Digital Library

Introduction to Agents (Alan Blount, Antonio Gulli, Shubham Saboo etc.)(Z-Library)

,
,
,
,

Share E-Book

Introduction to Agents (Alan Blount, Antonio Gulli, Shubham Saboo etc.)(Z-Library)

Author

,
,
,
,

Rating 3.5 AI initial rating

Log in to rate

C
Language English

This document is the first in a five-part series, acting as a formal guide for the developers, architects, and product leaders transitioning from proofs-of-concept to robust, production-grade agentic systems. While building a simple prototype is straightforward, ensuring security, quality and reliability is a significant challenge. This paper provides a comprehensive foundation: • Core Anatomy: Deconstructing an agent into its three essential components: the reasoning Model, actionable Tools, and the governing Orchestration Layer. • A Taxonomy of Capabilities: Classifying agents from simple, connected problem-solvers to complex, collaborative multi-agent systems. • Architectural Design: Diving into the practical design considerations for each component, from model selection to tool implementation. • Building for Production: Establishing the Agent Ops discipline needed to evaluate, debug, secure, and scale agentic systems from a single instance to a fleet with enterprise governance.

Format PDF
Size 9.0 MB
(First 20 pages)

Registered users can read the full content for free

Register as a Gaohf Library member to read the complete e-book online for free and enjoy a better reading experience.

