Home › Paths › AI Engineering › Databricks

Learning path · Databricks

AI Engineering on Databricks

You build products and agents where a model does part of the work, safely.

Free, like everything here: no sign-up, no paywall. Only the cloud you practise on may charge; the open-source path costs nothing.

Most of an AI system is ordinary software around a small model call: the tools, the checks, the state, the evaluation and the bill. AI engineers build that harness so the product holds up after the demo.

Every topic below is a concept (the job) with the Databricks product that does it. Learn the concept once; on another platform only the product name changes. Read alongside: The AI Universe · Agent Harness, drawn simply · The Agent Harness Series · Eval Harness, drawn simply · Vertical agents, by industry · Certification prep on this site.

Beginner · 6 weeks

Crawl: You can build one thing end to end, with help.

Call a model, get checked structured output, and give it a few safe tools.

Key ideas at this level, the same on every platform:

Learn

LearnWhat it meansOn Databricks you use
Python and APIsHTTP, JSON, async, tests; read an API's docsPythona language, properly
Databricks Appsrun an app
Calling a modelmessages, tokens, temperature, cost per callFoundation Model APIsmodel api
Structured outputask for JSON, validate it, retry on failureai_query + structured outputprompts and structured output
Toolslet the model ask your code to act; check before actingUnity Catalog functions as toolstool calling
Deterministic firstif code can do it, code does it; the model handles the restPythona language, properly

Build on GitHub

Under way · join

Agent harness from scratch

Build the loop, tools, context and checks around a model in plain Python, one small step at a time.

Built on Open source today. Porting it to Databricks is a good first contribution.

Proposed · needs a lead

Your first agent, three tools

A support assistant that can look up an order, check a policy and draft a reply, where code checks every tool call first.

You are ready to move on when

Intermediate · 3 months

Walk: You can build it so it keeps working, without help.

Build the harness: retrieval, state, approvals, tracing and evaluation on every change.

Key ideas at this level, the same on every platform:

Learn

LearnWhat it meansOn Databricks you use
Retrievalsearch by meaning; chunking; citationsVector Searchvector search
Agent loop and statesteps, budgets, checkpoints, waiting for a humanMosaic AI Agent Frameworkagent runtime
Checks and guardrailsbefore and after every model and tool callAI Gateway guardrailsguardrails
Tracingevery call, token and cent visibleMLflow tracingtracing
Evaluationgolden cases, rules, a gate in CIMLflow evaluationevaluation
GitHub Actions + bundlesci/cd

Build on GitHub

Under way · join

Claims assistant on Azure

A motor-insurance claims agent running for real: tools, checks, approvals, durable waits, evaluation and cost.

Built on Azure today. Porting it to Databricks is a good first contribution.

Under way · join

LearnLangGraph

A hands-on course in graph-shaped agents: state, branches, human approval and resuming after a crash.

Built on Open source today. Porting it to Databricks is a good first contribution.

Under way · join

Reference agent

A customer-support agent with no framework: one module per harness layer, the architecture enforced by tests.

Built on Open source today. Porting it to Databricks is a good first contribution.

You are ready to move on when

Advanced · 6 months +

Run: You can design it, prove it and lead others through it.

Prove an agent before it meets real people, and run many of them at a known cost.

Key ideas at this level, the same on every platform:

Learn

LearnWhat it meansOn Databricks you use
Simulated worldstest against simulated customers, systems and faultsMLflow evaluationevaluation
Gateway and budgetsmany models behind one door; fallbacks; spend limitsMosaic AI Gatewaymodel gateway
Assurancewhat must be true before it is trusted; evidence, not claimsMLflow evaluationevaluation
AI Gateway guardrailsguardrails
Portabilitysame agent, new cloud, by swapping adaptersDeclarative Automation Bundles (Asset Bundles)infrastructure as code
Mosaic AI Agent Frameworkagent runtime
Researchlong-running agents, self-repair, driftMLflow tracingtracing

Build on GitHub

Under way · join

Eval Harness Framework

Rebuild each conversation from the agent's own traces and check it against rules written in plain YAML.

Built on Azure, Open source today. Porting it to Databricks is a good first contribution.

Under way · join

AgentTwin

Simulate the agent's world (customers, systems, faults, time) so a real agent can be tested before it meets real people.

Built on Open source today. Porting it to Databricks is a good first contribution.

Proposed · needs a lead

Port the agent to your cloud

Take the reference agent and bind it to AWS or Google Cloud: same code, new adapters, same tests passing.

Under way · join

AgentTwin Lab

Research: an agent runs for weeks in a simulated business while a fixer repairs it. Does the fixer cheat?

Built on Open source today. Porting it to Databricks is a good first contribution.

You are ready to move on when

Optional

Certifications on Databricks

Projects prove more than certificates, but a certificate can open a door. These fit this path. Exam names and codes change, so check the current one before you book.

Free prep we have written: Certifications.

Learn together

Do it with others

Every project above has a page, a list of open work and a "good first issue" label on GitHub. Pick one at your level, say hello by email, and build it in the open. If a project says needs a lead, that can be you.

All projects →   Another path →