Blog
Research, product updates,
and case studies
Notes from the team on building AI that runs on real business data — what works, what we learned, and how customers put it to use.
Product update
Ask your company data in plain language
Dashboards and SQL keep answers locked away from the people who need them. Here is how Codelabs AI turns a plain question into a real number with its source.
Jul 14, 20265 min read
Research
Why every AI answer should cite its source
A confident answer with no citation is a liability. Retrieval-grounded AI — RAG done properly — is what makes an assistant safe to put in front of a business.
Jul 7, 20266 min read
Case study
How a Thai retailer cut stockouts with demand forecasting
A multi-branch retailer was losing sales to empty shelves and cash to overstock. SKU-level forecasting rebalanced both — without adding headcount.
Jun 24, 20264 min read
Research
Claude, OpenAI, or on-prem: choosing the right model
There is no single best model — only the best fit for a given task, budget, and data-privacy constraint. Model freedom is the point, not a feature.
Jun 10, 20265 min read