AI Toolkit
Free AI tools and templates for small businesses: use the AI cost and ROI calculators, browse self-hosted AI tools with licence and hardware details, and copy free AI automation templates and prompts. Everything here is free to use and needs no account.
02Cost & ROI Calculator
Three small calculators that run in your browser. Replace the example numbers with your own, because the answer depends far more on your volume and your time than on any vendor’s headline price.
Cash cost is what leaves your bank account. All-in cost adds your upkeep hours at the hourly value you enter, which is the cost most comparisons leave out. The most upkeep you can afford is the number of monthly hours at which self-hosting and the subscription cost the same. If your real upkeep is above it, the subscription wins. This assumes both options do the same job, so check features and the licence first.
Hours saved are tasks multiplied by minutes per task and by the share of time you expect to save. First-year return compares twelve months of value with twelve months of tool cost plus the setup time. Treat the hours as an estimate: time ten real tasks before you trust it, and remember that saved hours only become money if you spend them on paid or valuable work.
Cost per request is input tokens times the input price plus output tokens times the output price, divided by one million. The prices in the boxes are placeholders, not a quote for any model, so copy the current numbers from your provider’s pricing page. Real bills also include retries, long conversations that resend earlier messages, and tool calls, which is what the overhead box is for.
Everything you type stays in your browser. Nothing is sent or stored. Want the detailed version for one tool? Try the n8n Self-Hosting Cost Calculator, or read how much it costs to run an AI agent every month.
03Open-Source Directory
Each entry lists what it replaces, its licence, the hardware it needs and one thing to watch. The first nine entries come from my self-hosted software guide. The local AI entries summarise each project’s public description, so confirm details on the project’s own page before you rely on them, because licences and requirements change.
A visual workflow builder that connects apps, APIs and AI models. Run it yourself or use n8n Cloud.
Watch out: Your own upkeep time is the biggest hidden cost, and the licence restricts some ways of selling n8n as a service. Read it before you resell workflows.
A Postgres database with authentication, file storage and APIs, usable hosted or self-hosted.
Watch out: Self-hosting is a multi-service stack, so budget for upkeep and not only the server.
A single-file backend with an embedded database, user accounts, file storage and an admin screen.
Watch out: Built for small and mid-sized apps. Check that a single-server database fits how you expect to grow.
Project and issue tracking with boards, cycles and modules for small teams.
Watch out: AGPL-3.0 carries obligations if you modify the code and offer it over a network. Read it first.
An open-source CRM with customisable objects, views and pipelines.
Watch out: Check the feature list against your real sales process before you move any contacts.
A shared inbox for email, live chat and social messages, with assignment and canned replies.
Watch out: Some features sit in paid editions. Confirm the Community build covers what you need.
A newsletter and mailing-list manager that sends through an SMTP email service you choose.
Watch out: Sending email is the hard part. You still need an SMTP provider and good deliverability habits.
Privacy-focused web analytics with a simple dashboard.
Watch out: Reports are simpler than Google Analytics, so check it answers the questions you actually ask.
Lightweight, cookie-free web analytics you host yourself.
Watch out: The Community Edition is not the same product as Plausible Cloud. Compare features before you choose.
Runs open-weight language models on your own computer or server and exposes a local API.
Watch out: Local models are usually weaker than the largest cloud models. Test on your real tasks before you switch.
An inference engine for running quantised language models on ordinary CPUs and GPUs.
Watch out: Command-line first. Expect more setup than a desktop app.
A self-hosted API server that accepts OpenAI-style requests and runs models locally.
Watch out: Compatibility with the OpenAI API is not identical for every feature. Test your client against it.
A browser chat interface for local and OpenAI-compatible models, with user accounts.
Watch out: Read the licence before you rebrand it or offer it to clients.
Nothing here matches your search. Try fewer words or a different category.
04Copy-Paste Workflow Hub
The prompts are written to work with any chat model, such as ChatGPT, Claude, Gemini or a local model. The four n8n files are importable JSON starters built from the recipes below, and I have not run them in a live n8n, so expect to adjust node settings and credentials on first import. These are starting points I wrote, not benchmarked or production-proven exports. I will label a template as tested only after I have run it and published the result. Replace the [BRACKETS] and {{variables}}, try each one on real examples, and keep a person in the loop before anything is sent or changed.
