n8n and Make automation templates: what they are, how they differ, where to start

n8n and Make automation templates: what they are, how they differ, where to start

Automation is when services are wired to each other and the work between them happens on its own: an enquiry arrives from the website, lands in a spreadsheet, and a notification goes to the manager. Nobody moves anything by hand.

Automation is when services are wired to each other and the work between them happens on its own: an enquiry arrives from the website, lands in a spreadsheet, and a notification goes to the manager. Nobody moves anything by hand.

A template is one of those wirings that somebody has already built. All that is left for you is to plug in your keys and switch it on.

Below: how it works, how n8n differs from Make, how to put a model inside a chain, what to check before importing somebody else's template, what this work pays, and where to start so you get a result in an evening rather than drowning in theory.

This is a living guide: the daily AI digests keep it current with fresh techniques.

---

The short version

A wiring has three parts: what triggers it, what happens, where it shows up. Everything else is detail.

Do not start from a blank canvas, start from a template. Most tasks are standard and the solution is already built.

Describe the process first, automate second. Otherwise you cement the mess and make it harder to fix.

The saving comes from frequency, not complexity. A ten-minute task done daily is about forty hours a year.

n8n or Make is a choice between control and simplicity, and on eighty per cent of tasks there is no difference.

There is money here. On the market a system or a pipeline runs $490–1 460 against a median one-off job of $30–75.

---

Part 1. How it works

Three parts in any wiring. Understand them and you can read and edit anybody's template.

What triggers it. The event everything starts from: a time arrives, an email lands, somebody submits a form, a new row appears in a table.

What happens. Steps in sequence. Each takes the result of the previous one and passes it on: fetch data, call a service, write a row, send a message.

Where it all goes. Data flows from step to step. The last step puts the result where it is needed.

You assemble it visually, in blocks, with a mouse. The barrier to entry is roughly that of setting up email filters, not programming.

A template is one of those chains ready-made for a standard task. For example: new website enquiry → enrich the data → write to CRM → notify the owner. Import it, plug in your credentials, run it. Minutes instead of designing from scratch.

---

Part 2. n8n or Make: which to choose

Both solve the same problem — visual automation. The difference is emphasis.

n8n is about control. You can run it on your own server, insert your own code, and keep the logic and the data with you (official documentation).

Make is about simplicity. More ready connections to popular services out of the box and a lower barrier to entry.

How to choose in two minutes

Four questions, and the answers decide it without reading a single review.

Are you doing this for yourself or to sell? For yourself, take whatever you will learn faster. To sell, take what you can hand over and explain to a client.

How many operations a month? Hundreds — no difference in cost. Tens of thousands — do the maths, that is where it appears.

Is there data that cannot leave your premises? If yes, the question is settled: you need something that deploys on your own server.

Are you willing to work it out when a ready block does not exist? No — a visual builder. Yes — a platform you can extend with code.

General rule: start with the simpler one. Move when you hit a specific limit — "the block I need does not exist", "too expensive at this volume". "People say the other one is more powerful" is not a limit.

Your own server: when it is worth it

The defining feature of n8n is that you can run it yourself. This is not a feature for hobbyists but the answer to three situations.

Privacy. Data and keys never go to a third-party service. For sensitive scenarios that is not an advantage, it is a condition.

Control. You manage the version, the limits and which blocks are available.

Economics at volume. For intensive automations, running it yourself often costs less than paying per operation.

The price is that you maintain the server, the updates and the backups yourself. Small teams usually find it easier to start in the cloud and move later; flows already built do not break in the move.

---

Part 3. How to put a model inside

A wiring becomes "smart" when you add a step that calls a model: it takes the data from previous steps, sends it to the model, and passes the result on.

That is how automation stops being a rigid if-then diagram and starts handling text, images and everything else that does not fit neatly into fields.

The rule that saves money

Not everything should go to a model.

Automation runs on rigid rules. Predictable, cheap, never mistaken. But it does not understand content: it cannot read an email and decide whether it is a complaint or an order.

