Asset 20 8 2
Does AI recommend your business? Run the free check →

Join 15,000 business owners, marketers and entrepreneurs. The Sunday newsletter you'll be annoyed only arrives once a week.

Article

Make vs Relevance AI: Scenarios or an AI Workforce?

Make fits a team that wants to map rule-based workflows between apps on a visual canvas, starting on a free plan and paying in credits as it grows. Relevance AI fits a team that wants AI agents and multi-agent workforces to carry out tasks, with an embedded team helping it go live on an Enterprise plan.

Make and Relevance AI both promise to take work off your plate, yet they start from opposite ends. Make starts from the apps you already use and lets you wire them together step by step. Relevance AI starts from the job you want done and gives it to AI agents that work through it. Both now reach into the other's territory, which is why the comparison gets confusing, so this page sticks to what each vendor says it does and who that suits.

Rules on a canvas, or agents with a brief

Make is a visual automation platform. You build scenarios that connect apps, data and AI models, and you can see every step of the flow on one screen. It now adds AI agents and an MCP server on top, so the canvas is no longer only for fixed rules. Relevance AI is a low-code and no-code platform for building AI agents and multi-agent teams that complete tasks. Its docs call those teams workforces, in which specialised agents collaborate on complex work.

That split decides most of what follows. A scenario does the same thing every time it runs, which suits invoices, form entries and handovers between tools. An agent decides how to reach a goal, which suits research, sorting new leads or answering calls, where the steps change from case to case. Neither approach is the more advanced one; they fit different kinds of work.

What each platform brings to an ops or marketing team

Make's site advertises more than three and a half thousand apps out of the box, plus custom integrations for anything with an API. Its free plan has no time limit and needs no credit card, so you can build a working scenario before anyone signs off a budget. When a step needs more than drag and drop, you can fine-tune it with JavaScript or Python. The MCP server lets Claude, ChatGPT or Gemini build and run automations, which brings chat assistants into the same account. Make says more than half a million teams build on it, which is the vendor's own figure.

Relevance AI leans on what its agents know and what they can do. Knowledge is its RAG feature, giving agents access to specific information beyond what a model was trained on, such as your product notes or policies. The Enterprise plan lists more than two thousand integrations, unlimited agents and users, SSO, role-based access and audit logs, along with calling and meeting agents and A/B testing and analytics. Its homepage pitches Invent as a round-the-clock AI solutions engineer for non-technical teams, and an embedded deployment team gets customers live and then trains them to build on their own. A template library offers ready-made agents with a Start for free button. Relevance AI is the trading name of OnSearch Pty Ltd.

If agents are the part you care about most, my guide to AI agent builders for Slack shows how other platforms bring agents into the place a team already talks.

Do you make workflow automation platforms and AI agent builders? Tool makers can ask to be considered for a featured place on this list.

Credits by the module, or credits by agreement

Billing is where the two differ most plainly. Make switched to credits as its billing unit in late August, replacing operations, and most module actions use one credit each. Router and error handler modules don't consume credits, and the usage allowance includes data transfer and storage that scale with the credits you buy. So the cost of a scenario follows how many steps it runs and how often it runs.

Here's how the sum works. A scenario with five modules, one of them a router, uses four credits each time it runs, because the router doesn't count. Run it twenty times every working day and it uses eighty credits a day, so a working month of runs multiplies that again. Do that for each live scenario, add them up, and you have the credit figure to compare against the allowances on Make's pricing page.

Work with me

Want AI doing the heavy lifting in your marketing?

I build the systems that handle the boring 80 percent, so you get your week back. Done properly, with the human kept in.

Relevance AI's pricing page shows an Enterprise plan with custom vendor credits and a route to talk to sales, rather than self-serve tiers. That suits a company buying a deployment with support attached, and it means you can't price a pilot until you've had that conversation. Neither model is cheaper by nature: one rewards tight, short scenarios, the other is shaped by what you agree. If you're weighing the agent side against more options, my page on Relevance AI alternatives lists other agent platforms.

Want your tool on this list? Featured spots and reviews here are paid partnerships. Here's how to partner with me.

