Insights · Security and audit
AI is sometimes wrong. Can it handle work involving customer data?
AI evaluations for work usually end on the same question: the performance is clear, but can we really trust it with this? AI runs on probabilities.
✦ OwlAI BlogQuestions we met
Questions we met
building AI for work
How to talk with company data, hand off work, and make the results trustworthy.
Recommended
Insights · Asking your company database
The AI's SQL runs fine. Why is the revenue number wrong?
The demo is impressive.
Engineering Notes · Conversation engine
Shrink giant tool results before the provider cuts them, and say so
Sometimes a single tool result blows past the model's input limit in one go: a query that returns hundreds of…
Insights · Security and audit
Masked in chat, do national ID numbers still turn up in Excel?
You ask the AI to analyze customer inquiry data, and its answer prints customer phone numbers verbatim.
Engineering Notes · Security and audit
Answer-only checks leak via Excel: one check for every exit path
In a conversation that analyzes customer inquiries, someone without permission to view originals sees the phon…
Insights · Everyday conversations and meetings
Tens of thousands of orders: does AI really read them all?
You ask an AI to look through this year's orders and find anything unusual.
Engineering Notes · Design principles and architecture
Permissions are enforced in code, judgment is left to the model
OwlAI's agent reads internal databases and documents, and it also reads web pages and results from connectors…
Series
Insights · 41 postsShort reads for decision makers bringing AI into the business. Each starts from a question teams actually run into and shows, in three minutes, what gets solved and what is different.Engineering Notes · 76 postsDesign decisions and measurements from building an on-premises AI for work — how the principle of enforcing with code, guiding with instructions, and verifying with audits is implemented.