Sorts incoming email into categories and flags anything a person must read.
You are a support triage assistant for [COMPANY]. Read the email below and return JSON only, with these keys:
- category: billing, bug, how-to, sales, spam or other
- urgency: low, normal or high
- summary: at most 25 words
- needs_human: true or false
Set needs_human to true if the email mentions legal action, a refund above [AMOUNT], account deletion, a safety issue, or anything you are unsure about. Do not invent facts about our product.
Email:
{{email_body}}Drafts a reply that a person reviews before anything is sent.
Draft a reply to the customer message below. A person will review it before it is sent.
Tone: [TONE, for example friendly and direct].
Use only facts from the knowledge snippets. If the answer is not in them, write NEEDS ANSWER: followed by the question for the team instead of guessing.
Keep it under 120 words.
Customer message:
{{message}}
Knowledge snippets:
{{snippets}}Turns a batch of real customer questions into FAQ entries.
Below are real customer questions from the last [PERIOD]. Group the ones that mean the same thing. For each group write one FAQ entry: a short question in the customers own words, and an answer of at most 60 words using only the facts in the notes.
If the notes do not answer a group, write NEEDS ANSWER: and the question for the team.
Questions:
{{questions}}
Notes:
{{notes}}Summarises a long support thread for the teammate taking over.
Summarise the support thread below for a teammate who has not seen it. Write: what the customer wants, what has been tried, how the customer feels (one line, based only on their words), and the next step you recommend.
Do not add facts that are not in the thread. If something is unclear, list it under Questions.
Thread:
{{thread}}Drafts a steady reply for a person to review before sending.
A customer is upset. Draft a reply that a person will review before it is sent.
Acknowledge the specific problem in one sentence without admitting fault we have not confirmed. Do not promise a refund, date or fix unless it appears in the confirmed facts. Offer one clear next step. Keep it under 120 words.
Customer message:
{{message}}
Confirmed facts:
{{facts}}Rates an enquiry against your ideal customer and lists what is missing.
Read the enquiry below and return JSON only with: fit (strong, possible or poor), budget_signal (stated, implied or none), urgency (low, normal or high), reason (at most 20 words), and missing_info (a list of questions to ask).
Our ideal customer: [DESCRIBE IDEAL CUSTOMER]. Base the answer only on the text. If it is unclear, use possible and say what is missing.
Enquiry:
{{enquiry}}Drafts a short follow-up for a person to edit.
Write a follow-up email after a sales call. A person will edit it before sending.
Include: a one-line thanks, a recap of the three needs the prospect mentioned, the agreed next step with its date if one was given, and one question. Use only the call notes. Keep it under 150 words, plain and friendly.
Call notes:
{{notes}}Prepares honest answers to the objections buyers raise most.
List the five objections a buyer is most likely to raise about [PRODUCT OR SERVICE]. For each, write a two-sentence answer using only the facts below. If the facts do not support a good answer, say so and suggest what we would need to find out.
Facts:
{{facts}}Builds the structure of a proposal, not the final text.
Turn the discovery notes below into a proposal outline with these headings: Goal, Current situation, Proposed approach, Scope (included and not included), Timeline, Price (leave as [PRICE]), Risks and assumptions.
Use only what the notes say. Mark every gap with ASK CLIENT: and the question to ask.
Notes:
{{notes}}Gives a writer a clear brief before drafting.
Create a content brief for an article on [TOPIC] for [AUDIENCE]. Include: the one question the article must answer, a suggested title and three alternatives, an outline of H2 headings, what the reader should be able to do afterwards, and a list of facts or figures that need a source before publishing. Do not state any statistic yourself.
Creates short posts from an article you wrote.
Using only the article below, write [N] social posts for [PLATFORM]. Each must make one point from the article, stay under [LIMIT] characters, and avoid hype words. Do not add claims or numbers that are not in the article. End each with a plain call to read it.
Article:
{{article}}Gives options to test, not a promise of results.
Write ten subject lines for the email below: five plain and descriptive, five curiosity-led. Each under 55 characters. No clickbait that the email body does not deliver on, and no all caps.
Email:
{{email}}Drafts search snippets within the length limits.
