Introduction to AI Agents
Adel Nehme
VP of AI Curriculum, DataCamp
$$ Types of customer tickets
| Ticket Type | Knowledge Resources | Tools to Access |
|---|---|---|
| Billing disputes | Internal finance documentation, payment policy wiki, transaction logs | Secure payment APIs, CRM with billing integration |
| Technical issues | Engineering runbooks, system architecture docs, incident postmortems | Observability tools (e.g., Datadog), ticketing system, internal dashboards |
| Legal compliance questions | Legal knowledge base, compliance manuals, GDPR/CCPA documentation | Contract management system, legal Q&A assistant, document retrieval tools |
| Product recommendations | Product feature matrix, customer personas, sales playbooks | Recommendation engine, CRM with lead tracking, chatbot assistant |
Increasingly complex logic
Models using prompts with a high amount of if-else scenarios and edge-cases
$$
Tool overload
Agentic systems where a single model needs to call a wide variety of tools

Single Agent Systems
A single model equipped with appropriate tools and instructions executes workflows in a loop
Multi-Agent Systems
Execute workflows across multiple coordinated agents
$$

$$

$$

$$



Introduction to AI Agents