Page 1
Introduction to Agents Authors: Alan Blount, Antonio Gulli, Shubham Saboo, Michael Zimmermann, and Vladimir Vuskovic
Page 2
Introduction to Agents and Agent architectures November 2025 2 Acknowledgements Content contributors Enrique Chan Mike Clark Derek Egan Anant Nawalgaria Kanchana Patlolla Julia Wiesinger Curators and editors Anant Nawalgaria Kanchana Patlolla Designer Michael Lanning
Page 3
From Predictive AI to Autonomous Agents 6 Introduction to AI Agents 8 The Agentic Problem-Solving Process 10 A Taxonomy of Agentic Systems 14 Level 0: The Core Reasoning System 15 Level 1: The Connected Problem-Solver 15 Level 2: The Strategic Problem-Solver 16 Level 3: The Collaborative Multi-Agent System 17 Level 4: The Self-Evolving System 18 Core Agent Architecture: Model, Tools, and Orchestration 19 Model: The “Brain” of your AI Agent 19 Tools: The "Hands" of your AI Agent 20 Retrieving Information: Grounding in Reality 21 Executing Actions: Changing the World 21 Function Calling: Connecting Tools to your Agent 22 Table of contents
Page 4
The Orchestration Layer 22 Core Design Choices 23 Instruct with Domain Knowledge and Persona 23 Augment with Context 24 Multi-Agent Systems and Design Patterns 24 Agent Deployment and Services 26 Agent Ops: A Structured Approach to the Unpredictable 27 Measure What Matters: Instrumenting Success Like an A/B Experiment 29 Quality Instead of Pass/Fail: Using a LM Judge 29 Metrics-Driven Development: Your Go/No-Go for Deployment 30 Debug with OpenTelemetry Traces: Answering "Why?" 30 Cherish Human Feedback: Guiding Your Automation 31 Agent Interoperability 31 Agents and Humans 32 Agents and Agents 33 Agents and Money 34 Table of contents
Page 5
Securing a Single Agent: The Trust Trade-Off 34 Agent Identity: A New Class of Principal 35 Policies to Constrain Access 37 Securing an ADK Agent 37 Scaling Up from a Single Agent to an Enterprise Fleet 39 Security and Privacy: Hardening the Agentic Frontier 40 Agent Governance: A Control Plane instead of Sprawl 40 How agents evolve and learn 42 How agents learn and self evolve 43 Simulation and Agent Gym - the next frontier 46 Examples of advanced agents 47 Google Co-Scientist 47 AlphaEvolve Agent 49 Conclusion 51 Endnotes 52 Table of contents
Page 6
Introduction to Agents and Agent architectures November 2025 6 From Predictive AI to Autonomous Agents Artificial intelligence is changing. For years, the focus has been on models that excel at passive, discrete tasks: answering a question, translating text, or generating an image from a prompt. This paradigm, while powerful, requires constant human direction for every step. We're now seeing a paradigm shift, moving from AI that just predicts or creates content to a new class of software capable of autonomous problem-solving and task execution. This new frontier is built around AI agents. An agent is not simply an AI model in a static workflow; it's a complete application, making plans and taking actions to achieve goals. It combines a Language Model's (LM) ability to reason with the practical ability to act, allowing Agents are the natural evolution of Language Models, made useful in software.
Page 7
Introduction to Agents and Agent architectures November 2025 7 it to handle complex, multi-step tasks that a model alone cannot. The critical capability is that agents can work on their own, figuring out the next steps needed to reach a goal without a person guiding them at every turn. This document is the first in a five-part series, acting as a formal guide for the developers, architects, and product leaders transitioning from proofs-of-concept to robust, production-grade agentic systems. While building a simple prototype is straightforward, ensuring security, quality and reliability is a significant challenge. This paper provides a comprehensive foundation: • Core Anatomy: Deconstructing an agent into its three essential components: the reasoning Model, actionable Tools, and the governing Orchestration Layer. • A Taxonomy of Capabilities: Classifying agents from simple, connected problem-solvers to complex, collaborative multi-agent systems. • Architectural Design: Diving into the practical design considerations for each component, from model selection to tool implementation. • Building for Production: Establishing the Agent Ops discipline needed to evaluate, debug, secure, and scale agentic systems from a single instance to a fleet with enterprise governance. Building on the previous Agents whitepaper1 and Agent Companion2; this guide provides the foundational concepts and strategic frameworks you will need to successfully build, deploy, and manage this new generation of intelligent applications which can reason, act and observe to accomplish goals3.
Page 8
Introduction to Agents and Agent architectures November 2025 8 Words are insufficient to describe how humans interact with AI. We tend to anthropomorphize and use human terms like “think” and “reason” and “know.” We don't yet have words for "know with semantic meaning" vs "know with high probability of maximizing a reward function." Those are two different types of knowing, but the results are the same 99.X% of the time. Introduction to AI Agents In the simplest terms, an AI Agent can be defined as the combination of models, tools, an orchestration layer, and runtime services which uses the LM in a loop to accomplish a goal. These four elements form the essential architecture of any autonomous system. • The Model (The "Brain"): The core language model (LM) or foundation model that serves as the agent's central reasoning engine to process information, evaluate options, and make decisions. The type of model (general-purpose, fine-tuned, or multimodal) dictates the agent's cognitive capabilities. An agentic system is the ultimate curator of the input context window the LM. • Tools (The "Hands"): These mechanisms connect the agent's reasoning to the outside world, enabling actions beyond text generation. They include API extensions, code functions, and data stores (like databases or vector stores) for accessing real-time, factual information. An agentic system allows a LM to plan which tools to use, executes the tool, and puts the tool results into the input context window of the next LM call. • The Orchestration Layer (The "Nervous System"): The governing process that manages the agent's operational loop. It handles planning, memory (state), and reasoning strategy execution. This layer uses prompting frameworks and reasoning techniques (like
