Blog

Prachit Parikh's blog

Long-form guides on requirements, SQL data checks, UAT and AI at work, by Prachit Parikh, business analyst. Every post comes with a template, a worked example or SQL you can copy.

Prebuilt AI agents are arriving by the thousand. Run a fit-gap before you adopt one

IBM and Microsoft now offer 6,000+ prebuilt AI agents and assets. A fit-gap method for BAs: six gates, five fit levels and a filled retail example.

Metric view relationships: the join your AI agent now trusts, and the three checks that make it safe

Databricks now lets teams declare joins between metric views for AI and BI tools, but nothing checks the data. Here's what BAs should test first.

Assumptions log: how to turn every assumption into a requirement, a test or a risk before sign-off

How to run an assumptions log: every assumption gets an owner and a date, then leaves as a requirement, a test or a named risk before sign-off.

More of my writing

I publish a different article on each of these every few weeks. The full list of every article, video and template is on everything by Prachit Parikh.