Databricks decides
- Who may read or write data under Unity Catalog
- Which models and serving endpoints are available
- Workspace identity, OBO, and App service principals
- Jobs, Lakeflow, Genie, AI Search, Lakebase, MLflow
Agent control for Databricks
Compose Genie, SQL, AI Search, Jobs, and external tools in TypeScript. Add durable approvals, restart recovery, and Temporal without replacing Databricks governance.
npm install @fabric-harness/sdkNative Databricks foundation
Harness coordinates the run. Databricks remains authoritative for data, identity, models, compute, and hosting.
The 30 second answer
People often hear Fabric as a wrapper around Databricks products. That is the wrong layer. Unity Catalog, AI Gateway, Apps, Genie, Jobs, and MLflow stay native. Fabric is the durable agent control layer when request-scoped hosts are not enough.
Databricks decides
Fabric decides
If AppKit's request and thread lifecycle is enough for a Databricks-only interactive agent, use AppKit. If the work must outlive a request or cross systems, use Fabric on top of Databricks, not instead of it. Read the full boundary guide.
When the control layer earns its keep
Fabric earns its keep after the first crash, the long approval, or the cross-system effect—when the selected runtime and store are configured for durable recovery.
A multi-step Job dies with the process. You cannot tell what finished, what ran twice, or how to resume safely.
With Fabric. Submissions, leases, checkpoints, and terminal states make recovery inspectable. Optional Temporal keeps the same agent contract across worker replacement.
Request-stream approval evaporates when the chat ends. The next attempt is a free-form grant, not the exact operation you reviewed.
With Fabric. Approvals bind the exact tool input and principal, persist beyond one HTTP stream, and stay correlated with lineage, cost, and terminal outcome.
Databricks owns data and models well. The agent still needs git, shell, Slack, sandboxes, or another cloud under one policy trail.
With Fabric. Portable policy, sandboxes, sources, and deployment targets keep one finite or persistent definition across Databricks and the rest of your stack.
How it works
A coherent contract from local mock runs to Databricks Apps, Temporal workers, and portable cloud targets.
Finite jobs or persistent agents with typed input, tools, skills, and a capability policy floor that invocation cannot silently widen.
Sessions drive the model loop. Every tool, shell, or network effect passes policy. Approvals and budgets bind identity before side effects land.
Submissions, events, artifacts, cost, lineage, and replay views explain what resumed, failed, or changed after a crash, wait, or deploy.
Durability through Temporal
Harness records the agent lifecycle and effects. Add the optional Temporal runtime when a Databricks workflow must cross worker replacement, multi-day approval, or a process crash without changing the agent definition.
Durable execution trace
One submission across interruption
Accepted
submission persisted
Running
Genie + SQL evidence
Waiting
steward approval
Restart
App process replaced
Resumed
Temporal continues
Settled
outcome + lineage
The product boundary
Durability and portable governance
are the product boundary.
Agent loops, scoped tools, threads, and request-time approvals now exist in several platforms. Fabric differentiates by keeping bounded lifecycles, policy, recovery, isolation, and evidence coherent across supported runtimes.
Choose the operating plane
Fabric does not flatten every platform into the lowest common denominator. It gives Databricks a first-class governed surface while keeping agent, policy, runtime, and sandbox contracts portable.
Databricks · first-class
Use Databricks AppKit directly for workspace-only interactive agents. Add Fabric when work must survive process failure, cross services, use isolated execution, or retain portable governance evidence.
Cloud + edge · portable
Deploy Node or container artifacts to AWS, Azure, Google Cloud, Cloudflare, or Kubernetes. Swap sandboxes and persistence without rewriting the agent definition.
Databricks agent stack
Build on the Databricks capabilities customers already govern. Harness binds them to an explicit agent lifecycle, durable approval, recovery, and evidence contract.
Workloads
Use the same runtime for data, research, customer operations, incident response, durable business processes, and engineering automation.
A Databricks agent you can explain
This revenue agent asks Genie for business context, verifies claims with read-only SQL, and can refresh a forecast only after an exact-operation approval. Databricks remains the authority; Harness owns how the run proceeds and recovers.
1import {2 createAgent,3 useModel,4 useSkill,5 useTool,6} from '@fabric-harness/sdk';7import { financeControls } from '../skills/finance';8import {9 askGenie,10 readRevenue,11 runForecastJob,12} from '../tools/databricks';1314function RevenueOpsAgent() {15 useModel('databricks/system.ai.gpt-oss-20b');16 useSkill(financeControls);17 useTool(askGenie);18 useTool(readRevenue);19 useTool(runForecastJob);2021 return `Investigate revenue changes with Genie first.22Verify every claim with read-only SQL. If a forecast23must be refreshed, request approval before running the24Job. Return the SQL, Job run ID, and source lineage.`;25}2627export default createAgent(RevenueOpsAgent, {28 durability: { maxAttempts: 5, timeoutMs: 7_200_000 },29 policy: {30 toolPolicy: {31 allow: ['databricks_genie_ask', 'sql_read'],32 requireApproval: ['run_forecast_job'],33 },34 },35});
Deploy
Use Databricks when the agent belongs beside governed data. Use your cloud, cluster, edge, or durable workflow platform when that is where the application already operates.
FAQ
Use these when someone asks what Fabric provides that Databricks does not provide natively.
fh init --template databricks and use --mock for the model loop. Mock mode does not validate Databricks APIs or permissions; certify the target workspace before production.Start locally with mock tools, deploy the same definition to Databricks Apps, and add Temporal when recovery and multi-day work become requirements.
Fabric Harness is built and supported by TechFabric.
Contact TechFabric