Page 9
Introduction to Agents and Agent architectures November 2025 9 Chain-of-Thought4 or ReAct5) to break down complex goals into steps and decide when to think versus use a tool. This layer is also responsible for giving agents the memory to "remember." • Deployment (The "Body and Legs"): While building an agent on a laptop is effective for prototyping, production deployment is what makes it a reliable and accessible service. This involves hosting the agent on a secure, scalable server and integrating it with essential production services for monitoring, logging, and management. Once deployed, the agent can be accessed by users through a graphical interface or programmatically by other agents via an Agent-to-Agent (A2A) API. At the end of the day, building a generative AI agent is a new way to develop solutions to solve tasks. The traditional developer acts as a "bricklayer," precisely defining every logical step. The agent developer, in contrast, is more like a director. Instead of writing explicit code for every action, you set the scene (the guiding instructions and prompts), select the cast (the tools and APIs), and provide the necessary context (the data). The primary task becomes guiding this autonomous "actor" to deliver the intended performance. You'll quickly find that an LM's greatest strength—its incredible flexibility—is also your biggest headache. A large language model's capacity to do anything makes it difficult to compel it to do one specific thing reliably and perfectly. What we used to call “prompt engineering” and now call “context engineering” guides LMs to generate the desired output. For any single call to a LM, we input our instructions, facts, available tools to call, examples, session history, user profile, etc – filling the context window with just the right information to get the outputs we need. Agents are software which manage the inputs of LMs to get work done. Debugging becomes essential when issues arise. "Agent Ops" essentially redefines the familiar cycle of measurement, analysis, and system optimization. Through traces and logs, you can monitor the agent's "thought process" to identify deviations from the intended execution path. As models evolve and frameworks improve, the developer's role is to furnish
Page 10
Introduction to Agents and Agent architectures November 2025 10 critical components: domain expertise, a defined personality, and seamless integration with the tools necessary for practical task completion. It's crucial to remember that comprehensive evaluations and assessments often outweigh the initial prompt's influence. When an agent is precisely configured with clear instructions, reliable tools, and an integrated context serving as memory, a great user interface, the ability to plan and problem solve, and general world knowledge, it transcends the notion of mere "workflow automation." It begins to function as a collaborative entity: a highly efficient, uniquely adaptable, and remarkably capable new member of your team. In essence, an agent is a system dedicated to the art of context window curation. It is a relentless loop of assembling context, prompting the model, observing the result, and then re-assembling a context for the next step. The context may include system instructions, user input, session history, long term memories, grounding knowledge from authoritative sources, what tools could be used, and the results of tools already invoked. This sophisticated management of the model's attention allows its reasoning capabilities to problem solve for novel circumstances and accomplish objectives. The Agentic Problem-Solving Process We have defined an AI agent as a complete, goal-oriented application that integrates a reasoning model, actionable tools, and a governing orchestration layer. A short version is “LMs in a loop with tools to accomplish an objective.” But how does this system actually work? What does an agent do from the moment it receives a request to the moment it delivers a result?
Page 11
Introduction to Agents and Agent architectures November 2025 11 At its core, an agent operates on a continuous, cyclical process to achieve its objectives. While this loop can become highly complex, it can be broken down into five fundamental steps as discussed in detail in the book Agentic System Design:6 1. Get the Mission: The process is initiated by a specific, high-level goal. This mission is provided by a user (e.g., "Organize my team's travel for the upcoming conference") or an automated trigger (e.g., "A new high-priority customer ticket has arrived"). 2. Scan the Scene: The agent perceives its environment to gather context. This involves the orchestration layer accessing its available resources: "What does the user's request say?", "What information is in my term memory? Did I already try to do this task? Did the user give me guidance last week?", "What can I access from my tools, like calendars, databases, or APIs?" 3. Think It Through: This is the agent's core "think" loop, driven by the reasoning model. The agent analyzes the Mission (Step 1) against the Scene (Step 2) and devises a plan. This isn't a single thought, but often a chain of reasoning: "To book travel, I first need to know who is on the team. I will use the get_team_roster tool. Then I will need to check their availability via the calendar_api." 4. Take Action: The orchestration layer executes the first concrete step of the plan. It selects and invokes the appropriate tool—calling an API, running a code function, or querying a database. This is the agent acting on the world beyond its own internal reasoning. 5. Observe and Iterate: The agent observes the outcome of its action. The get_ team_roster tool returns a list of five names. This new information is added to the agent's context or "memory." The loop then repeats, returning to Step 3: "Now that I have the roster, my next step is to check the calendar for these five people. I will use the calendar_api."
