Agent Foundations and Prompt Engineering | Board Infinity
Home/Courses/Software Development/AI Agents
Intermediate Course 1 of 3 · AI Agents specialization

Build AI agents. Engineer better prompts.

Learn the foundations behind AI agents, then the prompting that makes LLM workflows work: agent fundamentals, prompt engineering, programmatic prompt chaining, tools and memory, research automation and evaluation.

Enroll on Coursera
Intermediate 4 modules · 16 assignments 2 weeks · 10 hours/week Self-paced
Want a coach alongside the course? See 1:1 coaching
Board Infinity Board InfinityInstructor · 287 courses on Coursera
Introduction to Agentic AI · 7:15

Built in Python

From a minimal agent to an end-to-end chained agent

Certificate included

Shareable on LinkedIn the day you finish

Graded and practice

16 assignments across the four modules

6 Lakh+learners on our Coursera courses
10+domains covered
270+courses
57+specializations
01 About the course

How agents work, then how to prompt them.

Four modules: agent fundamentals, prompt engineering, programmatic chaining with tools and memory, and research automation with evaluation.

4
Modules
Agents to automation
41
Video lessons
Including notebook demos
16
Assignments
4 graded quizzes, 12 practice
21h
Total learning time
≈ 2 weeks at 10 hours a week

The course starts with what makes an AI system agentic: how agents perceive, reason and act, and how policy, memory, tools and environment fit together - ending the first module with a minimal agent built in Python.

It then moves into prompt engineering - role, task and constraints, few-shot and chain-of-thought, tool-use prompts, evaluation, debugging and prompt libraries - before turning those ideas into programmatic workflows in Python with chaining, APIs, tools and memory.

The final module applies everything to research automation and summarization, with testing and evaluation. It's course 1 of Board Infinity's AI Agents: From Foundations to Applications specialization on Coursera.

Inside the course
01AI agents & prompt-driven systems≈ 6h 02Fundamentals of prompt engineering≈ 5h 03Programmatic prompt execution & chaining≈ 5h 04Optimization, debugging & observability≈ 5h
02 Who it's for

For people ready to build with LLMs, not just use them.

An intermediate-level course - Coursera lists it with recommended experience.

AI learners

Understanding how agents work

Building a structured understanding of how modern AI agents work.

Developers

Connecting LLMs to real code

Wiring LLMs, Python, APIs, tools and multi-step workflows together.

Prompt engineers

Making prompting systematic

A repeatable approach to prompt design, evaluation and debugging.

Automation builders

Automating research and workflows

Turning repetitive research and workflow tasks into AI-powered systems.

AI practitioners

Moving to advanced agentic AI

Progressing toward more advanced agentic AI workflows.

03 What you'll learn

Four capabilities, one per module.

Outcome statements as listed on the Coursera course page.

Module 1

Design AI agents

Design and build AI agents using LLM-based architectures and decision flows - perceive, reason, act, observe.

Module 2

Engineer prompts

Craft high-quality prompts using few-shot, chain-of-thought and role-based patterns.

Module 3

Chain workflows

Build programmatic prompt chains with Python for automated multi-step workflows, with tools and memory.

Module 4

Automate research

Develop research automation and summarization pipelines with quality evaluation.

1:1 coaching · optional add-on

Learn agents with someone in your corner.

A dedicated Board Infinity coach, alongside the course, guiding your practice toward the goal you set.

Book a demo session
  • A coach matched to your goal in 24 hours
  • A written roadmap you keep
  • Weekly sessions for as long as you want them

60-minute demo session · 100% refundable · no obligation to continue

A dedicated coach

One person who follows your progress through the course.

Goal-oriented guidance

Sessions shaped around what you want to build with LLMs.

A roadmap you keep

A written plan for what to practise and learn next.

Practice beyond the quizzes

Extra problems and direction on where agent skills fit in a role.

2,000+Industry coaches
16Domains covered
4.8/5Average coach rating
48,000+Sessions delivered
04 Syllabus

Four modules, from agents to automation.

About 21 hours end to end - 2 weeks at 10 hours a week, fully self-paced. Every module lists its learning objectives, its content, and what you'll walk out with.

