Agentic AI: From Acronyms to Applications
Demystifying the Agentic AI Landscape
Segun Akinyemi | Senior Software Engineer | Microsoft
`
​
Segun Akinyemi
Senior Software Engineer
LinkedIn
Website
Charlotte 3rd Places
> About
Senior Software Engineer at Microsoft building systems that power business decisions using Azure. I lead STEM outreach initiatives in Charlotte, North Carolina, connecting people with knowledge that helps them navigate tech careers. Beyond that, I blog, read, run, hike, watch anime, longboard, and enjoy exploring Charlotte's best third places.
> Highlights
•🌍 Roots: Nigerian heritage, raised in Seattle, educated in St. Louis, now in Charlotte.
•🎓 Education: B.S. in Computer Information Systems (Lindenwood University), M.S. in Information Systems Management (Washington University in St. Louis).
•💻 Engineer: Building with Python, C#, TypeScript, & SQL. Embracing AI Engineering.
•📚 STEM Educator: Leading programs that connect students with tech careers.
What Microsoft products have you used or are currently using?
You might be surprised by just how much Microsoft is a part of your everyday life! 🧐
Let’s Chat!
Ensure that artificial general intelligence (AGI) benefits humanity.
​
Empower every person and organization on the planet to achieve more
ChatGPT is powered by Microsoft Azure
Did you know?
Today we are…
Demystifying Agentic AI, what it is, and what it isn’t
Decoding its key concepts like RAG, MCP, RLHF, and more
Interacting with an AI agent and watching it make decisions
Building your own custom agent with personalized instructions and tools
No hype
No pretension
No LinkedIn-speak
Most Importantly
Agentic AI is a new frontier. We’re all learning. Do you feel lost? Join the club.
​
Even developers are overwhelmed.
​
Today we slow down. We keep it real. We understand what we’re really talking about without bloviated jargon.
​
​
​
Artificial Intelligence
When we say “AI”, what do we really mean?
Which type has everyone worried about their jobs?
​
Artificial Intelligence
​
Machine Learning
​
Deep Learning
This Is a New Moment For AI
Generative AI
1950s
Artificial Intelligence
the field of computer science that seeks to create intelligent machines that can replicate or exceed human intelligence.
1959
Machine Learning
subset of AI that enables machines to learn from existing data and improve upon that data to make decisions or predictions.
2017
Deep Learning
a machine learning technique in which layers of neural networks are used to process data and make decisions.
​
2021
Generative AI
create new written, visual, and auditory content given prompts or existing data.
The History of AI
​
​
1960
The ”first computer” that learned skills by trial and error.
​
​
1978/79
In Japan, SCARA, the robotic arm for high-speed assembly unveiled.
​
Late 2000s
IBM’s Watson, a computer system answers questions via natural language. Beats Jeopardy! contestants.
​
1950
Alan Turing introduces the “Turing Test”
1956
Field of AI is launched, “artificial intelligence” coined at Dartmouth
​
1997
IBM’s Deep Blue beats reigning world champion Garry Kasparov in chess.
Late 1990s
KISMET, a robot head that recognizes and replicates human emotion.
​
1988
Jabberwacky, a chatbot designed to have conversations with users and imitate human interaction.
​
2011
Apple launches Siri, an intelligent personal assistant.
​
​
2021
OpenAI develops DALL-E, an image generator based on text prompts.
2022
OpenAI launches ChatGPT,
a chatbot that interacts in
a conversational way.
​
​
16 years
3 months
50M
100M
​
​
​
Facebook: 4.5 years
ChatGPT: 3 Months!
Cell Phones: 16 years
Internet: 7 years
Time to reach 100M users
Generative AI Is Not Just Hype
Source: Microsoft Research
GPT stands for…
Generative: Creates new text by predicting what comes next, using patterns it learned from tons of reading
Pre-trained: Was trained ahead of time on books, websites, social media, and more to understand language and context
Transformer: A model that focuses on the most important words in a sentence, like highlighting key info to better understand meaning
LLM stands for…
Large: Trained on massive collections of text with billions of adjustable parameters so it can learn broad patterns.