Page 12
Introduction to Agents and Agent architectures November 2025 12 This "Think, Act, Observe" cycle continues - managed by the Orchestration Layer, reasoned by the Model, and executed by the Tools until the agent's internal plan is complete and the initial Mission is achieved. Figure 1: Agentic AI problem-solving process Let’s take a real-world example of how a Customer Support Agent would operate in this 5-step cycle: Imagine a user asks, "Where is my order #12345?"
Page 13
Introduction to Agents and Agent architectures November 2025 13 Instead of immediately acting, the agent first enters its "Think It Through" phase to devise a complete strategy. It reasons: "The user wants a delivery status. To provide a complete answer, I need a multi-step plan: 1. Identify: I must first find the order in our internal database to confirm it exists and get its details. 2. Track: From those details, I'll need to extract the shipping carrier's tracking number. Then, I'll query the external carrier's API for the live status. 3. Report: Finally, I must synthesize the information I've gathered into a clear, helpful response for the user." With this multi-step plan in mind, the agent begins execution. In its first "Act" phase, it executes step one of its plan, calling the find_order("12345") tool. It observes the result—a full order record, including the tracking number "ZYX987." The agent's orchestration layer recognizes that the first part of its plan is complete and immediately proceeds to the second. It acts by calling the get_shipping_ status("ZYX987") tool. It observes the new result: "Out for Delivery." Finally, having successfully executed the data-gathering stages of its plan, the agent moves to the "Report" step. It perceives it has all the necessary components, plans the final message, and acts by generating the response: "Your order #12345 is 'Out for Delivery'!
Page 14
Introduction to Agents and Agent architectures November 2025 14 A Taxonomy of Agentic Systems Understanding the 5-step operational loop is the first part of the puzzle. The second is recognizing that this loop can be scaled in complexity to create different classes of agents. For an architect or product leader, a key initial decision is scoping what kind of agent to build. We can classify agentic systems into a few broad levels, each building on the capabilities of the last. Figure 2: Agentic system in 5 steps
Page 15
Introduction to Agents and Agent architectures November 2025 15 Level 0: The Core Reasoning System Before we can have an agent, we must start with the "Brain" in its most basic form: the reasoning engine itself. In this configuration, a Language Model (LM) operates in isolation, responding solely based on its vast pre-trained knowledge without any tools, memory, or interaction with the live environment. Its strength lies in this extensive training, allowing it to explain established concepts and plan how to approach solving a problem with great depth. The trade-off is a complete lack of real- time awareness; it is functionally "blind" to any event or fact outside its training data. For instance, it can explain the rules of professional baseball and the complete history of the New York Yankees. But if you ask, "What was the final score of the Yankees game last night?", it would be unable to answer. That game is a specific, real-world event that happened after its training data was collected, so the information simply doesn't exist in its knowledge. Level 1: The Connected Problem-Solver At this level, the reasoning engine becomes a functional agent by connecting to and utilizing external tools - the "Hands" component of our architecture. Its problem-solving is no longer confined to its static, pre-trained knowledge. Using the 5-step loop, the agent can now answer our previous question. Given the "Mission": "What was the final score of the Yankees game last night?", its "Think" step recognizes this as a real-time data need. Its "Act" step then invokes a tool, like a Google Search API with the proper date and search terms. It "Observes" the search result (e.g., "Yankees won 5-3"), and synthesizes that fact into a final answer.
Page 16
Introduction to Agents and Agent architectures November 2025 16 This fundamental ability to interact with the world - whether using a search tool for a score , a financial API for a live stock price, or a database via Retrieval-Augmented Generation (RAG) is the core capability of a Level 1 agent. Level 2: The Strategic Problem-Solver Level 2 marks a significant expansion in capability, moving from executing simple tasks to strategically planning complex, multi-part goals. The key skill that emerges here is context engineering: the agent's ability to actively select, package, and manage the most relevant information for each step of its plan. An agent's accuracy depends on a focused, high-quality context. Context engineering curates the model's limited attention to prevent overload and ensure efficient performance. For instance, consider the "Mission": "Find a good coffee shop halfway between my office at 1600 Amphitheatre Parkway, Mountain View, and my client's office at 1 Market St, San Francisco." A Level 2 agent will start creating a plan: 1. Think: "I must first find the halfway point." • Act: Call the Maps tool with both addresses. • Observe: "The halfway point is Millbrae, CA." 2. Think: "Now I must find coffee shops in Millbrae. The user asked for 'good' ones, so I will search for places with a 4-star rating or higher."
Page 17
