AI Daddy › Agentic Systems
Agent Fundamentals · Agentic Systems
Agents are LLM-powered systems that move beyond "chat" into "autonomous problem solving." The definition has shifted from simple ReAct loops to Closed-Loop…
Agent Fundamentals
Agents are LLM-powered systems that move beyond "chat" into "autonomous problem solving." The definition has shifted from simple ReAct loops to Closed-Loop Reasoning Systems that use built-in "System 2" thinking (Claude Opus 4.7 extended thinking, GPT-5.5 reasoning, DeepSeek-R2, Gemini 3.1 Pro Deep Think).
Table of Contents
Modern agency is often described as:
Agent = Reasoning Model + Tool Use + Persistent Memory + Environment Feedback
Nuance: In 2023, agents were "wrappers" around chat models. Today, agents are increasingly Integrated. Frontier models (Claude Opus 4.7, GPT-5.5 with reasoning, DeepSeek-R2) have the "Thinking" process baked into pre-training, making the agent loop more stable and less prone to "stalling."
System 1 vs. System 2 Thinking
Architecting an agent requires choosing the right "Thinking Mode":
| Mode | Cognitive Type | Analogy | Current stack |
|---|
| System 1 | Fast, intuitive, reactive | Reflexes | Claude Haiku 4.5 / Sonnet 4.6 / GPT-5.5-mini / Gemini 3.1 Flash |
| System 2 | Slow, logical, planning | Deliberation | Claude Opus 4.7 / GPT-5.5 reasoning / DeepSeek-R2 / Gemini 3.1 Pro Deep Think |
The Design Pattern: Use System 1 models for "Fast UI" and "Routing." Use System 2 models for "Decision Gates" and "Complex Planning."
Agency Levels
Not every autonomous system is an "Agent." We categorize them by the Level of Agency:
- L0: Scripted Chains: Fixed sequence (e.g., standard LangChain).
- L1: Tool-Enabled: Model picks a tool but doesn't plan.
- L2: ReAct Agent: Simple loop of "Thought -> Action -> Observation."
- L3: Autonomous Planner: Decomposes a goal into a graph of sub-tasks.
- L4: Ambient Agent: Runs in the background, intervenes only when necessary.
Core Components
1. The Reasoning Model (The Executive)
The CPU of the agent. It determines the "Path to Success."
Interfaces (APIs, Browsers, DBs) that allow the agent to affect the world.
NOTE
The Model Context Protocol (MCP) is now the industry standard for tool interoperability, with adoption from Anthropic, OpenAI, Google, Microsoft, and AWS. Governance moved to the Linux Foundation's Agentic AI Foundation in December 2025.
3. Memory (The Experience)
- Short-term: Context window (KV Cache).
- Long-term: Vector DBs or persistent state (e.g., Mem0).
The Agent Lifecycle
- Intake: Receive user goal.
- Decomposition: Break goal into sub-steps.
- Execution: Call tools and handle results.
- Reflection: Evaluate if the observation got the agent closer to the goal.
- Completion: Synthesize final proof for the user.
Interview Questions
Q: Why is a "Reasoning Model" (like Claude Opus 4.7 or GPT-5.5 with extended thinking) better for agency than a standard LLM?
Strong answer:
Standard LLMs (System 1) predict the very next token based on pattern matching. When they encounter an error in a tool call, they often hallucinate a fix instead of admitting the failure. Reasoning Models use Chain-of-Thought (CoT) during inference. They "think" through multiple hidden turns before outputting a response. For an agent, this means higher Path Reliability—the model is significantly less likely to enter an infinite loop or try the same failing action twice because it has already simulated the failure internally.
Q: How do you prevent "Agentic Drift" in long-running tasks?
Strong answer:
Agentic Drift occurs when the sub-steps take the agent so far from the original goal that it loses context. The standard solution is Goal Anchoring: include the "Original Objective" as a pinned system message and use a Secondary Observer Model (a smaller, cheaper model) to score every agent action against the original objective. If the score drops below a threshold, the agent is forced to "re-plan" from the root.
References
- Kahneman, D. "Thinking, Fast and Slow" (applied to AI, 2025)
- OpenAI. "Learning to Reason with LLMs" (2024)
- DeepSeek. "R1: Cold-Start Data for Reasoning" (2025)
Next: Reasoning Loops: ReAct and Beyond