mercredi 19 novembre 2025

Agentic AI: Agentic AI and the future of work (Episode 4)

Agentic AI will accelerate automation, not just of simple, repetitive tasks, but of many complex workflows that once felt untouchable. That reality is both unsettling and full of opportunity. The question that matters is not whether change will happen, but how we steer it so people and organizations thrive.

Accepting a new scale of automation

It’s helpful to be frank: autonomous agents will take on a huge volume of repetitive work and many complex tasks previously seen as uniquely human. Some professions will change dramatically, others may shrink or disappear. That’s a hard truth and a moment to plan rather than panic.

Social safety and the case for shared security

Given the scale of transformation, ideas once considered radical like a universal basic income or income smoothing mechanisms are worth serious discussion. These are the kinds of social tools that can buy time for reskilling and reduce the human cost of rapid disruption.

New jobs may emerge

History shows us that technological revolutions destroy some jobs and create others. Agentic AI will spawn new roles: agent designers, orchestration engineers, AI ethicists, interaction designers for human–agent teams, and jobs we can’t yet name. The net effect depends on how we train and transition talent.

Why humans still matter: Innovation, Values and Empathy

Even when we tweak model temperature to drive creativity, we remain inside the box operating with constraints of data, assumptions, and design choices. Humans are essential for going truly out of the box: imagining new problems, reframing goals, and ideating radical directions that machines cannot originate on their own.

Beyond ideation, humans carry a bedrock of values. Empathy, cultural understanding, and moral judgment are the lenses through which we sense evolving customer needs and design services that matter. Those human qualities are not optional; they are the glue that makes technological capability humane and useful.

On layoffs, short-term gains, and long-term regret

Some companies may see productivity gains and respond by massively cutting headcount. That path risks long-term damage. An employee augmented with AI can reach far greater productivity than a replaced workforce. Companies that retrain and re-deploy staff can expand what they serve new markets, new product lines, deeper customer relationships instead of shrinking capacity.

In short: firing people to save costs today can destroy the very capability you need to grow tomorrow.

Lean, reimagined

Consider the Lean analogy: when some organizations use Lean to continually cut costs and offshore work, they can hollow out capabilities. By contrast, companies that truly embraced Lean principles like many Japanese manufacturers, invested in people, training, and continuous improvement, enabling them to successfully expand and even bring production back to new markets.

Agentic AI offers a similar fork in the road. If you only use it to do the same work with fewer people, you might win short-term savings. If you train your teams to master agentic tools, you multiply what your people can achieve: more products, broader services, faster learning.

Uncertainty is real but so is judgment

No one knows the absolute long-term truth about superintelligence or the full scope of disruption. That uncertainty calls for humility, not paralysis. My conviction is simple: place your bet on human potential. Invest in reskilling, build strong governance, and keep humans central to design and oversight.

Practical steps for leaders

  • Train first: Upskill teams on agentic tools rather than shrinking headcount immediately.
  • Redesign roles: Move people into higher-value jobs that use empathy, judgment, and creativity.
  • Adopt guardrails: Implement permission layers, audit logs, and human-in-the-loop checks.
  • Measure growth, not just cost: Track new revenue opportunities, products launched, and markets entered.
  • Engage stakeholders: Work with unions, communities, and policymakers on transition plans.

A positive, human-centered vision

Agentic AI will change work profoundly. The future we get depends on choices we make today. I believe the best path is one where companies empower people training them, entrusting them with higher-value tasks, and using AI to amplify human creativity and care.

If we build that future thoughtfully, we won’t merely replace effort with automation. We will expand what humans can imagine and build moving out of the box together.


Coming next: Episode 5 will explores how AI agents talk to each other: coordination, negotiation, shared memory, and the foundations of multi-agent intelligence.

mardi 18 novembre 2025

Agentic AI: MCP Model Context Protocol, giving agents access to the real world (Episode 3)

Large Language Models are powerful thinkers, but they have a limitation: they cannot act on the world unless someone manually wires them to tools, apps, or data sources. The Model Context Protocol (MCP) changes that. It provides a universal, open standard that lets any AI model connect to tools safely, consistently, and without custom integrations.