Write a meta title (under 60 characters) and a meta description (under 155 characters) for the page below. Put the main phrase [KEYWORD] near the start of the title, describe what the reader gets, and do not promise anything the page does not contain. Give three options and count the characters of each.
Page content:
{{content}}Tightens writing without changing its meaning.
Edit the text below for clarity. Shorten long sentences, replace jargon with plain words, and cut filler. Keep every fact, number and name exactly as written, and keep my voice. Return the edited text, then a short list of what you changed and anything you were unsure about.
Text:
{{text}}Pulls structured fields out of messy receipt text.
Extract these fields from the receipt text below: vendor, date (YYYY-MM-DD), currency, subtotal, tax, total, payment_method.
Return JSON only. Use null for any field you cannot find. Do not guess or calculate missing values.
Receipt text:
{{text}}Writes the wording of a weekly update from numbers you have already calculated.
You are writing a weekly update for [AUDIENCE]. Using only the numbers below, write five bullets: what changed, by how much (absolute and percent), the likely reason only if the data supports one, and one thing to check next week.
If a number looks like a data error, say so instead of explaining it.
Data:
{{table}}A sanity check to run next to the AI API cost calculator above.
Here is my planned AI feature: [DESCRIPTION]. Average input tokens per request: [N]. Average output tokens per request: [N]. Requests per month: [N]. Price per 1M input tokens: [PRICE]. Price per 1M output tokens: [PRICE]. Calculate the monthly model cost step by step, list three assumptions that could make the real cost higher, and suggest one way to cut cost without hurting quality.
Turns messy notes into a numbered procedure.
Turn the rough notes below into a standard operating procedure for [TASK]. Use numbered steps, name who does each step and which tool they use, add a check after each risky step, and end with what to do if something goes wrong.
If a step is missing or unclear, write ASK: and the question instead of inventing it.
Notes:
{{notes}}Lines up quotes on the same terms.
Compare the vendor quotes below in a table with one row per vendor and these columns: price, what is included, what costs extra, contract length, cancellation terms, and anything unclear.
Use only the text provided. Write NOT STATED where a quote is silent. Finish with three questions to ask each vendor.
Quotes:
{{quotes}}Drafts a firm but friendly reminder for review.
Write a polite payment reminder for invoice [NUMBER], amount [AMOUNT], due [DATE], now [N] days overdue. Tone: [TONE]. Mention how to pay and who to contact. Do not threaten, add fees or invent terms that are not listed below. Keep it under 100 words.
Payment terms:
{{terms}}Turns a transcript into decisions, owners and open questions.
From the transcript below, list:
1. Decisions made
2. Action items, each with an owner and a due date (write unassigned if either is missing)
3. Open questions
Keep dates exactly as spoken, and do not add tasks nobody mentioned. Quote nothing longer than 10 words.
Transcript:
{{transcript}}Builds an agenda with time boxes.
Create an agenda for a [LENGTH]-minute meeting about [PURPOSE] with [ATTENDEES]. For each item give the question to settle, who leads it and a time box. Put decisions first and updates last. End with five minutes for actions. Flag any item that could be an email instead.
Summarises a thread and pulls out what you owe.
Summarise the email thread below in this order: the decision or question at the centre, what each person wants, what is agreed, what is still open, and anything I need to reply to or do (with who asked and any date they gave).
Quote nothing longer than 10 words and add no facts.
Thread:
{{thread}}Records why a decision was made.
From the notes below write a decision log entry with: the decision, the date, who decided, the options considered, why this one was chosen, what would make us revisit it, and the review date. Use only the notes and mark gaps with UNKNOWN.
Notes:
{{notes}}Lists what to check before you repeat an article.
Read the text below and list every factual claim that could be checked: numbers, dates, names, quotations and cause-and-effect statements. For each, say what kind of source would confirm it. Do not say whether it is true.
Text:
{{text}}Scores options on what matters to you.
I am choosing between [OPTION A], [OPTION B] and [OPTION C] for [PURPOSE]. My criteria, in order of importance: [CRITERIA]. Make a table with one row per option and one column per criterion, using only the information I provide below. Write UNKNOWN where it is missing, then list what I should check first.
Information:
{{info}}Finds failure points before you build.
