Pull-quote: “Agents on the Lakehouse mean tools that read and write Delta tables, models that serve under MLflow, and evaluations that ship as Delta tables themselves.”
Why this matters
Agentic workflows are the next layer on the Lakehouse — agents that reason, plan, call tools, and produce verifiable artifacts. The Mosaic AI Agent Framework provides the runtime. The architectural decisions still belong to you.
Reference architecture
┌──────────────────────────────────────────────────────────────────┐
│ AGENT (LangGraph / LlamaIndex / Custom) │
│ │
│ Planner ──► Executor ──► Critic ──► Referee │
└─────────────────────┬────────────────────────────────────────────┘
│
▼
┌──────────────────────────────┐
│ Typed Tools │ ◄── Tool catalog
│ - read Delta tables │ (Unity Catalog)
│ - write Delta tables │
│ - call MLflow models │
│ - call REST APIs │
└──────────────┬───────────────┘
│
▼
┌──────────────────────────────┐
│ Mosaic AI Model Serving │
│ - foundation models │
│ - fine-tuned models │
│ - per-agent traffic split │
└──────────────┬───────────────┘
│
▼
┌──────────────────────────────┐
│ Evaluations as Delta tables │ ◄── Versioned
│ - golden datasets │
│ - regression suite │
│ - hallucination detection │
└──────────────────────────────┘What “typed tools” means
Every tool has a JSON schema for inputs and outputs. The agent cannot call a tool with invalid inputs — the schema rejects the call. This eliminates an entire class of failure that plagues unconstrained agents.
What “evaluations as Delta tables” means
Evaluation results are stored as rows in versioned Delta tables. Each row is (agent_version, input, expected_output, actual_output, score, metadata). Regression analysis is a JOIN between two agent_version slices. New versions don’t promote unless they pass.
The agent / human contract
Where humans fit:
- High-risk operations require human-in-the-loop checkpoints. Agents can propose; humans approve.
- Critic disagreements with the executor route to humans when the referee cannot adjudicate.
- Periodic spot-checks on agent decisions are scheduled into the evaluation harness.
This is not “manual override.” This is a designed-in contract about which decisions are agent-final and which are human-final.
Common architectural decisions
| Decision | Default |
|---|---|
| Number of executors | One unless sub-goals are independent |
| Critic per executor or shared | Shared unless executors are heterogeneous |
| Memory model | Working memory in agent state; long-term memory in Delta table |
| Tool call timeout | 30 s default, with retries on idempotent tools |
| Cost ceiling per session | Configurable; defaults to a hard cap |
Closing
Multi-agent workflows on Databricks are productive when the framework is paired with discipline: typed tools, deterministic logging, evaluations as Delta tables, and a designed-in agent / human contract. The Mosaic AI Agent Framework is the runtime; the architecture is yours.
