Applied AICollège Unica
3.1SpecializationSession 4 · Applied AI Systems & MLOps

Data collection and storage

20classes60htotalTH2 · PR2 · PNW2weighting per class

Class-by-class breakdown

20 classes

TH = theory · PR = practical · PNW = personal work. These are ministry weighting codes (not hours) used to split each class's minutes. Class length = course hours ÷ class count; the three time-boxes below always sum to that length.

0%

Quiz progress

0 of 0 classes attempted

First 2 classes free with a referral 19 more with enrollment180 min per classTheory 60mPractical 60mPersonal Work 60m
1

Why Data Feeds the Agent — From Raw Sources to GenAI Knowledge

FreeTH2PR2PNW2

An AI Integration Manager knows an agent is only as good as the data it retrieves — every RAG answer traces back to how data was collected and stored.

Theory60m
  • The agent data pipeline: collect → store → retrieve → generate
  • Why structured AND unstructured data both matter for GenAI
  • Map one business problem to the data an agent would need
Practical60m
  • List the data sources a customer-support agent would need for one company
  • Sketch the collect→store→retrieve→generate flow for that agent
Personal Work60m
  • Write a one-page data inventory for a sample agent use case
  • Micro-task: submit your inventory
2

Structured vs Unstructured Data — What Agents Actually Consume

LockedTH2PR2PNW2

Locked class preview

A Data/Business Analyst who distinguishes a database row from a PDF knows which storage fits each — agents increasingly need both

Enroll to unlock every class in this course — the full agenda, the AI tutor, and the quiz.

Talk to admissions
3

Relational Databases and SQL — The Foundation Agents Query

LockedTH2PR2PNW2

Locked class preview

A Data/Business Analyst who writes SQL can give an agent a reliable, queryable source of truth instead of hallucinated guesses

Enroll to unlock every class in this course — the full agenda, the AI tutor, and the quiz.

Talk to admissions
4

NoSQL and Document Stores — Flexible Storage for Agent Inputs

LockedTH2PR2PNW2

Locked class preview

An AI Integration Manager storing varied agent inputs (logs, JSON, chat transcripts) picks document stores when rigid tables won't fit

Enroll to unlock every class in this course — the full agenda, the AI tutor, and the quiz.

Talk to admissions
5

APIs as Data Sources — Letting Agents Pull Live Business Data

LockedTH2PR2PNW2

Locked class preview

A Project Manager who connects an agent to live APIs (CRM, billing, analytics) turns a chatbot into a real business tool

Enroll to unlock every class in this course — the full agenda, the AI tutor, and the quiz.

Talk to admissions
6

Web Scraping and Content Extraction — Building a Knowledge Base

LockedTH2PR2PNW2

Locked class preview

A Digital Marketing Strategist building a competitor-research agent needs scraped web content as the knowledge base the agent retrieves from

Enroll to unlock every class in this course — the full agenda, the AI tutor, and the quiz.

Talk to admissions
7

Chunking and Preparing Text for RAG — From Documents to Retrieval Units

LockedTH2PR2PNW2

Locked class preview

A Data/Business Analyst who chunks documents well directly improves RAG answer quality — bad chunks mean missed answers

Enroll to unlock every class in this course — the full agenda, the AI tutor, and the quiz.

Talk to admissions
8

Embeddings and Vector Storage — How Agents Find the Right Knowledge

LockedTH2PR2PNW2

Locked class preview

An AI Integration Manager who understands vector stores knows how a RAG agent retrieves the exact passage that answers a question

Enroll to unlock every class in this course — the full agenda, the AI tutor, and the quiz.

Talk to admissions
9

Building a RAG Knowledge Base — End-to-End Retrieval Store

LockedTH2PR2PNW2

Locked class preview

A Data/Business Analyst who builds a RAG knowledge base gives an agent a trustworthy source it can cite instead of hallucinating

Enroll to unlock every class in this course — the full agenda, the AI tutor, and the quiz.

