Make vs Turbotic (2026)

Agent tools are modules, scenarios, MCP server tools and other agents, drawn from Make's app and module catalog, and they connect agents to third party services such as email, database and CRM systems to carry out tasks. Scenarios become tools with defined inputs and outputs, and MCP toolboxes group tools.

Sourcehelp.make.com Introduction to Make AI Agent (New) and Scenarios for AI agentsread 2026-09-30

Automation AI connects to any service with an API. When a request needs an outside system, the AI asks for the key, explains where to find it and stores it as an environment variable, and the finished workflow then reads and writes in that system, adding a lead to Airtable or a CRM, sending an email or calling OpenAI.

HubSpot, Airtable, Google Sheets, Outlook and other email platforms, Jira, ServiceNow and UiPath are among the services it works with, and each integration is code Automation AI writes for that service's API rather than a maintained connector. Automation Orchestration reaches across UiPath, Blue Prism and Automation Anywhere robots and agents built on any framework, and when a failure is critical it opens the incident in ServiceNow, Jira or a similar service management tool without waiting for a person. The Turbotic AI Assistant connects to more than 200 business systems for the data it works on.

Sourceturbotic.com/platformread 2026-10-13

Agents call other agents, scenarios and modules as tools, and agents run inside scenarios, whose engine routes and branches between modules and handles failures through an error handling tree (error handlers, exponential backoff, throw), so deterministic steps and agent reasoning combine in one flow.

Sourcehelp.make.com Introduction to Make AI Agent (New) and error handling treeread 2026-09-30

From one request, Automation AI writes a multistep workflow with its trigger, conditions, delays and actions, such as waiting 24 hours after a new lead before sending an email, and runs it on Turbotic's own service. Users can change the logic by chat or edit nodes and code by hand, with version history kept. Automation Orchestration coordinates robots, AI agents and workflows across vendors from one control plane, including hybrid automations that pass work between AI and RPA. How Orchestration decides which robot or agent takes a job is not spelled out.

Sourceturbotic.com/resources/blog/turbotic-automation-ai-tutorial-build-first-automation-step-by-stepread 2026-10-13

Agents start from the first module of their scenario, with guided examples for chat messages, Slack and Telegram messages, emails and mailhooks, form submissions and webhooks, and they can also run on their own on a schedule.

Sourcehelp.make.com Create AI agents for different triggersread 2026-09-30

Published automations run on a schedule, such as a news digest every morning at 7:00, when something happens in a connected app, such as a new lead arriving in HubSpot, or when another system calls them through a webhook or an API trigger. For IT operations, workflows start from monitoring alerts and system events. Scheduling comes with Basic and the plans above it, and a chat prompt starts work on demand. Automation Orchestration watches running robots and agents for failures and anomalies as they occur.

Sourceturbotic.com/resources/blog/turbotic-automation-ai-beginners-guideread 2026-10-13

Knowledge files are stored in a retrieval augmented generation vector database. Make splits each file into chunks, converts them to vectors and returns the most relevant chunks to the agent at request time, not the whole file. Files of up to 20 MB, 20 per agent, in TXT, PDF, DOCX, CSV, MD or JSON format, are managed at organization level, can be downloaded, replaced and deleted, and are deleted after 180 days without a query.

Sourcehelp.make.com Knowledge files for AI agentsread 2026-09-30

The Turbotic AI Assistant works on data a team uploads from any enterprise system, SaaS application or data source, and keeps conversations and material in shared workspaces, where it turns them into process documentation. Automation AI keeps files beside each automation in its dashboard and reads whatever a workflow fetches on each run. Neither keeps an index of company knowledge that an automation searches as it works, so grounding comes from what a team uploads or a workflow fetches at run time.

Sourceturbotic.com/turbotic-airead 2026-10-13

The Run an agent module takes a Conversation ID that keeps a user's interactions in the same thread across runs, with a maximum conversation history setting. No scope beyond the thread, retention or delete path is described for that history. Data stores persist between scenario runs, but they are application data the builder reads and writes, not a memory layer.

Sourcehelp.make.com Make AI Agent (New) app and data storesread 2026-09-30

Each automation keeps its own version history, files and environment variables in the Turbotic dashboard, and the AI Assistant keeps work in shared workspaces. What an automation remembers between runs has no public description, and the product documentation needs a sign in.

Sourceturbotic.com/resources/blog/turbotic-automation-ai-beginners-guideread 2026-10-12

The customer controls which modules, scenarios and MCP tools an agent may call, and Make's best practices treat minimal access as the most reliable constraint, alongside prompt instructions to have a person validate outputs, which Make warns agents may not always follow. No approval, checkpoint or pause for a person is described for Make AI Agent (New).

Sourcehelp.make.com Make AI Agent (New) app and AI agent best practicesread 2026-09-30

Automation AI includes team collaboration and approval flows for automations, and the user reviews each generated step on a visual canvas before publishing.

Turbotic's governance work sets human in the loop and escalation points, approval points, intervention rights and stop conditions for each process, and the platform enforces them where the automations run, with agents acting only within approved policies, permissions and operating modes.

