Semantic Layers Were Built for Dashboards. AI Agents Need More.
What a semantic layer for AI agents still does well, and the structure and trust it never had to provide for a person with a dropdown.
A semantic layer answers one question very well: how is this metric calculated? That was the right question for dashboards. An AI agent asks it too, but it also needs to know what data exists, which values are valid, which answers are trusted and what this user is allowed to see. Most semantic layers were never designed to answer those.
My view: for AI agents, a semantic layer is necessary for the metrics that must be exact, and nowhere near sufficient for everything else an agent does. It’s worth being precise about which parts carry over and which don’t, because a lot of teams are budgeting for this right now. A Futurum survey of 818 enterprises found 44.5% plan to increase semantic layer spending over the next 24 months.
The problem the semantic layer solved
Ask finance, sales and product for last quarter’s revenue and you can get three defensible numbers: recognized net revenue by fiscal quarter, signed bookings by calendar quarter, ARR without usage overages. The semantic layer’s job was to write one of those down, with the SQL, the source table and an owner, so every dashboard computes it the same way.
It does that with a familiar set of parts: entities mapped to tables, dimensions to slice by, metrics, approved join paths and access rules, all compiled into SQL at query time. The consumer never writes the join or the formula, which is why two dashboards on the same layer can’t disagree. (I’ve written up how a semantic layer is put together in more detail elsewhere.)
But look at who sat at the other end. A human analyst opened the dashboard, picked a region from a dropdown and noticed when a number looked off. The BI semantic layer could leave a lot unsaid, because a person filled in the gaps.
What carries over to agents intact
Three parts of the semantic layer transfer to agents without loss, and arguably become more valuable.
Metric definitions. An agent answering questions in Slack all day has that many chances to pick a plausible definition that isn’t yours. A governed net_revenue removes the choice.
Join paths. Declared relationships prevent fan-out, where a one-to-many join silently double-counts. A person might notice a revenue figure that doubled overnight. An agent writing its own joins has no reference point, so the inflated number just looks like an answer.
Failing loudly. This one is underrated. In dbt Labs’ April 2026 benchmark, the dbt Semantic Layer answered 100% of in-scope questions correctly with both Claude Sonnet 4.6 and GPT-5.3 Codex, against 62.5% and 51.2% for text-to-SQL. On questions that needed more entity hops than the model covered, the semantic layer scored 0%, because it declined to answer. The authors put it this way:
“The Semantic Layer tells you it can’t answer. It never returns invalid data. Text-to-SQL will cheerfully give you a wrong number.”
A refusal costs a follow-up question. A confident wrong number can end up in a board deck.
What a dashboard never needed
This is where the BI-era design runs out. Each of the following was handled by a human or by the BI interface, and an agent has neither.
Allowed values
A dashboard filter is a dropdown. Nobody types 'Active' when the column holds 'active'. An agent writing a WHERE clause has no dropdown, so it needs the list of valid values before it writes SQL. Snowflake’s semantic view YAML spec added exactly this: sample_values, plus an is_enum: true flag that tells Cortex Analyst the list is complete.
What exists, and which table is authoritative
A BI model exposes a curated set of tables. An agent pointed at a warehouse sees fct_revenue and revenue_monthly_v2 and has no way to know which one the CFO trusts, or that one was abandoned in March. That’s structural knowledge, and most of it lives outside the semantic layer.
The long tail of questions
A semantic layer is exact on what you’ve modeled and silent on everything else. Dashboards only ask modeled questions, by construction. People asking an agent don’t know or care what’s modeled. In the dbt benchmark it took three additional dbt models before the semantic layer could answer every question in an 11-question set. Real question queues are a lot longer than 11.
Verified answers and enforced permissions
Row-level security carries over. But an agent also needs known-good answers to check itself against, golden questions to regression-test definitions, and permissions enforced outside the model rather than written into a prompt the model could reason around. Cube’s CEO Artyom Keydunov, arguing that the context layer needs a semantic layer, names the weakness of purely descriptive context like catalogs and glossaries: “nothing here produces an answer or enforces a rule.”
Get Ka Ling Wu’s stories in your inbox
Join Medium for free to get updates from this writer.
The companies that built BI semantic models have quietly conceded all of this. Microsoft’s Prep data for AI adds AI data schemas, verified answers and AI instructions on top of a Power BI semantic model, because when data is ambiguous, “AI systems can struggle to correctly interpret it.” You don’t bolt an AI layer onto something that was already enough.
Two camps, and why both are partly right
Teams are responding in two ways.
The first keeps the semantic layer at the center and wraps context around it. Keydunov calls the context layer “the superset” and the semantic layer “the one part that actually executes”: the piece that compiles certified metrics with access rules applied before any SQL reaches the warehouse.
The second skips the semantic layer. AngelList’s data team chose not to adopt a vendor semantic layer. Instead it keeps a markdown business glossary, a model catalog regenerated automatically from the dbt manifest (documenting some 27,000 columns) and a set of skill files, on the reasoning that an agent writes its own SQL and mostly needs legible, current text. Their line on maintenance is the best single sentence in this debate: “stale semantics are worse than none.” The trade-off they accept is that correctness depends on documentation quality and the model, not a deterministic planner.
I think the two camps are answering different questions. For the 10 to 20 metrics that go into board decks, you want something compiled that refuses rather than guesses. For the long tail, you want context the agent can read. dbt Labs reached the same conclusion from its own benchmark: “It’s both, for different things.”
The research also suggests the content matters more than the container. In a 2026 ablation study on the DABStep benchmark, adding semantic content lifted hard-task accuracy from 13.9% to 55.1% on the weakest of four models and from 37.0% to 77.4% on the strongest. Retrieval scaffolding on its own added between 0 and 15 points. What the agent is told matters more than how the telling is wired.
What to add on top of a semantic layer
If you’re putting an agent on a semantic layer you already have, these are the gaps to close. I sort them into three groups: structure, meaning and trust.
- Structure: register the tables the agent may use, with keys, and name the authoritative version when several look alike. List allowed values for low-cardinality columns and refresh them on a schedule.
- Meaning: your semantic layer’s metrics, plus vocabulary (“bookings” means signed contract value here) and the conventions an analyst would explain to a new hire.
- Trust: golden questions with verified SQL, run as evals whenever a definition changes, and permissions enforced deterministically, never delegated to the model.
If you don’t have a semantic layer yet, the same list is a starting point rather than a reason to wait. That’s the approach we took with Upsolve Data Models: tables and keys registered directly on the warehouse, definitions kept in a versioned system prompt, and selectable columns whose values are cached, with no semantic layer required. I’ve laid out how a context layer relates to the semantic layer in a longer guide.
The semantic layer was the right answer to the dashboard’s question. Agents ask more questions than dashboards did, and the semantic layer is still the best answer to one of them.
Follow me on Medium and LinkedIn for more on analytics agents, context engineering, and the practical infrastructure behind production-grade AI.
