LinkedIn·Tuesday, 11 August 2026·15d ago
An AI agent scored 37 out of 100 on questions about our own data. The same model later scored 100 out of 100. Ask an AI agent a question…
Dataminded
4,964 followers
An AI agent scored 37 out of 100 on questions about our own data.
The same model later scored 100 out of 100.
Ask an AI agent a question that spans multiple data products, and it quickly runs into limitations.
During our Innovation Days, Katarina Milosevic and her team explored what it takes to close that gap. A knowledge graph increased accuracy from 37% to 80% across four tiers of increasingly complex questions. Encoding human reasoning into the graph brought that to 100%.
The biggest improvement didn't come from using a larger model. It came from adding structure around the model.
Interested in learning how knowledge graphs can improve AI systems across your data landscape? We run free knowledge-sharing sessions for data teams, at your office, on the topic of your choice.
Book a session with Jonny Daenen: https://lnkd.in/ecEHzhxu
♥ 1
View on LinkedIn Cross-referenced
Related on the wire
Last week we hosted our Agentic AI Skills for Data Practitioners workshop at our Antwerp office, and what an evening it was! 🙌 We were…
Many organisations started a Data Mesh journey. Far fewer reached the outcomes they hoped for. Why? In the latest episode of The Data…
Most of what you ask AI to code isn't that hard. So why run it through your most expensive model? Teams often route routine work (Terraform…
Think your agent setup can hold up under real conditions? Prove it. Same model. Same tasks. Your harness, your context. Dataminded's data…
Time-series foundation models promise anomaly detection with no feature engineering. We tested the promise. The pitch is appealing: point a…
Most AI agent demos never touch a real pipeline. Ours does, and it gets scored on it. On 26 August in Antwerp, we're running a hackathon…