Language: Works with words as tokens. Uses context (what’s been said before) to understand your prompt and generate fitting responses.
Model: A mathematical system that predicts the next token (word) based on patterns, then chains those predictions into coherent responses.
Subtitle text
Subtitle text
​
​
The foundation of everything AI does is patterns. Patterns in text, images, audio, code, and other data.
We don’t have science fiction level AI yet. That’s called Artificial General Intelligence (AGI).
What we have today is extremely advanced and incredibly impressive pattern recognition at scale.
Pattern Recognition
The core concept behind AI
​
​
​
How Agentic AI will transform financial services with autonomy, efficiency and inclusion
Agentic AI
​
​
​
Look For Agentic AI To Empower Enterprises In 2025
​
​
​
Agentic AI will disrupt the mobile app landscape
​
​
​
What is Agentic AI, and How can it transform advice?
​
​
​
Intelligent Agents in AI Really Can Work Alone. Here’s How.
​
​
​
The Future Of GenAI Is Increasingly Agentic
​
​
​
​
Agentic AI will be the real banking disruptor
​
​
​
Why agents are the next frontier of generative AI
​
​
​
The transformative power of agentic AI and agentic automation
​
​
​
​
Agentic AI: A new iteration of AI is now taking the world by surprise
​
​
​
A.I. Isn’t Magic, but Can It Be ‘Agentic’?
​
​
​
Leading the Way with Agentic AI
​
​
​
​
AI to transform wealth management
​
​
​
How Agentic AI will transform financial services with autonomy, efficiency and inclusion
Agentic AI
​
​
​
Look For Agentic AI To Empower Enterprises In 2025
​
​
​
Agentic AI will disrupt the mobile app landscape
​
​
​
What is Agentic AI, and How can it transform advice?
​
​
​
Intelligent Agents in AI Really Can Work Alone. Here’s How.
​
​
​
The Future Of GenAI Is Increasingly Agentic
​
​
​
​
Agentic AI will be the real banking disruptor
​
​
​
Why agents are the next frontier of generative AI
​
​
​
The transformative power of agentic AI and agentic automation
​
​
​
​
Agentic AI: A new iteration of AI is now taking the world by surprise
​
​
​
A.I. Isn’t Magic, but Can It Be ‘Agentic’?
​
​
​
Leading the Way with Agentic AI
​
​
​
​
AI to transform wealth management
Agency is…
The ability to make decisions and act independently
Agentic AI is…
AI that can make decisions and act independently with minimal human oversight.
Once goals and guardrails are set, it plans, decides, and acts autonomously.
​
Agentic AI
​
​
Autonomy: Take goal-directed actions with minimal human oversight.
​
Reasoning: Provide contextual decision-making and make judgment calls and tradeoffs.
​
Adaptable Planning: Dynamically adjust plans based on changing conditions to complete processes.
​
Context Understanding: Comprehend and follow natural language and other modalities.
​
Action Enabled: Empowered to act via access to web services to deliver specific skills.
Key Characteristics
​
”
We’ve gravitated towards a simple definition for agents: LLM’s autonomously using tools in a loop.
An AI system that has instructions (what it should do), guardrails (what it should not do), and access to tools (what it can do) to take action on the user’s behalf
The Bare Necessities
These aren't different products. They’re different behaviors. The same AI model can do both. On its own, a model only knows what it learned during training. Give it tools, and it can go beyond that training to get stuff done.
Generative AI
AI that creates new content from patterns it learned
Agentic AI
AI that uses tools in a loop to achieve a goal
Reactive: Prompt and Stop
Proactive: Plan and Act
ELT layout
The Agent Lab
Interact with an AI agent, learn the acronyms along the way, then build your own!
​
Open your laptop and visit the website to the right.
​
Click Start Course then login with your Microsoft or Google account.