41 videos 13 readings 16 assignments ≈ 21 hours Download full syllabus
Learning objectives - by the end of this module you can:
  • Describe the structure, purpose and components of AI agents
  • Explain the agent loop and each of its stages
  • Explain how policy, memory, tools and environment fit together, and compare agent architectures
  • Build a minimal agent in Python
What's inside
9 videos72 min
4 readings120 min
4 assignments150 min
1 plugin5 min
Topics covered
Agentic AI Evolution of AI systems Agentic characteristics Real-world use cases The agent loop Policy, memory, tools, environment Agent architectures Minimal agent in Python
You'll leave with: a clear model of how agents work, and a minimal agent of your own in Python.
Learning objectives - by the end of this module you can:
  • Formulate effective prompts for task-specific outcomes
  • Structure prompts by role, task and constraints, and apply few-shot and chain-of-thought
  • Write function-based prompts for tool use
  • Evaluate, debug and organize prompts into reusable libraries
What's inside
12 videos82 min
3 readings90 min
4 assignments150 min
Topics covered
Role, task, constraints Few-shot prompting Chain-of-thought Tool-use prompts Consistency & reliability Prompt failure patterns Prompt debugging Prompt libraries
You'll leave with: a systematic way to write, evaluate and debug prompts - and a library to reuse them.
Learning objectives - by the end of this module you can:
  • Build chained prompts that pass context between tasks
  • Implement sequential chaining in Python and decide when chains are worth it
  • Give an agent tools and memory
  • Visualize and debug chains, then design and run a chained agent end to end
What's inside
12 videos97 min
3 readings90 min
4 assignments120 min
Topics covered
Prompt chaining Sequential chains in Python Dynamic prompting with APIs Tool-using agents Agent memory Why chains fail Debugging chains End-to-end chained agent
You'll leave with: a chained agent with tools and memory, built and run end to end in Python.
Learning objectives - by the end of this module you can:
  • Apply optimization, debugging and observability to retrieval systems and agents
  • Design a research system's architecture, data layer and data models
  • Build a research agent that collects, analyzes and summarizes
  • Test the system and evaluate summarization quality
What's inside
8 videos55 min
3 readings90 min
4 assignments150 min
Topics covered
Project architecture Data layer & scraper Review analysis Data models The research agent Testing & evaluation Observability & tracing Response optimization
You'll leave with: a working research agent, and a way to test and evaluate what it produces.
05 Tools & skills

What you work with, and what you come away with.

The tools below are the ones the course FAQ names. Skills are listed as they appear on Coursera.

The reasoning core

Large language models

The reasoning core behind the agents and workflows you design.

Automation

Python

From a minimal agent to chained prompts, in notebook demonstrations.

Integration

LLM APIs

Calling models programmatically, including dynamic prompting and API chaining.

Framework

LangChain

Named in the course FAQ among the tools for building AI agents and workflows.

Skills you leave with

Core skills from the Coursera course page, plus the workflow concepts the specialization names - grouped by what they're for.

LLMs & agents

Understanding and applying the models.

  • Large Language Modeling
  • LLM Application
  • Generative AI Agents
  • Agentic systems

Build & quality

Making what you build reliable.

  • Tool Calling
  • Debugging
  • Verification and Validation
  • Quality Assurance

Workflows

Turning prompts into multi-step systems.

  • Prompt Engineering
  • AI Workflows
  • Agentic Workflows
  • AI Orchestration
Certificate

Proof you can build with modern AI workflows.

Complete the course on Coursera to earn a shareable certificate from Board Infinity - with a verification link and a one-click path onto your LinkedIn profile.

A course certificate issued through Coursera. It is not a vendor or professional certification, and does not imply endorsement by any AI company.

On your profile in one click

Add it to your LinkedIn profile, resume or CV, where recruiters actually look.

Anyone can verify it

Its own verification link, so a hiring manager confirms it in seconds.

Earned, not attended

Awarded on a graded quiz in each of the four modules - it certifies what you can do.

Part of a specialization

Course 1 of 3 in AI Agents: From Foundations to Applications.

06 Career impact

Skills that point toward building with AI agents.

The role directions these skills relate to. They're directions, not guaranteed outcomes - the course does not include job placement.

Where these skills count

AI / ML Engineer

LLM applications, agent architectures and evaluation.

Generative AI Developer

Prompting, LLM APIs and multi-step generation workflows.