Introduction to Agents and Agent architectures November 2025 17 • Act: Call the google_places tool with query="coffee shop in Millbrae, CA", min_rating=4.0. (This is context engineering - it automatically created a new, focused search query from the previous step's output ). • Observe: "The search returns 'Millbrae Coffee' and 'The Daily Grind'." 3. Think: "I will synthesize these results and present them to the user." This strategic planning also enables proactive assistance, like an agent that reads a long flight confirmation email, engineers the key context (flight number, date), and acts by adding it to your calendar. Level 3: The Collaborative Multi-Agent System At the highest level, the paradigm shifts entirely. We move away from building a single, all- powerful "super-agent" and toward a "team of specialists" working in concert, a model that directly mirrors a human organization. The system's collective strength lies in this division of labor. Here, agents treat other agents as tools. Imagine a "Project Manager" agent receiving a "Mission": "Launch our new 'Solaris' headphones." The Project Manager agent doesn't do the entire work itself. It Acts by creating new Missions for its team of specialized agents much like how it works in the real life: 1. Delegates to MarketResearchAgent: "Analyze competitor pricing for noise-canceling headphones. Return a summary document by tomorrow." 2. Delegates to MarketingAgent: "Draft three versions of a press release using the 'Solaris' product spec sheet as context."
Page 18
Introduction to Agents and Agent architectures November 2025 18 3. Delegates to WebDevAgent: "Generate the new product page HTML based on the attached design mockups." This collaborative model, while currently constrained by the reasoning limitations of today's LMs, represents the frontier of automating entire, complex business workflows from start to finish. Level 4: The Self-Evolving System Level 4 represents a profound leap from delegation to autonomous creation and adaptation. At this level, an agentic system can identify gaps in its own capabilities and dynamically create new tools or even new agents to fill them. It moves from using a fixed set of resources to actively expanding them. Following our example, the "Project Manager" agent, tasked with the 'Solaris' launch, might realize it needs to monitor social media sentiment, but no such tool or agent exists on its team. 1. Think (Meta-Reasoning): "I must track social media buzz for 'Solaris,' but I lack the capability." 2. Act (Autonomous Creation): Instead of failing, it invokes a high-level AgentCreator tool with a new mission: "Build a new agent that monitors social media for keywords 'Solaris headphones', performs sentiment analysis, and reports a daily summary." 3. Observe: A new, specialized SentimentAnalysisAgent is created, tested, and added to the team on the fly, ready to contribute to the original mission. This level of autonomy, where a system can dynamically expand its own capabilities, turns a team of agents into a truly learning and evolving organization.
Page 19
Introduction to Agents and Agent architectures November 2025 19 Core Agent Architecture: Model, Tools, and Orchestration We know what an agent does and how it can scale. But how do we actually build it? The transition from concept to code lies in the specific architectural design of its three core components. Model: The “Brain” of your AI Agent The LM is the reasoning core of your agent, and its selection is a critical architectural decision that dictates your agent's cognitive capabilities, operational cost, and speed. However, treating this choice as a simple matter of picking the model with the highest benchmark score is a common path to failure. An agent's success in a production environment is rarely determined by generic academic benchmarks. Real-world success demands a model that excels at agentic fundamentals: superior reasoning to navigate complex, multi-step problems and reliable tool use to interact with the world7. To do this well, start by defining the business problem, then test models against metrics that directly map to that outcome. If your agent needs to write code, test it on your private codebase. If it processes insurance claims, evaluate its ability to extract information from your specific document formats. This analysis must then be cross-referenced with the practicalities of cost and latency. The "best" model is the one that sits at the optimal intersection of quality, speed, and price for your specific task8.
Page 20
Introduction to Agents and Agent architectures November 2025 20 You may choose more than one model, a "team of specialists." You don't use a sledgehammer to crack a nut. A robust agent architecture might use a frontier model like Gemini 2.5 Pro for the heavy lifting of initial planning and complex reasoning, but then intelligently route simpler, high-volume tasks—like classifying user intent or summarizing text—to a much faster and more cost-effective model like Gemini 2.5 Flash. Model routing might be automatic or hard- coded but is a key strategy for optimizing both performance and cost9. The same principle applies to handling diverse data types. While a natively multimodal model like Gemini live mode10 offers a streamlined path to processing images and audio, an alternative is to use specialized tools like the Cloud Vision API11 or Speech-to-Text API12. In this pattern, the world is first converted to text, which is then passed to a language-only model for reasoning. This adds flexibility and allows for best-of-breed components, but also introduces significant complexity. Finally, the AI landscape is in a state of constant, rapid evolution. The model you choose today will be superseded in six months. A "set it and forget it" mindset is unsustainable. Building for this reality means investing in a nimble operational framework—an "Agent Ops" practice13. With a robust CI/CD pipeline that continuously evaluates new models against your key business metrics, you can de-risk and accelerate upgrades, ensuring your agent is always powered by the best brain available without requiring a complete architectural overhaul. Tools: The "Hands" of your AI Agent If the model is the agent's brain, tools are the hands that connect its reasoning to reality. They allow the agent to move beyond its static training data to retrieve real-time information and take action in the world. A robust tool interface is a three-part loop: defining what a tool can do, invoking it, and observing the result.
The above is a preview of the first 20 pages. Register to read the complete e-book.

Recommended for You

Loading recommended books...
Failed to load, please try again later

Tip the Site

Scan the WeChat Pay or Alipay code to tip. No login required.

WeChat Pay
Alipay
← Back to List