22 tasks, each one witnessed by the sources that watched the job — and behind every one, a prompt you can use tonight.
You usually start by opening JIRA or whatever ticket system your team uses to see assigned tasks: bug fixes, code reviews, or feature development. Mornings often have a stand-up meeting with managers and engineers to sync priorities and blockers.
Afternoons are for writing or running SAS code, debugging jobs on EC2 or AWS data stores like Amazon Redshift or Amazon DynamoDB, and reviewing pull requests. Time is also spent mentoring juniors and updating documentation or user manuals so analysts know how to run reports.
Yes, AI can speed routine tasks: suggest code snippets, find syntax errors, or draft documentation. But always validate outputs. Run the suggested SAS code on real test data, check logs on EC2 or Redshift jobs, and re-review results—AI can hallucinate or produce incorrect calculations.
Treat AI like a junior colleague: it helps produce drafts quickly, but you must debug, test, and document every change, and ensure compliance with industry or regulatory standards.