Databricks Agent Bricks

What you get

the numbers that matter

Starting price

Priced on scope

starting price

Ready in

≈ 2 weeks

signed to first PR

Retention

96%

engagements renewed

Match

96%

to your stack & domain

Databricks product for building, evaluating and deploying data-aware AI agent systems on the Databricks platform.

How this operator works

every way of working, already decided

A · capability focus

Owns the system, not the ticket

Takes end-to-end ownership of a service or surface. Design, delivery, on-call. And is measured on outcomes, not hours.

B · ways of working

Embedded, async-first, instrumented

Works inside your repos, your CI and your rituals. Daily written standups, decisions logged. No status-meeting tax.

C · reliability posture

Runbooks, canaries, reversible deploys

Every change gated and reversible. Incidents get a timeline and a postmortem; nothing ships without a rollback.

D · comms & cadence

Plugged into your Slack & rituals

Joins standups and retros, reports weekly against the goal. You get an operator, not a queue.

E · tooling

Brings a pre-wired stack or adopts yours

Infrastructure and observability as code by default. No bespoke setup tax to absorb.

F · onboarding

Scoped, gated, reversible

Week-1 shadow, week-2 ownership, swap on request inside the trial window. No long-tail handover risk.

Overview

Agent Bricks is Databricks' commercial product for building and deploying data-aware AI agent systems. Teams declare the task an agent should perform, and Agent Bricks builds and tunes the agent against the organisation's own data on the Databricks platform.

Through Scrums.com, Databricks Agent Bricks is listed on the catalog and deployed by Scrums.com delivery teams. They integrate it into your stack, apply your governance rules, and track its operation on the SEOP.

What it does

Task-declared agent building

Teams describe the task; Agent Bricks assembles an agent system for it rather than requiring hand-built pipelines.

Automatic evaluation

Built agents are evaluated against the task so quality is measured, not assumed.

Agent optimization

Agent Bricks iterates on agent configurations to improve quality and cost for the declared task.

Databricks-native deployment

Agents run on the Databricks platform, close to the governed data they depend on.

Deploying it with Scrums.com

Scope. Scrums.com runs a fit assessment against your workflows and governance requirements, including the agent tasks and the Databricks data they depend on.
Integrate. Scrums.com engineers wire it into your repos, pipelines and tools with guardrails, building and deploying the agents in your Databricks workspaces.
Operate. The deployment runs under governance, with usage and outcome reporting via the SEOP.

Commercial availability

Agent Bricks is a commercial capability of the Databricks platform, billed under your Databricks consumption agreement. Procurement runs through Databricks; Scrums.com supports the commercial process as part of a deployment.

FAQs

How is this different from hand-building agents on a framework?

Frameworks give you parts; you assemble and tune them. Agent Bricks starts from a task declaration and handles building, evaluating and optimizing the agent on Databricks.

What does deployment need?

A Databricks workspace with the relevant AI features enabled in your region, plus access to the datasets and tools the agents will use.

How is it governed?

Agents run inside your Databricks environment under its access controls and platform governance. Scrums.com defines scopes with you and reports usage and outcomes via the SEOP.

What's included

in every engagement · no add-ons

✓Task-declared agent buildingincl.

✓Automatic evaluationincl.

✓Agent optimizationincl.

✓Databricks-native deploymentincl.

Track record

deployments on real systems · anonymized

SectorSystemOutcomeSpanStatus

Fintechpayments-core ledger99.97% achieved14 mocomplete

Commercecheckout platform−38% incident rate9 mocomplete

Health SaaSdata plane0 SEV1 in 6 mo11 moactive

Logisticsrouting enginezero-downtime cutover7 mocomplete

AI infrainference clusterp99 −120 ms5 moactive

Works inside your stack

surfaces this operator binds to

SurfaceBindingDirectionAuth

Source controlgithub.com/<org>reviews + writesOIDC

CI / CDscm-flow · deploy-servicegates deploysOIDC

Observabilityotlp://collector:4317metrics + alertsmTLS

Commsslack://<workspace>standups, incidentsSSO

Secretsvault://scrums/op/<id>short-lived credsSPIFFE

On-callpagerduty://<org>primary / secondaryAPI token

Boundaries

what to deploy instead

Scoped to this discipline. For an adjacent capability, compose a second operator into the squad. compose →

Not a fractional advisory engagement. For advisory-only, contact platform@scrums.com.

Deployments

the only social proof we publish

402deploys

across 38 organizations

+24 last 30 days · median age 11.4 mo · retention 96%

Live telemetry

this operator's system surface

system map

signals · last 24h

deploys18

p99 latency112 ms

error rate0.02%

incidents0

Pricing

one number · one footnote

starting price

Priced on scope

All-in: the operator, delivery manager and replacement guarantee. No recruiter fee, no markup surprises.

Final pricing computed at deploy from your committed envelope, region and account tier.

FAQ

common questions

How is Databricks Agent Bricks priced?+

Priced on scope. Request a quote and pricing is computed from the work envelope.

Is Databricks Agent Bricks available now?+

Yes. It is published and deployable directly from the Scrums.com catalog.

Can a Databricks Agent Bricks deployment be reversed?+

Yes. Deployments are reversible with a one-click swap inside the trial window.

Who provides Databricks Agent Bricks?+

Databricks, vetted by the Scrums.com platform.

How it compares

vs other agents

Option	From	Stack	Status
Databricks Agent Bricks · this one	Priced on scope	agent · ai-agents · data-agents	● available
Qdrant MCP Server	Priced on scope	mcp · qdrant · vector database	● available
Pinecone MCP Server	Priced on scope	mcp · pinecone · vector database	● available
Databricks SQL MCP Server	Priced on scope	mcp · databricks · sql	● available

Commonly deployed with

more agents

AgentsCAT-30031039

Qdrant MCP Server

Qdrant MCP Server gives approved AI clients access to qdrant vector-memory workflows for storing and retrieving semantically relevant context. It is most valuable where teams want to provide engineering agents with an explicit semantic memory or retrieval layer for code and technical knowledge.

mcpqdrantvector databasesemantic search

QdrantVIEW →

AgentsCAT-30031040

Pinecone MCP Server

Use Pinecone MCP Server to connect engineering agents with pinecone documentation, index management, upserts and vector queries. The key operational benefit is to let AI engineers build and operate retrieval systems directly from their coding agents.

mcppineconevector databaserag

PineconeVIEW →

AgentsCAT-30031041

Databricks SQL MCP Server

Databricks SQL MCP Server is a first-party MCP surface for aI-generated SQL against Unity Catalog tables with read/write governed by Databricks permissions. The engineering-leadership use case is straightforward: connect engineering and data agents to governed SQL execution over enterprise data.

mcpdatabrickssqlunity catalog

DatabricksVIEW →