If the LLM is the brain, MCP is the nervous system that links intelligence to real capabilities.

Why MCP matters ?

AI agents need more than reasoning, they need interaction. MCP enables exactly that:

  • Real-time tool use (APIs, databases, workflows, productivity apps)
  • Structured context shared among tools and agents
  • Safe autonomy through explicit permissions and transparent actions
  • Interoperability across ecosystems and providers

MCP creates a unified way for models to understand what tools can do, request actions, receive results, and continue reasoning in a loop.

MCP in simple terms

MCP defines how three components communicate:

  • The model —> thinks and decides
  • The client —> sets goals and instructions
  • The server —> exposes tools and actions

The flow is simple: the client exposes available tools → the model decides which action to take → the server executes → the model continues based on feedback. This creates a smooth "goal → action → feedback → adjustment" cycle.

MCP vs Traditional APIs, why MCP is different ?

MCP is often compared to APIs because both allow software to access functionality. But they operate very differently. Here’s a clear perspective:

1. APIs are built for software-to-software communication

APIs expect precise calls, strict schemas, and deterministic behavior. They work perfectly for apps, but not for LLMs that produce flexible, natural language instructions.

2. MCP is designed for model-to-tool interaction

Instead of requiring developers to adapt tools to each model provider, MCP standardizes:

  • How tools describe themselves (capabilities, inputs, outputs)
  • How models request actions (structured, validated)
  • How results are returned (safe and transparent)

3. APIs require instructions; MCP provides context

APIs demand exact calls. MCP prepares context ahead of time, allowing the LLM to reason with a full view of what tools exist and how they can be used.

4. MCP is multi-model, multi-agent, multi-platform

An MCP server works not just with one model, but with any LLM that understands the protocol, enabling:

  • agent-to-agent collaboration
  • shared memory and shared tools
  • consistent safety across platforms

In short: APIs are communication channels. MCP is an integration framework designed specifically for AI.

Benefits and real possibilities

With MCP, an AI agent can:

  • query databases and CRMs
  • edit documents or spreadsheets
  • run automations in Zapier or n8n
  • access files and knowledge bases
  • collaborate with other agents

This transforms the LLM from “a conversation partner” to “a capable actor” with tools, context, and awareness.

Risks and responsible use

Alongside the opportunities, MCP introduces new responsibilities:

  • Over-automation —> agents may take unintended actions
  • Data exposure —> tools may reveal sensitive information
  • Ambiguous intent —> misunderstood requests can trigger incorrect actions
  • Safety drift —> agents may chain actions in unpredictable ways

This is why MCP includes permission layers, tool declarations, structured validation, and human oversight mechanisms.

A new interaction layer for AI

MCP represents a shift from LLMs as isolated text generators to connected, tool-using agents. It is the bridge between intelligence and action, providing the structure needed to build safe, autonomous systems that can truly collaborate with humans.


Coming next: Episode 4 explores the future of work in the era of agentic AI.

Agentic AI: Understanding the types of "AI Agents" (Episode 2)

Artificial agents didn’t appear fully formed. They evolved slowly, iteratively, and sometimes unexpectedly much like the early stages of human reasoning. Today’s Agentic AI systems, capable of coordinating multiple specialized agents to pursue complex goals collaboratively, are the result of decades of refinement.

If Episode 1 traced the shift from prediction to generation and onward to automation and autonomy, this episode dives into the building blocks of autonomous behavior, the different types of AI agents that form the foundation of today’s intelligent systems.

Each agent type represents a distinct way of “thinking” about the world, from reacting instantly to planning strategically.

1. Simple reflex agents, intelligence as instant reaction

The most primitive form of artificial intelligence. Reflex agents operate like a thermostat: see something → react immediately. They have no memory, no context, and no anticipation. Fast and predictable, but limited when situations become ambiguous or complex.