We plan to automate [PROCESS] using [TOOLS]. Imagine it failed badly three months from now. List the ten most likely reasons, ordered by likelihood times damage. For each give an early warning sign and one safeguard, such as human approval, a spending cap or a log. Mark which risks involve customer data.
Writes a job description around results.
Write a job description for [ROLE] at [COMPANY]. Start from the outcomes this person should deliver in the first 90 days: [OUTCOMES]. Include a short overview, responsibilities, must-have skills, nice-to-have skills, and what we offer from the facts below. Avoid unnecessary requirements and exclusionary wording. Do not invent pay or benefits.
Facts:
{{facts}}Creates consistent questions for every candidate.
Write eight screening questions for [ROLE]. Each should test one skill from this list: [SKILLS]. For each question give what a strong answer includes and what a weak answer sounds like. Use the same questions for every candidate and avoid questions about age, family, health or other protected topics.
Keeps scoring consistent across interviewers.
Create an interview scorecard for [ROLE]. Use 5 to 7 criteria taken from the outcomes below. For each, give a 1 to 4 scale with a plain description of each score, and a space for evidence quotes. Add a reminder to score before discussing with other interviewers.
Outcomes:
{{outcomes}}Untested starter Tools you could use: n8n, Make or Zapier, plus any AI model API.
Guardrail: Nothing reaches a customer unless a person approves it.
Main cost driver: Two AI calls per email times your monthly volume. Use the AI API cost tab with your real token counts.
Untested starter Tools you could use: Any automation platform, a form tool and a CRM or spreadsheet.
Guardrail: Store only the fields you need, and say what the form is for on the form itself.
Main cost driver: Mostly the task or execution count on your automation platform.
Untested starter Tools you could use: A scheduler, a spreadsheet or database, and any AI model API.
Guardrail: Let code do the arithmetic and let the model do the wording.
Main cost driver: One AI call a week, which makes this the cheapest recipe here.
Untested starter Tools you could use: An RSS or web trigger, a small data store and any AI model API.
Guardrail: Treat a summary as a pointer to the source, never as the source.
Main cost driver: Grows with the number of sources times the number of new items, so set a daily cap.
No prompt or recipe matches your search.
For a full build with a human approval step, read How to Build a No-Code AI Agent Pipeline.
05AI Tools & Software Finder
Pick the job. For each one I name common options, say how to choose between them and point to the article to read next. No prices are quoted here because they change. The linked guides show prices together with the date they were checked.
Common options: ChatGPT, Claude, Gemini
How to choose: Give each the same real task and compare the editing you still have to do, not only the first draft.
Read next: ChatGPT vs Claude vs Gemini: Which AI Is Best for Business Productivity in 2026?
Common options: General AI assistants with web search, or an answer engine such as Perplexity
How to choose: Prefer tools that show their sources, then open the sources. An AI summary is a pointer, not evidence.
Read next: E-E-A-T and AI Content in 2026: How to Avoid Google’s “Lowest Quality” Rating
Common options: GitHub Copilot, Claude Code, Cursor
How to choose: Judge a coding tool by whether you can understand and test what it writes. Start with a small project.
Read next: Vibe Coding Explained: How Non-Developers Are Building Real Software
Common options: n8n, Make, Zapier
How to choose: Price the same workflow at your real volume on each platform, and add your own time if you self-host.
Read next: Zapier vs Make vs n8n: Real Cost at 10K, 50K and 500K Tasks
Common options: Vapi, Retell, ElevenLabs, Bland (voice); Chatwoot (shared inbox)
How to choose: Work out the cost per minute or per conversation at your volume, and keep a human path for anything urgent or sensitive.
Common options: Claude for Chrome, ChatGPT Atlas, Gemini
How to choose: Start with read-only tasks and review every action before it is confirmed.
Common options: One AI assistant, one automation platform, one support or scheduling tool
How to choose: Cover your three most repetitive jobs first and add a tool only when a task clearly needs one.
Read next: Best AI Tools for Solo Entrepreneurs 2026: A Lean 10-Tool Stack (With Real Prices)
No job matches your search.
06Learn AI & Automation
Start with the first path if you are new. Move to the cost path before you buy anything, and to the self-hosting path if you want more control over your tools and data.
A step-by-step route from a repetitive task to a working automation, with a workflow diagram.
A six-stage blueprint with a human approval step in front of anything that sends or changes data.