​
​
​
​
Follow the instructions, answer all questions, and proceed through the units.
Raise your hand if you have any questions!
​
​
​
​
Click the Green play button
Then click X for a larger view
Click the green play button in the upper right to load the Agent Playground
​
uncc-wids-2026
Workshop Key
​
​
Can your agent make it onto the live feed?
​
Make sure you’re on the Post to the Live Feed page. The Live Feed tool will be first in the list and already enabled!
You’re Ready: From Acronyms to Applications
GPT
Generative Pre-trained Transformer
​
LLM
Large Language Model
NLP
Natural Language Processing
RAG
Retrieval-Augmented Generation
Context & Context Window
AI’s memory and the size of it
MCP
Model Context Protocol
RLHF
Reinforcement Learning from Human Feedback
GANs
Generative Adversarial Networks
Some Final Thoughts
We’ve learned the concepts, now let’s explore some resources for further exploration.
•You built an AI agent today by writing English and picking tools.
•That’s a growing phenomena called Natural Language Programming.
•That simplicity exists because software engineers first built the models, cloud infrastructure, APIs, MCPs, databases, security, networking, data pipelines, RAG systems, and tooling that power these platforms.
•Companies like GitHub, Microsoft, Google, Amazon, Meta, OpenAI, and Anthropic build these foundations so others can create custom agents using natural language, often defined in markdown files.
•You can describe intent in natural language but building enterprise‑grade software still requires strong technical skills.
•Overall, programming has shifted from syntax-first to intent-first, lowering the barrier to building useful software and agents.
What You Just Did Has a Name
​
​
​
​
​
​
​
​
​
​
​
​
Natural Language
Code
first
Microsoft’s Agent Landscape
​
M365 Copilot
Agent Builder
For End Users
Copilot Studio
+ Microsoft Foundry
For Makers
VS Code/GitHub/
Microsoft Foundry
Microsoft Agent Framework
For Developers
​
”
Agentic AI doesn’t eliminate the need for human expertise, it amplifies it.
The Dangers of Handing Over Control to AI Agents
​
When AI systems can control multiple sources simultaneously, the potential for harm explodes. We need to keep humans in the loop.
​
Advanced Concepts to Explore
​
Agentic RAG
Decides what to retrieve
Searches without being asked
Updates knowledge autonomously
​
​
Fine-Tuning
Teaches AI your domain
Makes generic AI specific
Customizes for your business
The AI Engineer
Model Selection & Evaluation
(GPT, Claude, Llama, Geimini, etc.)
Data Architecture for AI (Vector DBs, embeddings, indexing)
Connect AI to Everything (MCP, RAG, CAG, real-time APIs)
#1 Fastest Growing Job (LinkedIn 2025)
Vector Databases
GPS for finding data
Stores knowledge as numbers
Lightning-fast information retrieval
​
​
Cache-Augmented Generation
CAG, an alternative to RAG
Remembers frequent AI requests
Speeds up responses, cost efficient
GitHub Education Student Developer Pack
Learn to ship software like a pro. There's no substitute for hands-on experience. But for most students, real world tools can be cost-prohibitive. That's why we created the GitHub Student Developer Pack with some of our partners and friends.
Microsoft Recruiters Early In Profession LinkedIn Group
Exclusive LinkedIn group run by Microsoft recruiters. This invite-only group isn't discoverable through search and is only accessible to those who receive the link directly.
Microsoft Learn
The hub to access training, credentials, documentation, community, and a variety of other resources to empower learners worldwide with in-demand skills.
My LinkedIn
Follow Up Resources
Check out my blog at segunak.com
AI & Your Tech Career
Companion Article
Thank You!
感謝
Dank u wel
谢谢
Grazie
Danke
Merci
Terima kasih
ありがとうございました
Kop khun ขอบคุณ
Tack
감사합니다
Obrigado
Teşekkür ederiz
Dziękuję
Gracias
Cám ơn
Questions?