Strength: Extremely fast and predictable. Limitation: Easily confused by complexity.

2. Model-based agents, when perception meets memory

Model-based agents maintain an internal representation of the world. They remember recent events, infer hidden state, and update their internal model as new data arrives. This ability to hold a model of the environment enables better handling of partially observable situations.

Strength: Can reason about partial observability. Limitation: Still fairly reactive with limited long-term planning.

3. Goal-based agents, intelligence gains direction

Goal-based agents act with purpose. Instead of merely reacting, they evaluate actions by whether those actions bring them closer to a defined objective. These agents can plan, sequence tasks, and weigh alternative paths before acting.

Strength: Capable of planning and sequencing. Limitation: Goals are externally defined and typically not self-generated.

4. Utility-based agents, choosing the best action

Where goal-based agents ask “will this achieve the goal?”, utility-based agents ask “how well will this achieve the goal?” Utility introduces trade-offs, preferences, and optimization into decision-making allowing agents to balance multiple criteria and pick the best outcome.

Strength: Nuanced decision-making and optimization. Limitation: Designing robust utility functions can be difficult.

5. Learning agents, systems that improve themselves

Learning agents adapt from experience. Instead of relying solely on rules or fixed models, they update their strategies based on feedback and outcomes. This learning capability is central to modern agentic architectures that refine behavior continuously.

Strength: Self-improving and versatile. Limitation: Can be hard to control and may amplify biases if not carefully governed.

6. Multi-agent systems, when intelligence becomes collective

The most powerful and complex form: multiple specialized agents collaborate, communicate, and coordinate. Modern Agentic AI often composes orchestrators, planners, memory systems, and role-specific agents that together solve tasks no single agent could handle alone.

Strength: Scales to complex, multi-step problems. Limitation: Coordination, safety, and emergent behaviors become central challenges.

A clear trajectory

When we zoom out, the evolutionary path becomes clear:

  • Simple reflex → react instantly
  • Model-based → maintain a state
  • Goal-based → pursue objectives
  • Utility-based → optimize trade-offs
  • Learning agents → improve from experience
  • Multi-agent systems → collaborate and orchestrate

What started as simple reaction loops has grown into coordinated, memory-driven, goal-oriented networks capable of planning, learning, and cooperating in ways that echo human organizations. This evolution explains why Agentic AI is more than automation: it’s the emergence of structured, collaborative, adaptive intelligence.


Coming next: Episode 3 will explore how AI agents communicate with external tools and systems through the Model Context Protocol (MCP), a powerful standard that enables truly autonomous, tool-driven intelligence.

vendredi 14 novembre 2025

Agentic AI: The game changer already transforming how we work (Episode 1)

Artificial Intelligence has gone through several revolutions, and the next one is happening now.

We’ve shifted from prediction, where algorithms forecast outcomes, to generation, where models create text, images, and code. Now, we’re entering the age of automation and autonomy, where intelligent systems can plan, act, and learn on their own.

That’s the promise and power of Agentic AI.

If predictive AI focused on insight and generative AI focused on creativity, then Agentic AI emphasizes decision-making and action. It’s no longer just a tool that answers; it’s a collaborator that thinks.

The brain behind the agent

At the heart of every Agentic AI system is a Large Language Model (LLM) that acts as the brain. It interprets goals, reasons about context, and organizes the next best actions.

Other components act as the senses and hands. They collect data, carry out actions, and send results back to the model. Together, they create a closed cognitive loop, giving AI agents a sense of situational awareness.

The Agentic flow: perception, reasoning, action, learning

Agentic AI works through a continuous and adaptive cycle:

  • Perception : sensing and analyzing data from the environment.
  • Reasoning : the LLM evaluates objectives, plans steps, and makes decisions.
  • Action : the agent carries out those plans using digital or physical tools.
  • Learning : the system observes outcomes, adjusts strategies, and improves.