A model understands. More expensive, more complex, less predictable.

The split is simple: mechanical work to a rule, work that needs understanding to a model. Getting it wrong in either direction costs money: a model where a rule would do is expensive and less reliable; a rule where live language is involved simply does not work.

And the practical conclusion: most of what people reach for agents to do is solved by an ordinary wiring.

The next step up is an agent step, where the model does not just answer but chooses which tool to call. How that works, what it costs and how to run it safely is in the AI agents hub. And the knowledge of how a procedure should be carried out gets packaged into skills — the Skills for Claude Code hub.

---

Part 4. Five tasks that get automated most often

Nearly every working wiring comes down to five classes, and the library has ready templates for each.

Enquiry intake. Requests from every source — form, email, messenger, social — collected in one place, with a notification to whoever owns them.

Content. On a schedule or an event, material is assembled (often with a model involved) and published to the right platforms.

Alerts. The wiring watches a source and warns the team when something happens.

Data sync. Rows across spreadsheets, CRMs and databases stay consistent without manual copying.

Reports. On a schedule, figures from several sources are gathered into a summary.

The value of ready templates is precisely that all five have already been built and debugged by somebody. No need to design from scratch — take the closest flow and adjust it.

---

Part 5. One template taken apart

So that you can read any other one. Take a standard case: enquiry → data enrichment → CRM → notification.

The trigger is a form on the website: on submission it sends the data into the system.

Step one receives the fields: name, contact, message.

Step two enriches them: an external service is queried on the contact so the manager sees straight away who they are dealing with.

Step three writes the enquiry into the CRM.

Step four notifies the owner: it takes the link to the created record and sends it to a messenger.

Data flows between steps: the CRM takes fields from the enrichment result, the notification takes the link from the CRM result.

What to check before going live

What happens if the external service is down. Enrichment is a nice-to-have, not a requirement. The enquiry must reach the CRM regardless, not disappear along with the outage.

What happens if the form is submitted twice. Somebody double-clicks — the CRM must not end up with two identical clients.

Where the keys live. In the platform's secure store, not in the text of the flow, which can be exported along with your credentials by accident.

Take one template apart like this and you can read any of them: the trigger → steps → data structure is the same everywhere.

---

Part 6. Reliability: dealing with failures

A wiring is useful exactly to the degree that it survives failures. External services occasionally return an error or go silent, and without preparation such a failure breaks the chain quietly — you spend a week believing the process is running when it stopped.

Three techniques.

Retries on steps that call unstable services. A short pause and a repeat often resolves a temporary failure.

A separate branch for errors. A step fails and the chain does not stop, it takes the fallback path: sends a warning and stores the data to retry later.

Duplicate protection. Running again on the same data must not create a second record.

And the main rule: every wiring must be able to report a failure. A failure alert matters more than the automation itself — without it you find out about the problem when a client asks why nobody replied.

A good template already contains an error branch. If it does not, add one, or the first failure becomes a silent loss of data.

---

Part 7. Security: keys and access

A wiring holds the keys to your services, so its security is first of all access management.

Minimum rights. Give a flow access only to what it genuinely needs, not "just in case".

Keys in the store, not in the text. A secret written into a step travels with the exported flow.

Read other people's templates before importing. Look at which services the flow calls and what access it asks for. That is exactly why descriptions in the catalogue are open before download — you assess a template and its appetites in advance.

If a flow contains an agent step, the same measures apply as for agents generally: isolation and confirmation on destructive and payment operations. Covered in detail in the AI agents hub — automation with an agent in it inherits every one of that agent's risks.

---

Part 8. When you have a lot of automations

What comes to the fore is not individual flows but maintaining them.

A run log. The execution history you use to investigate failures. For critical flows, an alert when one falls over.

Versions. So you can roll back when a new edit breaks something.

Separate environments. A test one for checking changes, a live one for the work. Experiments must not touch what is running.

