The AI platforms we build on, and how we pick one for your workflow

You bring the workflow and we choose the platform that fits it, whether that is n8n, Kestra, Microsoft Foundry, Claude Cowork, SAP Joule Studio or Sim AI. The same team scopes it, builds it and runs it after launch.

Already paying for one of these? We build on the platform you have.

Start from the job8 jobs
  1. When something happens in one app, update the othersn8n
  2. An agent that works through a queue of tasksMicrosoft Foundry
  3. An assistant that answers from your own documentsMicrosoft Foundry
  4. Custom agents IT and security can sign offMicrosoft Foundry
  5. Scheduled data and AI pipelines, defined as codeKestra
  6. AI for everyday work across every teamClaude or ChatGPT
  7. Agents inside your SAP processesSAP Joule Studio
  8. Agent workflows you can self-hostSim AI

The first four jobs are scored across eight platforms in our platform comparison, checked 4 October 2026.

Clients include

AudinatePinkcubeBizIQCourserAllClear Travel Insurance

Go deeper on each platform

One page per platform: what we build on it, how a build runs, what it costs to run and the questions teams ask before they start.

Workflow automation

n8n

Builds, reviews, Enterprise setup, training and support from an official n8n Select Partner.

  • Agency builds and expert reviews
  • n8n vs Zapier and Make
  • Enterprise plans and security
Read the n8n page
Enterprise AI platforms

Microsoft Foundry

Production AI workflows built in your Azure tenant, under Entra ID and your data rules.

  • Where Foundry fits, and where it does not
  • Pricing on your Azure bill
  • The data boundary inside your tenant
Read the Microsoft Foundry page
Workflow automation

Kestra

Declarative, event-driven data and AI pipelines on your own infrastructure.

  • A real Kestra flow, step by step
  • Moving off Airflow or cron
  • Build plan and handover to your team
Read the Kestra page
Workplace AI

Claude Cowork

Cowork connected to the systems your teams use, with people approving what matters.

  • Task routing and document drafting
  • Approval gates and admin controls
  • Rollout plan with team training
Read the Claude Cowork page
SAP

SAP Joule Studio

Custom Joule skills and agents that answer from SAP and non-SAP data in one conversation.

  • Procurement, HR and supply chain workflows
  • Non-SAP data through BTP
  • Release with your Basis team
Read the SAP Joule Studio page
Agent builders

Sim AI

Open-source AI agent workflows, built on a canvas and run on Sim Cloud or your own infrastructure.

  • One workflow, from trigger to approved action
  • Where Sim fits next to n8n and your models
  • Implementation plan, step by step
Read the Sim AI page

Every platform we build on, by the job it does

Platforms in the same group do the same kind of job. Each page shows where that platform fits, what it costs to run and where we would build on something else.

Workflow automation

A trigger runs the same defined steps every time, with AI inside the steps, so every run is predictable, testable and auditable.

  • n8nBilled per run however many steps it takes, and self-hostable in your own cloud.
  • KestraOpen-source orchestration for data and AI pipelines, defined as code.
Agent builders

Open-source platforms where AI agents are built on a canvas, connected to your tools and self-hosted when data has to stay in your network.

  • Sim AIAgent workflows built on a canvas, in chat or in code, and deployed as an API, a chat interface or an MCP server.
Enterprise AI platforms

Agents built inside your Microsoft estate, under your identity, data and compliance rules.

  • Microsoft FoundryAgents built in your Azure tenant under Entra ID, billed on your Azure account.
Workplace AI

Assistants your whole company uses for everyday work, set up with the connectors and permissions each team needs.

  • Claude CoworkAnthropic's agent for knowledge work, with the connectors and skills your teams use.
  • ChatGPT for workChatGPT rolled out to your company with connectors, custom GPTs and admin settings.
SAP

AI inside the SAP systems your finance and supply chain teams already run.

  • SAP Business AIJoule and SAP's AI features, connected to the processes you run in SAP.
  • SAP Joule StudioCustom Joule agents and skills built for your own SAP workflows.
Not sure which group?

Score eight platforms against what matters to you: where it runs, who builds it, how many runs and how much AI it needs.

Open the platform comparison

Six questions that decide the platform

We ask these in the scoping call, before any platform is named. The platforms that score highest on each come from our platform comparison.

Data

Where must it run?

If the workflow has to run on your own servers, n8n and Kestra both self-host. Microsoft Foundry does not, but its Standard setup keeps agent data in your own Azure resources.

People

Who will change it after launch?

If your developers will maintain it, we use the platform they already know. If business users will, we pick one they can edit and train them on it.

Control

How much custom code does it need?

n8n and Microsoft Foundry score highest when the workflow needs custom code, its own models or full control over hosting.

Volume

How many runs a month?

At millions of runs, billing decides the cost. n8n bills once per workflow run however many steps it takes, which keeps high volume cheap.

AI depth

A few AI steps, or an autonomous agent?

Microsoft Foundry scores highest for agents that choose their own next step. A workflow with a few AI steps fits n8n.

Estate

What do you already run on?

Teams on Microsoft 365 and Azure get the most from Microsoft Foundry. Teams that run finance and supply chain in SAP start with SAP Joule Studio.

Already running one of these?

Platform chosen

We build on the platform you pay for

Tell us which platform you have and the workflow you want on it. A senior partner tells you on the call whether it fits, and scopes the build if it does.

Book a Discovery Call
Built by another team

We take over what is already built

We start with a technical assessment of the system's quality, then fix, harden and run it in weekly sprints that you direct.

See AI managed services

What teams ask about AI platforms

Ask us something else

Which AI platform should we use?

The one that fits the job. Workflows that move data between apps on a trigger fit n8n. Agents that work a queue of tasks fit Microsoft Foundry. Assistants your security team must approve inside Azure fit Foundry. The platform comparison scores eight platforms against your own priorities.

Do we have to choose a platform before we talk to you?

No. We scope the workflow first: the systems it touches, who will maintain it and where it has to run. The platform follows from those answers, and we tell you why before you commit.

Can one workflow use more than one platform?

Yes, and it often should. A common pattern is n8n moving the data between your apps and calling a Microsoft Foundry agent for the reasoning step.

Which of these can we self-host?

n8n has a self-hosted Community Edition plus Business and Enterprise plans. Kestra is open source under the Apache License 2.0 and runs on Docker or Kubernetes. Microsoft Foundry runs in Azure only.

Who runs the system after launch?

The engineers who built it, in weekly sprints that you direct, with error alerts going straight to them. See AI managed services.

Where should we start?

With the workflow that has the most volume and the clearest rules. If you already know which one, book a discovery call. If you have several candidates, the AI Audit ranks them by value, effort and risk over 4 to 8 weeks and ends in a 90-day roadmap. It costs $10,000 to $100,000 depending on scope, and the fee is credited toward your first build.

Put your first workflow on the board

Answer a few questions about your team and what you want automated, then a senior partner scopes it with you on the call.