The ontology as the agent's context
Agents do not fail for lack of model, they fail for lack of context. What an ontology adds over a table schema, and how to build one from a concrete use case.
Contact: bgaldos@galde.app
I specialise in data governance and in building data products that actually get used to make decisions. I work at the intersection of business and technology: I design governed platforms, turn critical processes into data products, and make sure everything runs in production and is adopted by the teams that need it.
I have led end-to-end projects in complex environments (energy, reinsurance, fintech and marketplaces), working with data leadership, business areas and engineering teams to launch scalable, secure platforms. I also have hands-on experience deploying solutions on Palantir Foundry, from ontology modelling to governance by design and access control.
What I bring:
- Standing up data governance: rules, lineage and quality built into the platform.
- Building data products oriented around domains and business cases.
- Translating business processes into operational applications and reproducible pipelines.
- Aligning with compliance, security and adoption teams so the investment pays off.
Articles (34)
Page 1 of 12
AgentOps: observing the reasoning, not just the result
Storing an agent's answer will not help you debug it. What to instrument at every reasoning step and tool call, and which signals warn you before something breaks.
An agent is an identity: permissions, scope and owner
Once an agent stops answering and starts acting, the question is no longer what it knows but what permissions it holds.