And a review once a quarter. Fifteen minutes to check every wiring is still needed and still does what it should. The most treacherous breakage is not a failure but a wiring that faithfully keeps doing something nobody needs any more.

As load grows, cost comes to the fore too: intensive flows that call models start spending noticeably. The same techniques apply as in token economics: cache the unchanging part, an inexpensive model by default, pay for the result rather than the text. Covered in the LLM pricing and token economics hub. It is exactly at the junction of volume and cost that your own server usually pays for itself.

---

Part 9. Content automation: what it looks like

A popular class of its own, and it shows nicely how a model fits into a chain.

A standard flow: once a day the schedule fires → a step gathers the inputs (topic, source, brief) → a model step generates the text → if needed, the next one calls image or video generation → the final step publishes it or puts it in a review queue.

The key point: the "smart" step is an ordinary step in the chain. It takes data from the previous ones and hands its result on, exactly like any other.

Two pieces of advice that save money.

Keep a human check where a mistake is expensive. Fully automatic publishing belongs only to proven low-risk formats. Material that goes out without a human glance will eventually go out badly.

Watch the spend. Content pipelines with text, images and video burn through noticeably more. The same techniques work: an inexpensive model by default, cache the unchanging part, a draft before the expensive final pass.

Ready content flows are in the automation templates section, and building prompts for images and video is easier to hand off to the prompt generator.

---

Part 10. What this pays

The section missing from almost every other piece written about automation. People write about it as technology — and earn from it as a service.

The three things people buy most

Enquiry intake in one place. A business gets requests from four or five sources and loses some of them. The owner knows their revenue and does not know their losses: an enquiry that arrived in the wrong place exists in no report.

Winning back existing clients. A reminder to people who have not been in touch for a while. The fastest payback in the whole set: these people do not need to be bought with advertising or convinced who you are.

Regular reporting. Not to save an hour but because the report starts existing at all. Most small companies do not have one — not because they do not want it but because every time somebody has to be chased.

What all three have in common

None of them is about complicated technology. All three are about something that is not being done at all, not about speeding up something that is.

That is the key to selling it. Automation that speeds up work already being done sells badly: the client counts the hours saved and sees no gain. Automation that creates something absent sells easily.

Frame it as absence: "right now the after-hours enquiries are lost", "right now nobody works the old client list", "right now there is no report".

How to approach a client

Not with an offer of automation. With one question: how many enquiries arrive outside working hours, and what happens to them.

The owner almost never knows the exact answer. That not knowing is your sale.

The price range

From a scrape of 848 job listings over 24 days: a system or pipeline runs $490–1 460, against a median one-off job of $30–75.

An honest caveat: an explicit budget appears in 6% of listings, with two to fifteen observations per category.

Quote it as a composition, not as one number: inventory of sources, building the wirings, the texts and the rules, failure alerts, documentation and training, what the client pays for directly from then on, ongoing support. Seven lines defend themselves — people argue with items, not with the total.

And the real money is not in the first build. Services change their interfaces, wirings break, the client's processes get rebuilt. Support is a recurring payment and an honest one.

In the scrape, 21.9% of clients are looking for someone long-term and 20.3% mention ongoing volume. Almost half the market does not fit inside a one-off job.

Three mistakes when selling

Selling the platform. The client does not care what it is built on. The conversation is about the result.

Automating before describing. A process done differently every time will be cemented in exactly that state.

Promising headcount cuts. Even if it is true. One mention turns the client's staff into opponents at every step where you need them to be honest about how the work is really done. The right framing: the freed-up time goes to what nobody ever got round to.

---

Part 11. When Make and n8n are overkill for you

An honest fork worth naming before you climb into a builder.

Make and n8n exist for connecting services to each other: a website enquiry into a CRM, an email into a spreadsheet, an order status into a notification. That is their job and they do it well.

But most "I want to automate this" requests are not about that. People want to produce: content, documents, images, clips. There the job is not to link two services but to carry material through several processing steps.

There is a separate section for that — AI Workflow — and it is simpler.

