Skip to content

Command Palette

Search for a command to run...

AI for Everyone

AI for Everyone: Practical Guides, Prompts and Workflows

Learn to use AI assistants, automations and agents at work and at home, without needing to code. The guides are practical, cautious about claims, and clear about when a human must decide.

Last reviewed . AI products change quickly; check the linked sources before relying on details.

What you can aim for

Save time

Draft, summarise, plan and sort routine work faster. Typical wins are email digests, meeting follow-ups and first drafts. Time saved depends on your tasks, and you still review the output.

Business and financial outcomes

Use AI to prepare research, explain your own reports and draft customer communications. There are no guaranteed returns, and nothing here is financial, legal or tax advice. Verify numbers and talk to a qualified professional before decisions that carry money risk.

Everyday life

Meal plans, household admin, learning and travel planning. AI is not a substitute for medical professionals. For health questions, use it to prepare questions for your doctor, not to diagnose or choose treatment.

Build practical workflows

Turn a prompt you trust into a repeatable workflow with a trigger, limited permissions and a human approval step, using tools such as n8n, Make or Zapier.

Assistant, workflow or agent?

Three terms are often mixed up. The difference matters for cost, risk and how much you need to supervise.

  • Assistant. You ask, it answers. Nothing happens until you type, and you decide what to do with the answer. Examples: a chat window in ChatGPT, Claude or Gemini.
  • Reusable workflow. A fixed sequence of steps that runs when something triggers it, such as a schedule or a new email. One or more steps may call an AI model. The path is decided by you, not by the model.
  • Agent. The model decides which steps and tools to use to reach a goal. It is more flexible and less predictable. Some agent products run on a schedule or in the background, but whether one runs continuously depends on the product and your plan.
Assistant, workflow or agent: who decides the stepsThree columns. With an assistant, you decide every step. With a workflow, fixed steps you set up run on a trigger with an AI step inside. With an agent, the AI chooses the steps and tools and repeats. A human approval gate sits under all three before anything is sent, posted, bought or deleted.AssistantYou decide every stepYou askAI answersYou act on itWorkflowFixed steps you set upTriggerAI step (summarise)Fixed next stepsAgentThe AI picks the stepsGoal you setAI chooses stepsUses tools, repeatsHuman approval before anything is sent, posted, bought or deleted
The more the AI decides, the more flexible and the less predictable it gets, so the approval gate matters more.
Key takeaway

Start with an assistant, move to a workflow when you repeat the same task, and consider an agent only when the steps genuinely cannot be written down in advance.

Where to start

Start Here

A seven-day path from first prompts to a recurring workflow.

Compare AI Models

How to choose between assistant families, and how to check what is current.

Find the right AI

Match a task to the type of tool that suits it.

Prompt Library

Copy-ready prompts with a universal template and verification notes.

AI Agents

Assistants, workflows and agents explained, with platform comparison and safe setup.

Open-source AI

Running models and tools on your own machine, with licence caveats.

Business use cases

Prospect research, outreach drafts and plain-English reports.

Personal productivity

Planning, meeting notes and task management prompts.

BioTech

Literature, regulatory, business and lab-operations guidance with expert review built in.

Personal AI agents

Always-on assistants and social bots: what exists, limits and risks.

For engineers

If you build AI systems rather than use them, the same topics are covered in more depth in the Agent Stack and the agentic AI engineering course.

Ground rules used across these pages

  • Verify facts against primary sources. Models can be fluent and wrong.
  • Keep sensitive data out of tools you have not checked, including health records, identity documents and financial accounts.
  • Give automations the least access they need, and keep a person in the loop before anything is sent, posted, bought or deleted.
  • Time-sensitive statements carry a date and sources. Check them again before relying on them.

Frequently asked questions

What is the difference between an AI assistant, a workflow and an agent?

An assistant answers when you ask, and you decide what to do with the answer. A workflow is a fixed sequence of steps that runs when something triggers it, and one step may call an AI model. An agent chooses its own steps and tools to reach a goal, so it is more flexible and less predictable.

Do I need to know how to code to use AI at work?

No. The guides are written for using AI assistants, automations and agents at work and at home without coding. They are practical, cautious about claims and clear about when a person must decide. If you do build AI systems, the site points to the Agent Stack and the agentic AI engineering course for more depth.

Should I start with an AI agent or a simple assistant?

Start with an assistant. Move to a workflow when you repeat the same task, and consider an agent only when the steps genuinely cannot be written down in advance. Agents add flexibility but are less predictable and need more supervision, so they are the last step rather than the first.

Is it safe to use AI for health or money questions?

Use it with care. AI is not a substitute for medical professionals, so use it to prepare questions for your doctor rather than to diagnose or choose treatment. For money, there are no guaranteed returns and nothing here is financial, legal or tax advice. Verify numbers and talk to a qualified professional before decisions that carry risk.

What are the basic safety rules for using AI at work?

Verify facts against primary sources, because models can be fluent and wrong. Keep sensitive data such as health records, identity documents and financial accounts out of tools you have not checked. Give automations the least access they need, and keep a person in the loop before anything is sent, posted, bought or deleted.

Where to go next