| InTouch AI | Make | |
|---|---|---|
| What it is | Automation platform with a built-in agentic AI assistant. Runs on your own machine, from a laptop to a Raspberry Pi to a server. | Hosted visual automation platform built around a drag-and-drop scenario canvas. |
| Who it is for | One person with a to-do list through to a Fortune 500 IT floor — technical or not. The assistant is the way in. | Power users who like to see the shape of their logic on a canvas. |
| Where it runs | Your hardware, your network. Nothing has to leave the building. Also fine in a cloud VM if you want one. | Their cloud only. There is no self-hosted Make. |
| How you pay | Personal Edition free forever, no per-run charge at any volume. Paid editions are licences, not meters. | Per operation — every module execution is billed, plus data transfer. |
| InTouch AI | Make | |
|---|---|---|
| How automation gets built | Describe it in plain English and the assistant builds it. Or write IML directly. Or both — edit what it wrote. | Drag modules onto a canvas and wire them together. |
| What the automation IS | IML — plain JSON you own. Diff it, review it in a pull request, commit it, carry it to another install. | A scenario blueprint (JSON) you can export — but it only runs inside Make. |
| Adding a capability that does not exist yet | Implement one interface, drop in a JAR, and it hot-loads without restarting. It arrives already scheduled, credentialed, retried, logged and alerted. | Build a custom app in their app-builder, or use the generic HTTP module. |
| Configuration screens for your own tools | The Schema Designer renders a tool’s entire configuration form from its schema — including tools you wrote yourself. Nobody writes UI code per tool. | Custom app definitions render inside Make’s UI. |
| Reach beyond SaaS APIs | 33 tool types in the free download: HTTP, AWS (the entire CLI v2), Google Workspace, email (IMAP read), messaging, OS/spawn, archive, runtime environments, vector store, skills, workflows and the AI family (Anthropic ×5, OpenAI, Gemini, Mistral, Groq, DeepSeek, xAI, OpenRouter, Ollama, Hugging Face, embeddings, image generation, speech to text, text to speech, fine-tuning, document chunker) — SQL, SSH, FTP/SFTP, rsync, Docker, Excel, PDF, Git, LDAP, MongoDB, Cassandra and dozens more install from the Hub in one click; Essbase and TM1 are licensed connectors, delivered separately | App modules plus generic HTTP/SQL modules. Same on-network limitation. |
| InTouch AI | Make | |
|---|---|---|
| Scheduling | 7 native schedule types, plus file triggers, folder triggers and AI-condition triggers. | Scenario scheduling on an interval or a specific pattern, plus instant triggers. |
| Reacting to a file landing on disk | First-class. A trigger watches a path or folder, with a settle timer so it does not fire on a half-written file. | Same — cloud storage watchers, not local paths. |
| Stopping two runs colliding | Collision detection and exclusive locks, so a long run cannot trample the next one. | Not offered. |
| InTouch AI | Make | |
|---|---|---|
| Where the AI sits | Inside the engine. The assistant builds tools, workflows, credentials, schedules and monitors, runs them, reads the logs and fixes what broke. | AI modules and agent features you place on the canvas. |
| Choosing your own model | 8 providers — OpenRouter (one key, 367 models), Anthropic, OpenAI, Gemini, Mistral, DeepSeek, xAI, and Ollama for fully local. | Provider modules you configure. |
| Running with no AI at all | Fully supported and common: AI authors the workflow once, then it runs forever with no model in the execution path and zero AI cost per run. | Same. |
| Cost of AI over time | Zero per run once authored, because the artifact is deterministic. You can also watch spend by provider, model and project. | AI modules consume operations on every run. |
| InTouch AI | Make | |
|---|---|---|
| Where your credentials live | An AES-256 vault on your machine. The assistant can USE a credential to do work without the secret ever entering its context. | Stored in Make’s cloud. |
| Whether your data leaves the building | It does not have to. Run every step locally, with a local model if you want, and nothing crosses the network. | Every operation runs in their cloud. |
| Audit trail | Every action attributed and timestamped; every run keeps inputs, outputs and result code — in the free edition, not a tier. Both are readable by the assistant. | Execution history; broader audit on enterprise plans. |
| Granting access to individual capabilities | Capability grants: allow or deny individual tools, AI providers, skills — and the assistant itself — per user or per group. Deny-by-default, enforced where a user reaches for the capability: listing tools, adding one to a workflow, running a skill, opening the assistant. (Enterprise; Department governs objects through roles.) | Team roles on higher plans. |
| InTouch AI | Make | |
|---|---|---|
| What it takes to install | One JAR with an embedded database. About five minutes. A Raspberry Pi 5 is enough. | Nothing to install — a genuine advantage. |
| If the vendor disappears tomorrow | It keeps running. It is on your hardware, and the automation is JSON you already have. | Your automation stops. |
| Air-gapped or regulated environments | Supported. No outbound dependency, and a fully local model if AI is required. | Not possible. |
| Choose InTouch AI when… | Choose Make when… |
|---|---|
| Your automation has to reach machines and databases on your own network; you want it reviewed like code rather than inspected like a diagram; you do not want per-operation billing; or you want to describe the job in words instead of assembling it. | The canvas. For branching, iteration and data reshaping, seeing the whole scenario laid out visually is genuinely easier to reason about than reading any file — and Make’s routers, iterators and aggregators are excellent at it. |