase\, generates an implementatio
 n plan\, writes the code and tests\, and runs verification (linting\, buil
 ds\, unit tests). Then an AI peer review evaluates the changes for code qu
 ality issues. A third phase automatically addresses the review findings an
 d pushes fixes. Only after this internal review cycle completes does the f
 inal phase open a PR.\n\naddress-reviews — A separate periodic job that 
 runs every three hours. It queries GitHub for agent-created PRs with pendi
 ng review comments from humans or AI reviewers\, categorizes them by prior
 ity (blocking\, change requests\, questions\, suggestions)\, makes the req
 uested code changes\, amends the relevant commits\, and posts concise repl
 ies — closing the feedback loop without context-switching a developer. I
 t can also be triggered on-demand for any PR via a Prow comment.\nTogether
 \, these create a pipeline where low-priority backlog items flow from Jira
  to review-ready PRs with minimal human intervention. Developers review th
 e AI's work rather than doing it themselves\, acting as supervisors instea
 d of implementers for routine fixes.\n\nWe'll cover:\n\nArchitecture: How 
 we built a system of Claude Code skills that encode our team's standards 
 — code formatting conventions\, Gherkin-style test patterns\, effective 
 Go idioms\, conventional commit formatting\, PR templates\, and a project-
 specific AI review profile — so the AI produces output that meets the sa
 me bar as a human contributor.\n\nThe solve pipeline: Jira ticket parsing 
 → codebase analysis → plan generation → implementation → verificat
 ion → AI peer review → review fixes → PR creation\n\nThe review loop
 : How the address-reviews job triages human and AI feedback\, makes surgic
 al code changes\, amends commits\, and replies to reviewers\n\nGuardrails:
  Comment deduplication\, authorization checks\, token refresh across long-
 running phases\, and why human review remains essential\n\nResults and les
 sons learned: What works\, what doesn't\, and where human judgment is stil
 l irreplaceable\n\nWhether you're a platform engineer\, SRE\, or developer
  tired of your backlog growing faster than you can triage it\, this talk w
 ill give you a practical blueprint for putting AI to work on the tasks you
 r team doesn't want to do and the lower-priority ones it doesn't have time
  to do.
DTSTAMP:20260727T174809Z
LOCATION:Ladd Room (Capacity 170)
SUMMARY:AI-Powered Backlog Burndown: How We Taught Claude Code to Solve Jir
 a Tickets and Address Code Reviews - Bryan Cox\, Alberto Garcia Lamela
URL:https://pretalx.devconf.info/devconf-us-2026/talk/7TZHJF/
END:VEVENT
END:VCALENDAR