20 practical guides

AI Agents and Automation Guides

Learn how to choose an agent workflow, connect tools and knowledge, keep people in control, and evaluate the complete system.

Why this topic

For operators, developers, and professionals automating multi-step work.

01
Agent foundations

Agents vs chatbots

Choose a conversational assistant or an action-taking agent by comparing task boundaries, tool access, risk, and oversight needs.

02
Agent mechanics

How tool calling works

Understand tool schemas, model requests, application execution, returned observations, and the controls around every AI tool call.

03
Workflow design

Reliable agent workflows

Turn a broad automation goal into bounded states, explicit tools, completion checks, recovery paths, and observable handoffs.

04
Knowledge systems

RAG from first principles

Build a clear mental model of indexing, retrieval, grounded generation, citations, and the separate checks each RAG stage needs.

05
Retrieval foundations

Embeddings and search

Learn how vectors support meaning-based retrieval, where similarity fails, and how to evaluate search against real information needs.

06
Retrieval infrastructure

Choosing a vector database

Compare vector storage options using retrieval needs, filters, operations, security, migration, and measured workload evidence.

07
Retrieval preparation

Chunking for retrieval

Divide documents into retrievable units that preserve meaning, provenance, permissions, and enough context to answer real questions.

08
State and personalization

Agent memory

Design short-term state and durable memory with purpose limits, provenance, user controls, retrieval rules, and deletion paths.

09
Agent governance

Human approval for agents

Place informed approval before consequential AI actions with clear previews, authority checks, expiration, and audit evidence.

10
Research automation

Source-tracked research agent

Design research automation that decomposes questions, records claim-level evidence, exposes gaps, and produces inspectable citations.

11
Inbox automation

Email triage agent

Classify incoming email, extract actionable facts, route uncertain cases, and keep sending or destructive actions under explicit control.

12
Team workflow automation

Meeting follow-up workflow

Convert transcripts into reviewable decisions and actions while preserving uncertainty, consent, source locations, and owner approval.

13
Data workflow automation

Spreadsheet analysis agent

Analyze workbook data with explicit scope, deterministic calculations, cell-level evidence, validation, and controlled write-back.

14
Service automation

Customer support agent

Ground support answers in approved policy and account data, constrain actions, route uncertainty, and evaluate real resolution quality.

15
Web task automation

Browser automation agent

Automate browser tasks with restricted sites, observable state, protected credentials, confirmation before side effects, and robust tests.

16
Agent integrations

MCP servers with assistants

Connect assistants to Model Context Protocol servers by defining trust boundaries, permissions, discovery, approval, and operational checks.

17
Agent security

Prompt injection defense

Reduce prompt injection risk with explicit trust boundaries, least-privilege tools, validated actions, isolated content, and adversarial tests.

18
Agent quality

Repeatable agent evaluations

Build repeatable agent evaluations that score decisions, tool use, safety, state changes, and outcomes across representative cases.

19
Agent operations

Monitoring agent failures

Observe agent outcomes, trajectories, costs, policy events, and recovery signals without collecting excessive sensitive data.

20
Agent architecture

Production agent architecture

Design production agent boundaries for orchestration, tools, state, knowledge, policy, evaluation, observability, and recovery.

Demand and scope reference: OpenAI agents guide. Official guidance for building agent workflows with current OpenAI platform capabilities.