Talk to admissions
10

Agent Memory — Short-Term Context vs Long-Term Storage

LockedTH2PR2PNW2

Locked class preview

An AI Integration Manager designing an agent must decide what stays in context vs what's stored — memory design shapes agent behavior

Enroll to unlock every class in this course — the full agenda, the AI tutor, and the quiz.

Talk to admissions
11

Data Lakes and Warehouses — Where Enterprise Agent Data Lives

LockedTH2PR2PNW2

Locked class preview

A Project Manager scoping an enterprise agent must know where the org's data actually lives — lakes, warehouses, or both

Enroll to unlock every class in this course — the full agenda, the AI tutor, and the quiz.

Talk to admissions
12

Cloud Storage for AI Projects — Object Storage and Managed Stores

LockedTH2PR2PNW2

Locked class preview

An AI Integration Manager deploying an agent uses cloud object storage for documents and managed vector stores for retrieval

Enroll to unlock every class in this course — the full agenda, the AI tutor, and the quiz.

Talk to admissions
13

Data Quality for Agents — Garbage In, Hallucinated Out

LockedTH2PR2PNW2

Locked class preview

A Data/Business Analyst knows a RAG agent fed bad data gives confidently wrong answers — data quality is an AI safety issue

Enroll to unlock every class in this course — the full agenda, the AI tutor, and the quiz.

Talk to admissions
14

Pipelines and Orchestration — Automating the Collect→Store→Retrieve Flow

LockedTH2PR2PNW2

Locked class preview

A Project Manager who automates the data pipeline keeps the agent's knowledge base current without manual work

Enroll to unlock every class in this course — the full agenda, the AI tutor, and the quiz.

Talk to admissions
15

Security, Privacy and Access Control for Agent Data

LockedTH2PR2PNW2

Locked class preview

An AI Integration Manager must ensure an agent only retrieves data the user is allowed to see — access control is non-negotiable

Enroll to unlock every class in this course — the full agenda, the AI tutor, and the quiz.

Talk to admissions
16

Mini-Project — Assemble an Agent's Knowledge Base

LockedTH2PR2PNW2

Locked class preview

This ties collection and storage together — a Data/Business Analyst who builds a working RAG knowledge base proves an agent can answer from real data

Enroll to unlock every class in this course — the full agenda, the AI tutor, and the quiz.

Talk to admissions
17

Evaluating Retrieval Quality — Is the Agent Getting the Right Data?

LockedTH2PR2PNW2

Locked class preview

An AI Integration Manager who measures retrieval quality can prove the agent finds the right passage — not just any passage

Enroll to unlock every class in this course — the full agenda, the AI tutor, and the quiz.

Talk to admissions
18

Cost and Scaling of Agent Data Stores

LockedTH2PR2PNW2

Locked class preview

A Project Manager must estimate storage and embedding costs before scaling an agent — unbounded ingestion burns budget fast

Enroll to unlock every class in this course — the full agenda, the AI tutor, and the quiz.

Talk to admissions
19

Data Governance and Lineage — Tracking Where Agent Knowledge Came From

LockedTH2PR2PNW2

Locked class preview

A Project Manager who tracks data lineage can answer 'where did this answer come from?' — governance builds stakeholder trust in the agent

Enroll to unlock every class in this course — the full agenda, the AI tutor, and the quiz.

Talk to admissions
20

Present and Reflect — Your Agent Data Architecture

LockedTH2PR2PNW2

Locked class preview

A Data/Business Analyst presenting a data architecture proves the agent's answers are grounded in well-collected, well-stored data

Enroll to unlock every class in this course — the full agenda, the AI tutor, and the quiz.

Talk to admissions

Unlock all 20 classes

Get the full agenda, AI tutor, and quiz for every class in 3.1 · Data collection and storage.

Apply via admissions

Online checkout not yet live — contact admissions to enroll.

Previous course

4.3 · Cloud computing

Next course

4.5 · Develop your leadership skills

Back to Session 4