Frequently asked questions

Is Make or Relevance AI easier for a non-technical team to start with?

They're easy in different ways. Make gives you a free plan with no time limit and no credit card, and a visual canvas where every step is laid out in front of you, so someone comfortable with spreadsheets can build a first scenario in an afternoon. Relevance AI aims its homepage at non-technical teams too, pitching Invent as an AI solutions engineer, and an embedded deployment team gets customers live and then trains them to build. So Make suits a team that wants to explore on its own first, and Relevance AI suits a team that would rather be guided into a working deployment with the vendor's people alongside.

How does the cost of Make compare with Relevance AI?

Make bills in credits, and most module actions use one credit, while routers and error handlers don't count. To estimate it, take your busiest scenario, count the module actions in one run and multiply by how often it runs in a month. Relevance AI's pricing page lists an Enterprise plan with custom vendor credits and asks you to talk to sales, so the figure comes from that conversation. Make also offers a start-up plan with a discount on Business for companies with fewer than twenty employees. Figures for both sit on each vendor's own pricing page, and I'd model a busy month rather than a quiet one before signing anything.

Can Make build AI agents, and can Relevance AI connect apps?

Yes on both counts, which is why the line between them blurs. Make now offers AI agents on its canvas and an MCP server that lets Claude, ChatGPT or Gemini build and run automations. Relevance AI lists API and MCP among its support links and more than two thousand integrations on its Enterprise plan. So the connectors overlap, though the counts differ: Make advertises more than three and a half thousand apps. The real difference is the starting point. Make starts from the flow and adds agents into it, and Relevance AI starts from agents and workforces that use integrations to finish a task.

What does moving work from Make to Relevance AI, or back, involve?

Neither vendor describes an importer for the other, so plan on rebuilding rather than transferring. Because both expose MCP and APIs, and their connectors overlap, the apps you rely on will often be reachable from either side, but the logic changes shape. A Make scenario is a fixed sequence of modules, while a Relevance AI workforce is a set of agents with goals and knowledge. Start by writing down each live scenario's trigger, steps and accounts, then decide which ones are rule-based and which need judgement. Rebuild one, run old and new side by side for a week, and only switch off the original once the new version matches it.

Where does each platform fall short?

Make's limits come from its credit model and its rule-based core. Because most module actions use one credit, a scenario's cost rises with every extra module and every extra run, so a long scenario that runs often uses more of the allowance. Relevance AI's limits are mostly about access: its pricing page shows only the Enterprise plan with custom credits, and the pricing page doesn't set out a free plan, even though its template library carries a Start for free button. So a small team may find it hard to price a pilot without a sales call. Both are fair trade-offs, and which one matters depends on your team's size and budget process.

How can I test Make and Relevance AI side by side in an hour?

Pick one task a real person does each week, such as qualifying new leads from a form. In Make, build a scenario on the free plan that takes a form entry, enriches it with an AI step and posts a summary to your team chat, then run it with a few real entries and check the credits it used. In Relevance AI, open an agent template from its library, give it the same brief and your lead criteria through Knowledge, and feed it the same entries. Compare how much setup each took, how readable the result is and how easy it'll be to see why each decision was made.

Published and maintained by the Lilach Bullock team, covering marketing, AI and business growth.
Your buyers are asking AI who to use. Does it say you?

See for free whether ChatGPT, Claude, Perplexity, Gemini and Google name you, and get the plan to become the answer.

Check my AI visibility →
Sundays only

Get the Sunday newsletter.

One email a week. AI experiments, marketing tactics, and the workflows Lilach is building right now in her own business.

Subscribe free

Let’s get your marketing running on AI.

Book a free 30-minute call

We figure out what you need, where AI fits in, and what working together would look like.

Book the call →

Or take the 30-second calculator

You’ll see the hours and the money quietly leaking out of your week, and the three workflows worth building first.

Take the calculator →

Or grab the free AI resource library

Prompt packs, templates, checklists, and swipe files. The exact tools I build for paying clients. Yours, free.

Get the library →
Keep reading

More from the blog.