| InTouch AI | Microsoft Power Automate |
| 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. | Microsoft's automation service for flows across Microsoft 365 and connected apps, plus Windows RPA. |
| 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. | Organisations already standardised on Microsoft 365, usually with IT involved in licensing. |
| Where it runs | Your hardware, your network. Nothing has to leave the building. Also fine in a cloud VM if you want one. | Microsoft's cloud. An on-premises data gateway reaches local data; the flow engine still runs in their cloud. Desktop flows (RPA) do run locally on Windows. |
| How you pay | Personal Edition free forever, no per-run charge at any volume. Paid editions are licences, not meters. | Per user, or per process/flow, with premium connectors and AI Builder priced separately. |
| InTouch AI | Microsoft Power Automate |
| How automation gets built | Describe it in plain English and the assistant builds it. Or write IML directly. Or both — edit what it wrote. | Designer UI, or Copilot from a prompt. Expressions use Power Fx / WDL. |
| 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 flow definition inside your tenant, exportable as a solution/ZIP for other Power Platform tenants. |
| 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. | Author a custom connector (OpenAPI) — premium licensing applies to those who use it. |
| 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. | Connector definitions render in the flow designer. |
| Reach beyond SaaS APIs | 35 tool types in the free download: 11 SQL databases, SSH, FTP/SFTP, rsync, HTTP, AWS (the entire CLI v2), Google Workspace, OS/spawn, runtime environments, messaging, skills, and the AI family (Anthropic ×5, OpenAI, Gemini, Mistral, DeepSeek, xAI, OpenRouter, Ollama, embeddings, vector store, speech, images). Essbase and TM1 bring it to 37 once licensed. Docker, Git, Excel, PDF, LDAP, MongoDB, Cassandra and thirty more install from the Hub in one click. | Broad connector catalogue; on-premises data via the gateway. Shell and file-level work is Windows RPA territory. |
| InTouch AI | Microsoft Power Automate |
| Scheduling | 7 native schedule types, plus file triggers, folder triggers and AI-condition triggers. | Recurrence trigger, plus a large set of event triggers across Microsoft services. |
| 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. | Local folders via a desktop flow on Windows, or cloud storage connectors. |
| Stopping two runs colliding | Collision detection and exclusive locks, so a long run cannot trample the next one. | Concurrency control settings on a flow. |
| InTouch AI | Microsoft Power Automate |
| 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. | Copilot drafts flows; AI Builder adds models. Both are priced separately. |
| Choosing your own model | 8 providers — OpenRouter (one key, 367 models), Anthropic, OpenAI, Gemini, Mistral, DeepSeek, xAI, and Ollama for fully local. | Azure OpenAI and AI Builder within Microsoft. |
| 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 Builder credits on every run. |
| InTouch AI | Microsoft Power Automate |
| 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 as connections in your Microsoft tenant. |
| 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. | Runs in Microsoft's cloud; the gateway brokers access to local data. |
| 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. | Run history, plus tenant auditing through Purview. |
| 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.) | DLP policies, environments and Managed Environments (premium). |
| InTouch AI | Microsoft Power Automate |
| What it takes to install | One JAR with an embedded database. About five minutes. A Raspberry Pi 5 is enough. | Nothing for cloud flows; Windows machines for RPA, plus a gateway for local data. |
| If the vendor disappears tomorrow | It keeps running. It is on your hardware, and the automation is JSON you already have. | Tied to your tenant and its licensing. |
| Air-gapped or regulated environments | Supported. No outbound dependency, and a fully local model if AI is required. | Constrained; cloud dependency remains. |