AI & GenAI.
LLM agents for data onboarding, checked by evaluation frameworks (golden sets, trajectory, prompt injection, drift), while production stays deterministic and auditable.
Three areas, one question: can we trust this data enough to decide?
Projects
Production work on this topic.
P—03
Active
Featured
Contract-Driven Data Platform with GenAI-Assisted Onboarding
New data sources join through validated YAML contracts; LLM agents work at design time only, so production runs stay deterministic.
Role
Architecture and hands-on development · Data Solution Architect
P—04
Completed
Fashion Retail Competitive Intelligence & GenAI Trend Platform
Competitor price, stock and colour data for 20+ brands in ~95 markets, normalized with LLMs: pricing and assortment decisions from 1 week to 1 day.
Role
Design and build · Data Solution Architect
Architecture katas
Design studies, not delivered systems. Their figures are design assumptions.
K—09
Featured
Governed GenAI Data Agents with LLM Evaluation
Three enterprise agents limited to certified metrics, contracted data and permitted documents, with traced answers and gated releases.
Sector
Enterprise analytics and AI governance
K—10
Claims Intake with Document Intelligence
Self-hosted models recommend, rules and adjusters decide, eight GPUs sit behind a queue, every decision is auditable for seven years.
Sector
Insurance
Publications
Articles and talks on this topic.
Blog
Wrong data costs more than missing data
ahmetkalafat.com
Blog
Twelve techniques, one scorecard
ahmetkalafat.com
Blog
Why I lowered my own maturity score
ahmetkalafat.com
Blog
Blog
Blog
Blog
Blog
Blog
Blog
Working on something like this?