philliant
a place for all my philliant ideas
current writing
latest essay
reading the diff is the whole job
less than a year ago, ai assisted around the edges. today, I work almost exclusively by chatting with models and reviewing agent diffs. when generation costs drop to zero, reading the diff becomes the whole job, human review becomes the sole bottleneck, and domain mastery remains the only way to spot subtle errors in code you did not write.
read the essay →featured book
AI-Assisted Data Engineering
A senior engineer's playbook for building real dbt and Snowflake data products with AI agents, released one chapter at a time.
explore by topic
all series →ai
practical notes on ai workflows, decision quality, and sustainable usage
explore →data vault 2.0
hands-on patterns for hubs, links, satellites, and evolvable warehouse design
explore →dbt
modeling, testing, and maintainable transformation workflows with dbt
explore →sql
query patterns, debugging habits, and practical sql work across projects
explore →recent writing
archive →
