Vivid Sydney · Builder's Field Guide 2026 Edition

How AI Agents
Are Built

The five components behind every production agent, the two key architectures, and the IRL stack teams ship in 2026.

Vivid Savitri-Hampton

AChatbot vs Agent

A chatbot waits for input and replies. An agent is given a goal.

  • Decides its own next action with an LLM, step by step
  • Plans multi-step work and self-corrects mid-run
  • Calls tools, reads memory, acts on external systems
→The test: remove the human. If work still moves forward, it's an agent.

BTwo Architectures

Single agent: one model, many tools. It's an OK stack for most v1 builds.

→Manager pattern: one agent decomposes the goal, delegates to specialists
→Peer network: agents coordinate directly, no top-down control
→Go multi-agent only when tasks demand parallelism or deep specialisation.

Five Components of Every Agent

MODEL → MEMORY → TOOLS → INSTRUCTIONS → ORCHESTRATION
01
Model
The reasoning core

Picks the next action, plans the sequence, recovers from its own errors. Optimise for task accuracy first, then cost and latency.

GPT-5.6 Claude Fable 5 GLM-5.3 Qwen-3.8 Max Kimi-K3
02
Memory
State that survives the session

Short-term: the context of the current run. Long-term: user preferences and past decisions, usually in a vector store.

Qdrant Milvus MongoDB Atlas Redis
03
Tools
Hands on the real world

APIs, databases, email, CRMs. A model without tools can only talk about the work. Tools let it do the work.

Zapier Make n8n Hugging Face
04
Instructions
The operating contract

Your SOPs rewritten as prompts: tight scope, explicit edge cases, defined fallback paths for every failure mode.

system prompts few-shot examples fallback paths
05
Orchestration
The conductor

Wires model, memory and tools into one loop. Routes work between agents when the system grows past one.

LangChain LangGraph CrewAI AutoGen

CGuardrails

Boundaries are a feature, not a constraint.

  • Privacy: sensitive data never leaves approved paths
  • Content safety: block harmful or off-policy output
  • Dynamic rules: permissions adapt to user role and task risk
Azure AI Content Safety Guardrails AI

DHuman in the Loop

Autonomy is earned, never assumed.

  • Error thresholds: repeated failures escalate to a person
  • High-stakes gates: refunds, deletions, payments need sign-off
  • Full traces: log every step so failures are auditable
LangSmith Weights & Biases

The 2026 Agent Stack

PURPOSE → TOOLS
Frontier models
GPT-5.6 Claude Fable 5 GLM 5.3 Qwen-3.8 Max Kimi-K3
Vector memory
Qdrant Milvus MongoDB Atlas Redis
Orchestration
LangChain LangGraph CrewAI AutoGen
Integration & actions
n8n Hugging Face Zappier Make
Guardrails
Azure AI Content Safety Guardrails AI
Observability
LangSmith Arise Phoenix Weights & Biases