How it differs

The result of one step automatically becomes the input of the next. Idea → script → frame → animation → voiceover → finished clip. No downloads and re-uploads in between.

Thirteen ready templates, so you do not start from a blank canvas: a clip from an idea in 3 steps, a UGC ad from a product photo in 6, a marketplace listing in 6, cleaning machine clichés out of posts in 10, a 13-section business pack in 86 steps, a month of carousels from a content plan in 129.

The quote is calculated before the run. You see what the whole run will cost and what will be left on your balance. Charging follows the steps actually executed, and money for anything not done comes back automatically.

The run continues on the server even if you close the tab.

Control blocks

What makes the chain more than a straight line.

Condition — a branch on a rule. AI branch — the model picks the direction rather than a hard rule. Loop — repeat a section as many times as needed. Iterator — run a section for every item in a list: thirty posts in one go. Approval — a pause where the chain waits for your decision. Template as a step — nest a finished chain inside another.

Plus publishing — the finished piece goes straight to Instagram, TikTok, YouTube, Facebook, X, LinkedIn, Threads or Pinterest.

Which is for whom

Connecting services, handling enquiries, syncing data — Make or n8n.

Producing content, documents, visuals — AI Workflow. Simpler, needs no third-party service keys, and does not make you learn a builder.

Both — take both: they do not compete, they cover different halves of the work.

An assembled chain is saved to your profile permanently: open it, drop in new data, run it. Scheduled and event-triggered runs come with the Full plan.

---

Part 12. Where to start

Better to start from a ready template for a nearby task than from a blank canvas: you see a working chain immediately and edit it to fit.

The automation templates section holds more than 3 000 ready flows with open descriptions. What a flow does and why it is useful is visible before download; the files themselves open with a subscription. The catalogue grows daily.

The route: open the section → find a template for your task → read the description → import → plug in your keys → run it on test data.

What to look for in the description

Five questions before importing:

The open description on the card is exactly what lets you answer all of this before downloading, instead of wasting time on a flow that needs a service you cannot reach.

---

Part 13. What to open up for your task

Six steps, from free to serious. Do not take the top one if a lower one covers you.

1. Ready templates — free to look at, Plus to use

More than 3 000 flows in the automation templates section: enquiry handling, mailouts, reports, integrations between services.

Finished agents, separately. Not just if-then wirings but flows that call a model: inbox triage, enquiry qualification, drafting replies.

Descriptions are open to everyone without registration: what a flow does and which keys it needs is visible before download. Files come with Plus, advanced ones with Full.

2. AI Workflow — if the task is about production

Content, documents, visuals. Thirteen templates, condition and loop blocks, a quote before the run. Needs no third-party service keys.

Scheduled and event-triggered runs come with the Full plan.

3. The "Automator" module — Plus plan

The entry level of the programme: automating routine tasks. Included alongside the photo, video and editing modules.

This is the answer to "where do I start" if what you want is understanding rather than a ready template.

4. Express course "AI Agents" — $9

From a first automatic agent to chains running round the clock. 20 finished projects and four platforms: Make, n8n, Relevance, Lindy.

Included in the Make and Team plans. Not included in the three free days of Basic: a one-off purchase, a plan, or 1 000 XP points.

Take it if you want to understand agent flows but have not decided which platform to settle on.

5. The Make plan — the full Make course

Module 11 of the programme plus the mini-course on agents. And the library above all: more than a thousand ready AI agents in the Make aggregator, plus CRM integration templates.

Take it if your tasks are integrations with services and CRMs and you would rather not deal with infrastructure.

6. The N8N plan — the full n8n course

Module 12 of the programme plus the mini-course on agents. The library: more than 500 ready n8n templates, RAG agent templates, a sales-call monitoring system, a finished AI influencer workflow.

The skills you come out with differ from Make: self-hosting via Docker and a VDS, corporate document search on vector databases, enterprise-grade fault-tolerant automations.

Take it if you need control, privacy and your own server.

