BEGIN:VCALENDAR
VERSION:2.0
PRODID:-//pretalx//pretalx.com//txlf2026//talk//SYKJDG
BEGIN:VTIMEZONE
TZID:US/Central
BEGIN:STANDARD
DTSTART:20251107T000000
TZNAME:CST
TZOFFSETFROM:-0600
TZOFFSETTO:-0600
END:STANDARD
BEGIN:DAYLIGHT
DTSTART:20260308T030000
RDATE:20270314T030000
TZNAME:CDT
TZOFFSETFROM:-0600
TZOFFSETTO:-0500
END:DAYLIGHT
BEGIN:STANDARD
DTSTART:20261101T020000
TZNAME:CST
TZOFFSETFROM:-0500
TZOFFSETTO:-0600
END:STANDARD
END:VTIMEZONE
BEGIN:VEVENT
SUMMARY:Agentic Infrastructure Lifecycle Management - Cody Lee Cochran
DTSTART;TZID=US/Central:20261107T140000
DTEND;TZID=US/Central:20261107T145000
DTSTAMP:20260930T133618Z
UID:pretalx-txlf2026-SYKJDG@pretalx.com
DESCRIPTION:AI assistants can generate infrastructure code quickly\, but s
 peed alone does not make infrastructure safe\, repeatable\, or maintainabl
 e. The interesting problem is not how to get an AI agent to write Terrafor
 m\, Compose\, Ansible\, or Kubernetes manifests. It is how to design infra
 structure projects where an agent can make useful changes without bypassin
 g the engineering practices that make infrastructure-as-code reliable.\n\n
 This talk presents a practical framework for using agentic tools across th
 e infrastructure lifecycle: build\, update\, test\, deploy\, and destroy. 
 Using Docker Compose-based applications as an approachable example\, we'll
  examine how familiar IaC practices such as pinned dependencies\, modular 
 and DRY configuration\, environment separation\, secrets management\, idem
 potency\, automated testing\, and reviewable changes become even more impo
 rtant when an AI agent is modifying the repository.\n\nWe'll also look at 
 the agent-facing side of the problem: repository instructions\, scoped con
 text\, validation commands\, tests\, and explicit guardrails that give an 
 agent enough information to work effectively without giving it unrestricte
 d authority over production-impacting decisions.\n\nAlthough the examples 
 use Docker Compose\, the patterns apply broadly to Terraform/OpenTofu\, An
 sible\, Kubernetes\, Helm\, Pulumi\, CI/CD systems\, and other infrastruct
 ure-as-code environments.\n\nThe goal is not better prompt engineering. It
  is better infrastructure engineering: building repositories where humans
 \, automation\, and AI agents can all make changes through the same predic
 table\, testable\, and reviewable lifecycle.
LOCATION:Lil Tex
URL:https://pretalx.com/txlf2026/talk/SYKJDG/
END:VEVENT
END:VCALENDAR