Hi, I'm Linda. I went from "what's ChatGPT?" to building AI agents for my business. This is where I share everything I learn — clearly, practically, and without the jargon.
I started learning about AI agents because I wanted to save time in my business. What I found was confusing, technical, and full of hype. So I created the guide I wished existed — practical, honest, and built for real people.
Everything here comes from real experimentation. What works, what doesn't, and exactly how to get started — without a tech background.
Every topic links to real tools and step-by-step guides.
No jargon. If I didn't understand it at first, I explain it differently.
AI moves fast. This site evolves with it every week.
Everything tested on a real business, not just theory.
From managing your inbox to automating entire workflows — click any use case to go deep.
Triage, draft, and schedule — automatically.
Turn any topic into a structured, sourced report.
Answer questions and resolve issues 24/7.
One brief → a full week of content, in your voice.
Describe what you need. The agent builds it.
Connect your tools. Let agents do the rest.
A step-by-step account of setting up an email triage agent using n8n and Claude — and what I learned along the way.
The clearest explanation I could write of why agents are a step-change, not just an upgrade.
Five automations I actually use every week — with templates you can steal.
Everything you need to understand, try, and build each one — with real tools, steps, and prompts.
Stop drowning in your inbox. An agent reads, prioritises, drafts replies, and books meetings — you just approve before anything sends.
Authenticate your email. Set trigger: "New email received."
Send subject + body. Ask: "Is this Urgent / Reply needed / FYI / Junk?"
Urgent → priority list. Reply needed → draft. Junk → archive.
Pass email + your tone context to Claude. Save as Gmail draft.
Use Calendly or Google Calendar API to check availability and suggest meeting slots.
"Read this email and classify it as [URGENT], [REPLY_NEEDED], [FYI], or [JUNK]. State why in one sentence. Email: {{email_body}}"
Give it a question. Get back a structured, sourced report — in minutes, not hours. Perfect for market research, competitor analysis, or briefing documents.
Sections: Executive Summary, Overview, Key Players, Trends, Recommendations.
Use Tavily API or Serper API to give the agent real-time search.
Ask Claude to decompose your topic into 5 sub-questions before searching.
One search per sub-question. Pass all results to Claude to synthesise.
Combine sections into a final document. Export as PDF or Word.
"I want to research: {{topic}}. Break this into 5 specific sub-questions that together give a complete picture. Return as a numbered list only."
Handle 80% of repetitive questions automatically — so you only deal with the 20% that genuinely needs you. Runs 24/7, never loses patience.
Write your 20 most common Q&As + policies + product info.
Use Botpress or Supabase+pgvector so the agent can search your docs.
Define brand voice, what the agent can/can't do, and escalation rules.
Embed on your site using Tidio, Crisp, or a custom widget.
Try angry customers, unusual questions, discount attempts. Refine.
Route unresolved chats to Slack. Log all conversations to improve over time.
"You are a friendly support agent for {{company}}. Acknowledge emotion first, then solve. If unresolved after 2 messages, say: 'Let me connect you with our team.'"
Brief it once. Get a full content calendar with posts, captions, and email copy — all tailored to your brand voice. Consistent content without the burnout.
Tone, banned phrases, 3 example posts, your audience persona. One page.
Fields: Topic, Goal, Key message, Channel, CTA. Fill once per campaign.
One prompt per channel with format rules (length, hashtags, tone).
New row in content calendar → generate content → save drafts to Notion.
Automate creation, not publishing — until you fully trust the output.
"Take this blog post and create: (1) a LinkedIn post, (2) 3 Instagram captions, (3) an email newsletter section. Match my brand voice. Post: {{content}}"
Describe what you want built. A coding agent writes it, runs it, finds the bugs, fixes them, and keeps going until it works. No code knowledge required to start.
Install Claude Code via npm or download Cursor IDE. Both are agent-ready.
Language, inputs, outputs, edge cases, libraries. More detail = better first draft.
Use a virtual environment or Docker so the agent can execute code safely.
Check git diff before merging. Agents can make unexpected changes elsewhere.
Give the agent a test suite. Instruct it to keep running until all tests pass.
"Build a {{language}} function that takes {{input}}, returns {{output}}, handles {{edge_cases}}, includes error handling and comments. Write tests alongside it."
Connect your tools. Define the triggers. Let agents move data and fire actions automatically — the highest-leverage use of AI for any business owner.
Pick something you do 3× a week that always follows the same pattern.
"When X happens, do A, then B, if C do D, else do E, then notify me."
Start with a template. Customise rather than build from scratch.
Use Claude to classify, score, or enrich data mid-workflow.
Check every step before enabling automatic triggers.
Set up error alerts. Review logs weekly. Refine as you go.
"Classify this enquiry as [HIGH_PRIORITY], [STANDARD], or [SPAM]. High priority = budget over £10k or urgent deadline. Return label + one-line reason. Enquiry: {{text}}"
Honest, practical writing about AI agents — from someone learning and building in real time.
A step-by-step account of setting up an email triage agent using n8n and Claude.
The clearest explanation I could write of why agents are a genuine step-change.
Five automations I actually use every week — with templates you can steal.
Using Perplexity and Claude to build a competitor analysis report in 12 minutes.
The exact process I use to make AI content feel genuinely mine — not generic.
My honest experience going from idea to deployed app without writing a single line of code.
Every tool I've tested, organised by use case — with honest notes on what each one is actually good for.
Open-source automation. Build email triage + draft agent without per-task costs.
Classify emails and draft replies that sound like you.
AI calendar agent that protects focus time and auto-schedules.
Premium AI email client with triage, summaries, and smart replies.
Built-in research mode — searches the web and synthesises multi-source reports.
AI search engine. Ask a research question, get a cited answer instantly.
Upload your own docs. Ask questions across all of them. Great for internal research.
Research agent built for academic papers and deep analysis.
Affordable AI chatbot for small businesses. Easy to embed on any site.
Visual agent builder. Connects to Claude, GPT, and your data.
Open platform to build and deploy custom AI agents. Developer-friendly.
Enterprise-grade AI that resolves tickets automatically at scale.
Write and schedule social posts. Suggests optimal posting times.
Subject lines, body copy, and audience segmentation — automatically.
Marketing-focused AI with templates for ads, blogs, and social.
AI video/podcast editor. Repurposes long content into short clips.
Terminal agent that reads your whole codebase and makes changes autonomously.
AI-native IDE. Best-in-class for agents that understand full project context.
Describe an app in plain English. Replit builds and deploys it.
Live code suggestions in your IDE. Agent mode writes entire features.
Open-source, self-hostable. Most powerful free automation tool available.
Easiest to start. 6,000+ app integrations. AI step built in.
Visual builder. More powerful than Zapier, still beginner-friendly.
AI-native automation. Build agents in plain English — no code needed.