Home › How-to guides › Automate IT and DevOps chores

How to automate IT and DevOps chores with an AI agent

I looked through 51 real cases about IT and DevOps chores and pulled out what people actually did, the prompts they used and the places it went sideways. No theory, no invented success stories.

What people actually do

• Agents cut each service migration from 3 months to 2 weeks · Multi-agent migration (Google Cloud) · DevOps & Infra
  Sportswear brand On says it used a multi-agent approach to migrate 24 core services to Google Cloud, cutting each from three months to two weeks.…
• Sort nightly test failures into bugs, flakes and infra problems · Strands Agents on Amazon Bedrock · DevOps & Infra
  Rescale added an agent to its CI pipeline that classifies each failed end-to-end test as infrastructure, code bug, flaky test or environment…
• An agent answers 'where is my drive data?' tickets at Mobileye · AI Support Agent (Amazon Bedrock AgentCore) · DevOps & Infra
  Mobileye engineers kept asking about the status of drive-recording sessions in its data pipeline, and each answer meant checking several systems. An…
• A hospital's IT help agent cuts handle time from 25 minutes to 9 · Wali (Moveworks) and Now Assist · DevOps & Infra
  ServiceNow says Wellstar Health System's assistant Wali answers clinicians' IT questions inside Teams and the EMR support environment, while Now…
• A backup firm's agent resolves up to 63% of issues on its own · DruAI (Druva) · DevOps & Infra
  AWS says Druva's DruAI agent, in use for 3,000+ customers, solves up to 63% of issues without human intervention and speeds up resolution by up to…
• Control a fan from sleep position · Custom agent · DevOps & Infra
  According to the write-up, the setup runs a MediaPipe pose vision model on a Raspberry Pi home server that watches the sleeping person via camera.…
• Claude Code as a general computer operator · Claude Code · DevOps & Infra
  A writer argues a terminal coding agent can handle many everyday computing jobs and shows examples beyond writing code.
• Let terminal agents make phone calls · Make · DevOps & Infra
  Documented elsewhere: the builder assembled a CLI tool powered by Twilio and GPT-live that gives terminal agents a voice for outbound calls. The…

Browse all 1081 cases to see the rest.

Prompts to start from

These are the reusable prompts from real cases. Swap in your own details, run it once on something low-stakes, and read what the agent did before you trust it.

Help me migrate this service to a new cloud. Map how it is deployed across our repositories, write the configuration scripts, replicate the data, and validate the new environment before we cut over.

Our nightly browser tests failed. For each failure, look at the logs and past failures and label it as infrastructure, code bug, flaky test or environment. Give the evidence and the file or function to check. Do not change anything, just report.

Tools that show up most

Claude Code (14), Custom agent (6), Claude (6), Cursor (4), Grok Bot (2), Hermes Agent (2).

Guardrails

Try it first on a staging system or with read-only credentials, and require approval for anything that changes production.

Where it went wrong, or nearly did

• Validation agent that stops after three tries: A guardrail by design: it patches failures up to three times, then leaves a blocker note for a human.

More mess: the AI agent fails page. Related: the prompt library.