← back
Thinner Agents on a Smarter Substrate: The Ontology-based Semantic Layer — Emil Eifrem, Neo4j
Takeaway
Move shared business-to-data mappings and execution knowledge into a governed semantic layer so agents can remain simpler.
Summary
- Hard-wiring data sources into each enterprise agent duplicates discovery, trust checks, and maintenance while preventing shared learning.
- Neo4j proposes an ontology-based semantic layer with business concepts, technical metadata, and mappings between them.
- Runtime traces record attempted actions and outcomes, helping agents choose data sources based on prior successes in relevant contexts.
- A bank-account-opening example maps identity verification to DMV or passport services through a shared graph rather than repeated per-agent wiring.
ontologiessemantic-layerknowledge-graphs
Original description
To automate opening a bank account, your agent needs to verify identity, so a team wires it to the DMV and a passport service and ships it. Then the next team builds the next agent and rediscovers, from scratch, where its data lives, across a hundred databases plus Snowflake, Databricks, and S3, whether it can trust the version, and whether it is even allowed to touch it. Every agent repeats that wiring, nothing updates when a source moves without a manual rewire, and no agent is smarter tomorrow than today. Emil Eifrem's fix is to make the agents thin and put the intelligence in a shared substrate underneath. That substrate is an ontology based semantic layer with three parts. A business ontology names the real concepts, customers, accounts, checks, in the words people actually use, not f_name. A technical ontology catalogs every data source and its schema, with a mapping between the two. And execution traces record what each agent tried and whether it worked, so the layer learns bottom up: an agent that succeeded with the DMV lookup last time is more likely to reach for it next time. Discovery, trust, deduplication, and learning stop being every team's problem and become the substrate's. Speaker info: https://x.com/emileifrem / emileifrem Timestamps: 0:00 - The account opening agent and its data sources 1:53 - The problem: every team rewires data from scratch 4:00 - Thin agents on a smarter shared substrate 4:37 - Pillar 1: a business facing ontology 5:26 - Pillar 2: a technical ontology and the mapping 6:19 - Pillar 3: execution traces that make it learn 8:01 - Solving discovery, trust, DRY, and learning