AI Automation Developer

Prompt chains in Python that automate repetitive work.

Prompt Engineer

Structured prompts, debugging and reusable libraries.

AI Solutions Developer

Combining LLMs, tools and memory into working systems.

AI Agent Developer

Agent loops, tool calling and decision flows.

The honest comparison

What you're actually paying for

Documentation, open-source examples and free videos are excellent ways to learn. What a course adds is structured progression: an order to learn things in, and a way to check you've learned them.

What you need
This course
Piecing together tutorials
Order of learningAgents → prompts → chains → automation
A progressive curriculum, agent foundations first
Scattered concepts, unclear progression
Prompt engineeringOne consistent vocabulary
Structure, patterns, evaluation and debugging together
Inconsistent terminology between sources
Building workflowsFrom one prompt to a system
Chaining, then tools and memory, then research automation
Hard to know what to learn next
Checking your understandingLearning that sticks
16 assignments, including graded quizzes
Little systematic evaluation
Showing your workVerifiable, on LinkedIn
A shareable certificate on Coursera
Your own projects, documented by you
07 The bigger path

This is the foundation. Two courses build on it.

Agent Foundations and Prompt Engineering is Course 1 of the AI Agents: From Foundations to Applications Specialization on Coursera.

You're here Course 1

Agent Foundations and Prompt Engineering

Agent architectures, prompt engineering, prompt chaining with Python, and research automation with evaluation.

≈ 21 hours · 4 modules
Back to top
Course 2

RAG Systems & Agentic Workflows with Pinecone and LangGraph

End-to-end RAG pipelines connecting LLMs with external knowledge, plus agentic workflows.

≈ 20 hours
View course
Course 3

Advance Multi-Agent Systems & Production AI with LangSmith

Multi-agent systems and production-ready AI pipelines, with observability.

≈ 16 hours
View course

Course titles as listed on the specialization page.

Know exactly what you're signing up for.

4 modules · 41 lessons · 16 assignments · free PDF

08 FAQ

Common questions

Answers about the course follow the Coursera course page.

About the course

You'll learn to work with large language models (LLMs), prompt engineering techniques, Python for automation, LLM APIs, LangChain framework, and tools for building AI agents and automated workflows.

You'll be able to build AI agents for workflow automation, customer experience chatbots, research automation tools, summarization pipelines, and intelligent decision-making systems using LLMs.

Yes. The course includes Python notebook demonstrations, practice quizzes after each video, AI dialogue exercises, and graded assessments to reinforce your learning with practical application.

Coursera lists it as intermediate level with recommended experience, taking 2 weeks to complete at 10 hours a week on a flexible schedule. The four modules are listed at 6, 5, 5 and 5 hours.

Access, certificate & cost

According to Coursera, to access course materials, assignments, and earn a Certificate, you'll need to purchase the Certificate experience when you enroll in a course. Eligible learners may also have the option to start with a Free Trial. Some courses may also offer a Full Course, No Certificate option, which lets you access course materials, submit required assessments, and receive a final grade, but not earn or purchase a Certificate. Check the course page for the options available to you.

Coursera says that when you enroll in the course, you get access to all of the courses in the Specialization, and you earn a certificate when you complete the work. Your electronic Certificate is added to your Accomplishments page, from where you can print it or add it to your LinkedIn profile.

Yes. In select learning programs, you can apply for financial aid or a scholarship if you can't afford the enrollment fee. If financial aid or a scholarship is available for your learning program selection, you'll find a link to apply on the description page.

About this page

No. Board Infinity 1:1 coaching is a separate, optional add-on. Enrollment, lessons, grading and the certificate all happen on Coursera. Learn about coaching.

No. This is an independent educational resource created by Board Infinity. It is not affiliated with, endorsed by, sponsored by, or officially associated with any company, organization, or certification body unless explicitly stated. Tools such as LangChain are named for educational purposes only.

Want someone building this with you?

Optional Board Infinity 1:1 coaching pairs you with a coach while you take the course.

See 1:1 coaching

Build the foundations. Then build the agent.

Start with agent architecture and prompt engineering, then move toward chained workflows, research automation and more advanced agentic systems through the specialization.

Enroll on Coursera

Agent Foundations and Prompt Engineering · by Board Infinity · offered on Coursera

Agent Foundations & Prompt Engineering Enroll