This flow transforms static AI into a living, evolving system capable of managing complex, changing environments.

The ecosystem powering Agentic AI

Building and coordinating autonomous agents is now possible thanks to a fast-growing set of tools:

  • LangChain : connects LLMs to APIs, data sources, and logic blocks, allowing for context-aware reasoning and dynamic tool use.
  • LangGraph : builds on LangChain with a graph-based structure that organizes agentic workflows, enabling loops, branching logic, and multi-agent coordination.
  • Zapier : connects agents to thousands of real-world applications, including email, Slack, spreadsheets, and CRM systems.
  • n8n : an open-source option for secure and customizable automation flows, giving developers full transparency and control.

These platforms create the infrastructure that lets the LLM “brain” interact smartly with its environment, perceiving, reasoning, and acting in real time.

Why It’s a game changer

We are already seeing the effects across various industries:

  • Manufacturing : predictive agents identify and fix issues before they disrupt production.
  • E-commerce : autonomous recommender agents create tailored experiences on the fly.
  • Energy : exploration agents optimize drilling operations and resource use.

Benchmarks show a leap: agentic frameworks can raise model performance from around 67% to over 90% on complex reasoning tasks.

That’s not evolution; it’s transformation.

A new era of intelligent collaboration

As these systems gain autonomy, responsibility and governance become crucial. Agentic AI should not replace human intelligence but enhance it, creating a new partnership between humans and digital minds.

What’s next ?

This post marks the start of a detailed exploration into the world of Agentic AI. In upcoming articles, we’ll cover:

  • The different levels of reasoning that make agents truly intelligent from reflexive reactions to strategic thinking.
  • How agents communicate with tools through the Model Context Protocol (MCP).
  • How agents collaborate with one another.

Each layer will show how autonomy, communication, and learning combine to shape the next generation of intelligent systems.

So stay tuned; the era of Agentic AI is not on the way. It’s already here, changing how we create, decide, and act.

dimanche 19 octobre 2025

Pydantic: Your new data bodyguard

Picture this: you order a burger online. You’re expecting something juicy and delicious... but the delivery guy hands you a necktie instead 😵

Without Pydantic, that’s pretty much daily life for our Python functions. You expect an int, but you get a str that looks like a number or worse, None. The code crashes at runtime, and you waste hours debugging TypeErrors or, even worse, silent bugs.

Pydantic is the strict bodyguard standing at the door of your function, API, or data pipeline. It says:
“Show me what you’ve got. I’ll check it, convert it if I can, and hand it back in exactly the format you expect.”

Why is it so brilliant? A quick example says more than a thousand words (compatible with Pydantic v2):

In the attached example, Pydantic has:

  • Validated types, name is a string, score is a positive integer.
  • Parsed the string "1995-04-12" into a native Python date object automatically.
  • Guaranteed that your data is safe and matches your expectations. If score had been -10, it would’ve raised a clear, immediate error, saving you from a potential bug.

Why should every Pythonista know it?

  • 🕒 Time Saver: No more miles of if isinstance(...) checks. Validation becomes declarative.
  • Confidence: You can fully trust the shape and type of your data once it’s passed through the Pydantic gate.
  • 🌍 Universal Pivot: It’s everywhere, the standard for FastAPI, essential for configuration, data parsing, and beyond.

It’s not just a library, it’s a shift in mindset: declare your data shape, and let the machine handle the grunt work.

P.S. If you’re passionate about data quality and cleaning (because having a “bodyguard” is great, but preparing your data upstream is even better 😉), check out my course on #LinkedInLearning:
👉 https://lnkd.in/eXegxieF

Do you already use Pydantic? What’s your favorite feature or your best tip to get the most out of it?

#Python #Pydantic #Development #BestPractices #CodeQuality #FastAPI #DataEngineering #DataCleaning #DataQuality

From quotes of wisdom

From quotes of wisdom