Full — both platforms and the archives

Every module of the programme, the Make and n8n archives, access to local models. The level for people building private environments for companies.

---

Choosing between Make and N8N by plan

The same question as at the top of this guide, but now about the training.

Tasks are integrations with services and CRMs, infrastructure holds no interest → Make.

You need your own server, data privacy and large volumes → N8N.

Undecided → start with the $9 express course: four platforms at once, and after it the choice becomes obvious.

---

What sits nearby

140+ AI assistants across 14 categories — for tasks that need understanding rather than a rule. Plan: Basic.

And separately, the Bot Architect in the Engineering category: it writes system prompts for conversational systems, including the rules for handing a conversation to a human.

The Skills for Claude Code catalogue — over nine thousand procedures for agents.

The Open Source section — open tools and everything you can deploy yourself.

Prompt generator — if your chain includes generation.

Timeline: what is happening now

The automation and agent layer moves fast: harnesses are becoming products of their own, models get cheaper and more expensive, new solutions ship almost weekly. Fresh releases and techniques are covered in the daily AI digests.

For how agents are built, the AI agents hub; for open models, Best open LLMs 2026; for ready flows, the templates section.

---

FAQ

What is the difference between n8n and Make, in plain words?

n8n is about control: you can run it on your own server, insert code, keep the data with you. Make is about simplicity: more ready connections and a lower barrier to entry.

Does it matter to you? On most standard tasks, no — you will not notice the difference. It shows up when the data is sensitive or the volume has grown to tens of thousands of operations a month.

Do I need to know how to program?

No. A template is imported and configured visually: you supply your keys and data, the logic is already built by its author. Code is only needed for non-standard processing, and not always then.

That is exactly why you should start with a ready template for a nearby task rather than building from scratch: you get a working chain immediately and learn on it.

Can I put a model inside an automation?

Yes: you add a step that calls a model, and for complex tasks an agent step that picks its own tools.

But check first whether you need one: if the task can be described as "if A then B", the rule will be cheaper and more reliable. Agents in detail are in the AI agents hub.

Can n8n be run for free?

It can be run on your own server — that is the platform's defining feature. That removes per-operation charges and leaves you with server and maintenance costs.

For a team that values privacy and control this is often cheaper and steadier over time. The price is that you keep the server, the updates and the backups yourself, so small projects find it easier to start in the cloud and move later. Requirements are in the official documentation, and ready templates work identically either way.

Where should a beginner start?

Not by studying a platform "in general" but with one specific task you currently do by hand.

Keep a list of everything you did more than once this week. Keep it for a week and automate nothing. Whatever appears three times is your first candidate.

Then find a ready flow for a nearby task in the templates section, read the description, import it, plug in your keys and run it on test data. In an hour you have a working result instead of theory.

How much can you earn from automation?

From the scrape of 848 listings, a system or pipeline runs $490–1 460 against a median one-off job of $30–75. Those are different units: one is an operation, the other a result with stages and a handover.

And the real money is not in the first build but in the support: services change, wirings break, processes get rebuilt. Almost half the clients in the scrape are looking for someone long-term — automation is precisely the kind of service that fits there.

---

Try it

Registration is free and opens three days of full Basic access — all 140+ assistants, the prompt texts, the skill files, the ten-lesson sales module and six foundational courses.

One thing to do right now. Start a list of the tasks you did by hand more than once this week. Do not try to fix anything — just keep the list for a week.

The list will show you where to start more accurately than any audit.

What to read next

Make or n8n: which to choose — decided by four questions in two minutes.

Automation without a developer — where to start if you are not an engineer.

Three automations people buy — what gets ordered and how to sell it.

A company knowledge base as a service — RAG agents and why they pay more.

Local AI models for sensitive data — self-hosting as a condition of the deal.

Process audit — what gets done before automating.

Digitising an offline business — where exactly the clients leak away.

Sales call audit — a system from $9 600 and its smaller version.

Build once, run always — the alternative when the task is about production.

AI for business owners — how this looks from the client's side.