AI Agents or Agentic Systems
Dall-E 2 generated image

AI Agents or Agentic Systems

In the new year 2025 we see everyone talking about “Agents” or Agent like systems called “Agentic Systems”.

I recently read a post with title “SaaS apps are dying, and Agents will take over”. This is just another clickbait, and I don’t agree to this. The Agents are not ready for this yet (as of Mar 2025), but this will change.

So, let’s describe Agents and the production readiness, in simple words.

What’s an AI Agent?

An AI agent is a system that perceives its environment, processes information, and takes actions to achieve specific goals autonomously or semi-autonomously. E.g.

1.??? My Personal Travel Agent to which if I give this chat command “Can you book me a 1 week vacation to Italy in Sep 2025”. This can invoke the AI Agent for these Tasks

a.??? Search best flight tickets in any week of Sep 2025

b.??? Search best hotel accommodation in days between flights

c.???? Find best places to visit and book its tickets

d.??? Send email to my work manager at work to approve the holiday, and wait for confirmation

e.??? And on confirmation book flights, hotel and places of interest after confirming with me in a chat (so it’s a semi-autonomous agent where I am the Human Reviewer). Note this involves Financial transactions which I have authorised this Agent to do

f.????? Block my work calendar and put out an out of office

g.??? Keep an eye on any flight / hotel changes, cancellation and update after confirming with me

h.??? Etc


2.??? My Software Engineer Agent which takes a chat like, “In the GitHub repository "TheBestCasuals - Retail for casual clothes” please replace current search feature with a new search feature which is based on latest Semantic Search technology using RAG and a Vector Db”, This can be another semi-autonomous Agent which will

a.??? Get the repository “TheBestCasuals - Retail for casual clothes”and understand the full code

b.??? Find current Fixed Search implementation

c.???? Replace this with the new logic of SemanticSearch by suggesting me the best LLM and Vector DB to use by writing all Dev and Test code

d.??? Write best Evaluation metrics

e.??? Creating all changes as multiple GitHub Pull Requests and send for my Review

f.??? After I review the Code is published to the QA Env

g.??? After I approve the Code is published to the Prod Env

?

What does an Agent comprise of?

Agents or Agentic Systems have an Agent Runtime which is the environment where an agent operates. It includes the Orchestration, Model, Tools, and Memory (short-term and long-term). It manages the execution of the agent, including how it takes in information, reasons about it, and uses tools to interact with the world.

Agent Runtime

1.??? Orchestration - a cyclical process that governs how the agent takes in information, performs some internal reasoning, and uses that reasoning to inform its next action or decision.

2.??? Model - centralised decision maker for agent processes like the latest reasoning based LLMs

3.??? Tools – access external data and services via Functions, Extensions, Data Stores and Plugins, Rest APIs etc.

4.??? Memory - Agents manage memory using two types: Short-term and Long-term.

a.??? Short-term memory: This is immediate and context-driven, like remembering the current stage of a conversation or the last tool used.

b.??? Long-term memory: This stores broader knowledge and learned patterns, similar to how a model's training data provides it with a foundation of understanding. Long-term memory enables an agent to draw on past experiences and apply them to new situations, enhancing its reasoning and decision-making.?


Image credit – Agents Google Whitepaper

?

Now the most important question :)

If Agents are so good what’s stopping us from using them for most day to day tasks?

As Chip Huyen explains in her talk there a “Curse of complexity”. As the no of steps in a Task increases the probability of failure increases exponentially.

https://www.youtube.com/watch?v=D6v5rlqUIc8&ab_channel=AIEngineer

?

The probability of failure of an AI Agent is directly proportional to the number of steps it involves

1.??? A relatively simple task using an AI Agent comprises of at least 5-10 steps. At the moment in Mar 2025, the LLM models can fail with a probability of approximately 2% for 1 step task, 18% for a 10 step task and 87% for a 100 step task.

2.??? So the probability of failure of a 10 step task which is about 18% is not an acceptable probability of failure for any production grade task. The above example of “My Personal Travel Agent” is more than 10 steps which means its probability of failure is more than 20%. And this Agent involves finances, booking tickets, booking hotels, so we are not ready yet.

?

The good news is LLMs are evolving:

1.??? LLMs are getting better at planning and reasoning,

2.???They can use reliable tools and

3.??? And they are getting much larger context window.

So, it’s a matter of time when Agents or Agentic Systems can be used for solving day to day production grade tasks which are slow and costly today…

?

Reference and acknowledgements:

1 - Agents Google Whitepaper by Julia Wiesinger, Patrick Marlow and Vladimir Vuskovic - https://www.kaggle.com/whitepaper-agents

?2 - Chip Huyen

https://www.youtube.com/watch?v=D6v5rlqUIc8&ab_channel=AIEngineer

https://huyenchip.com/2025/01/07/agents.html

?

- Mahtab Syed, 10 Mar 2025, Melbourne

?

Yanhong (Jessika) HU

PhD in Public Health | MD in Clinical Medicine | MPH in Public Health | Mixed qualitative and quantitative methods | RCT & Cohort

1 周

Well explained very insightful!

要查看或添加评论,请登录

Mahtab Syed的更多文章

  • Develop your career in AI in 2025

    Develop your career in AI in 2025

    The hype of AI, especially in 2023 and continuing in 2024 and now in 2025, has created a supply of various courses. And…

    1 条评论
  • Generative AI - Learnings 2023

    Generative AI - Learnings 2023

    This year 2023 has been the year of Generative AI using Large Language Models both closed source and open source. Like…

    2 条评论
  • On Emotional Intelligence

    On Emotional Intelligence

    From my old archives - published on Tue 02 Nov 2010 in https://mahtabsyed.blogspot.

    1 条评论
  • What is Data Governance? And why is it necessary especially now?

    What is Data Governance? And why is it necessary especially now?

    With the advent of Machine Learning and Artificial Intelligence for Predictions (Business metrics like Inventory…

  • Its end of year again… And I have no new year resolutions…

    Its end of year again… And I have no new year resolutions…

    Its 31 Dec 2022, an end of a year again… And I am quite happy and contented. ?? I have a clear vision of what I will do…

    3 条评论
  • Machine Learning Blog – 9

    Machine Learning Blog – 9

    Machine Learning using 3 ways - Full code vs. No Code vs.

    3 条评论
  • Winning with life which keeps throwing new challenges every day...

    Winning with life which keeps throwing new challenges every day...

    I had written this self care tip few months back which I thought its better to be published as an article..

    2 条评论
  • The Silence within

    The Silence within

    Its peak winter in Melbourne and early morning of Wed 29 May 2019, and so far it’s the coldest day this year. I am at…

  • This year 2021… was in the trenches of worries

    This year 2021… was in the trenches of worries

    This year 2021… was in the trenches of worries due to Covid lockdowns, number of daily cases, economic slowdown…

    1 条评论
  • Machine Learning Blog – 8

    Machine Learning Blog – 8

    Multi-Layer Stacking Ensemble and Optuna Hyperparameter Tuning In this blog I will illustrate and link to the code of a…

    1 条评论

社区洞察