Ten use cases, plus a research-agent demo that checks automation-platform pricing.
Monthly cost for 1,000 conversations on budget, mid-tier and top-tier models, with the arithmetic shown.
A plain-language way to estimate the cost per task before you set a price.
A line-by-line monthly budget, with lean, typical and heavy versions.
How to measure whether an automation is paying off.
The server, backups, licence and your own time, with a calculator.
Ten tools with their licences and hosting requirements.
What a self-hosted voice agent costs on a very small server.
How to deploy AI agents without losing control of them.
No guide matches your search.
Looking for something else? The Guides page lists the best starting articles by topic.
07Free Downloads & Templates
The worksheet, checklist and prompt pack are created in your browser when you click, so nothing is uploaded. The n8n workflow files are plain JSON you import into n8n. No sign-up is needed for any of them.
A spreadsheet with the same arithmetic as the ROI calculator, using live formulas that open in Excel, Google Sheets or LibreOffice.
Ten checks to run before you move a tool onto your own server, from licence to restoring a backup.
All 30 prompt templates from the workflow section in one file you can keep in your notes.
Sorts incoming email, drafts replies and sends them to your team for approval. Nothing goes to the customer. Untested starter.
Checks and de-duplicates a form lead, sends it to your CRM, and alerts you if the CRM step fails. Untested starter.
Reads a published CSV, calculates the changes in code and has the model write the wording. Untested starter.
Watches an RSS feed, summarises new items and lists claims to check against the source. Untested starter.
The four starter workflows above in one file.
No download matches your search.
08Reviews & Comparisons
Cost and feature comparisons written to help you choose, not to sell. This page contains no affiliate links. Where affiliate links exist elsewhere on the site, they are disclosed on the page where they appear and never change a verdict. See the Affiliate Disclosure and the Editorial Policy.
The same workflow priced on both platforms at three volumes.
The three-way cost comparison at 10K, 50K and 500K tasks.
Three AI assistants compared on business productivity work.
What the ChatGPT plans cost for a five-person team.
Eight CRMs compared for startups.
Four voice-agent platforms priced at 100, 1,000 and 10,000 calls.
Real costs, and which one to buy.
Three browser agents compared on business tasks.
Five AI platforms compared for business efficiency.
No comparison matches your search.
09Our Digital Projects
So you can see the work behind the advice. More projects will be listed here once they are ready for visitors to use.
This site: cost breakdowns, buying guides and how-tos on AI and SaaS tools, written and maintained by one person.
A stand-alone calculator that compares an n8n server with n8n Cloud, including your own upkeep time.
The best starting articles on AI agent costs, small-business AI budgets and WordPress technical SEO.
How articles are researched, how AI is used, what gets tested and how corrections work.
Who builds and maintains these resources, and what he has actually built and run.
No project matches your search.
10Recently Updated Resources
The six most recently updated articles. I update an article when prices, licences or facts change, and I note the change on the article.
Updated October 24, 2026
Updated October 24, 2026
Updated October 24, 2026
Updated October 23, 2026
Updated October 23, 2026
Updated October 23, 2026
No recent article matches your search.
This page is a working index to the tools, calculators and guides on Beeznez Tech. I built it for founders, freelancers and small teams who want to use AI and automation without paying for more software than they need. The calculators run in your browser, the directory lists software I have written about or plan to cover, and the guides it links to show their arithmetic and their sources.
Licence, price and hardware figures in the directory come from official documentation and are summarised in my guides, together with the date they were checked. The local AI entries are summaries of each project’s public description. The prompt templates and workflow recipes are starting points I wrote myself. I have not run them in production, so each recipe is labelled as an untested starter. When I run one and publish the result, I will change its label and link the write-up. My Editorial Policy explains how I research, test and use AI assistants, and what I will not publish.
This page contains no affiliate links today. If that changes, they will be marked and covered by the Affiliate Disclosure. The site may show Google ads, as described in the Privacy Policy, and ads never influence what is listed.
If you spot an outdated price, a wrong licence or a broken link, please contact me and I will correct it and note the change. If a tool or template is missing, tell me that too.
11 · Stay updated
The quickest way to follow new tools, templates and updated guides is the site’s feed, which works in any feed reader. Missing a tool or template? Tell me and I will consider it.