Turbotic's agent platform promises approval gates on the way from test to production and an AI supervisor that flags drift or unsafe actions and escalates them to a person. A buyer cannot yet see how an approver finds and clears a waiting step.

Sourceturbotic.com/what-we-do/governance-complianceread 2026-10-13

Make's information security program is ISO 27001 certified, and Make has completed SOC 2 Type II and SOC 3 audits and adheres to GDPR. The SOC 2 report details internal controls, and a product-specific public SOC 3 summary is available at trust.celonis.com/product/make/soc-3.

Controls include single sign-on with Google, Facebook and GitHub, with Enterprise customers able to use their own SSO, advanced role and team management within an organization profile, log retention beyond the 30-day default on Enterprise, and a hosting environment reachable only from the private network over VPN, with no direct public internet access.

The program also covers regular independent penetration testing, vulnerability management, OWASP-aligned coding standards with static application security testing, AES-256 full-disk encryption with AWS KMS, TLS 1.2 and 1.3 in transit, a public bug bounty and an enterprise security whitepaper.

Sourcemake.com security pageread 2026-09-01

Turbotic holds ISO 27001 certification for how it builds, hosts and runs its platform, and a SOC 2 Type II report on security, availability and confidentiality controls tested over time. In the Turbotic AI Assistant, a customer's administrators add, remove and suspend users, access, share and remove what users submit, and see logs of how people use the service.

Credentials for the services an automation connects to stay in environment variables, out of the workflow itself, and Turbotic's governance service sets data handling and access rules for each agent and automation. The agent platform promises role based access and policies that block unsafe actions before they run, but a buyer cannot check whether Automation AI signs people in through the company's own identity provider or which roles separate building an automation from running it.

Sourceturbotic.com/what-we-do/governance-complianceread 2026-10-13

Each agent run returns metadata with its execution steps and token usage, and a Reasoning tab shows processing steps, speed, context window use and any fallback connection, with the agent's step by step decisions available for debugging. Agents run as modules inside scenarios, which keep the platform's run records and error handling.

Sourcehelp.make.com Make AI Agent (New) app and Introduction to Make AI Agent (New)read 2026-09-30

Every Automation AI run writes a log of each step, the dashboard keeps a logs section beside each workflow, and each automation reports hours saved, money earned and the value it created. Automation Orchestration tracks performance, failures, cost and behavior across robots and agents, ranks anomalies by impact, groups the past week's errors by category and shows license use against potential savings, and its view of language model work covers prompt analysis, compliance oversight, usage and cost. Every recommendation, approval and action stays on record for audit.

Sourceturbotic.com/orchestrationread 2026-10-13

An on-prem agent ships as downloadable installers for Windows Server and for Debian, Ubuntu, Fedora and Red Hat, needs Java 11 or above and is configured with a client ID, secret and base URL, so a customer can run an execution component inside its own infrastructure without a sales conversation, though it is still in beta.

The Enterprise platform runs in a separately managed AWS environment isolated from self-service cloud customers, and log data is kept for 30 days by default, with longer retention on Enterprise. The cluster runs across two zones on AWS EC2 private instances within an Amazon VPC. No region choice or residency option is offered, and the platform itself is not self-hostable.

Sourcemake.com on-prem agents and security pagesread 2026-09-01

Automation AI runs as a Turbotic cloud service, and the Enterprise plan adds an option to deploy it on premises in the customer's own environment. Turbotic AB is in Stockholm, personal data is processed at its operating offices and wherever the other parties to the processing sit, and Turbotic AI is sold only in the geographies Turbotic supports. Where the cloud service is hosted, and whether a customer can choose, is not public.

Sourceturbotic.com/platformread 2026-10-13

The AI Agents Library offers pre-made AI agent scenarios as starting points, among them Account Researcher, Lost Deals Analysis, Resume Analysis, Sales Coach, Lead Qualification, Personalized Outreach, Interview Scheduler, Customer Feedback, HR Onboarding Q&A and Competitor Price Monitor agents, each doing its own job.

Sourcemake.com AI agents libraryread 2026-09-30

Automation AI starts every automation from a description of the job, with no forms and no templates by design. In the Turbotic AI Assistant a team saves its own templates and uses a built in meeting agent for summaries, action items and sentiment, and Turbotic's agent platform promises a shared library of tools, prompts and patterns for new agents to build on. All of it is material a team assembles itself, so a new customer starts from its own words rather than from a library of ready made automations.

Sourceturbotic.com/turbotic-airead 2026-10-13

An AI provider connects the agent to a model, with OpenAI, Gemini and Anthropic Claude named as common providers. Make's own provider needs no provider account, custom AI provider connections are available on paid plans, and the Run an agent module takes a connection and a model selection.

Sourcehelp.make.com Introduction to Make AI Agent (New) and Make AI Agent (New) appread 2026-09-30

Automation AI writes, tests and repairs workflows with Turbotic's own AI agents, whose underlying provider a customer neither sees nor picks. The automations it builds can call OpenAI or any other AI service a user adds a key for, so the model inside a finished workflow is the customer's choice, and Turbotic's agent platform promises agents built on OpenAI, Anthropic, Google or open source models. Turbotic does not use what customers submit to Turbotic AI to train generative models.

Sourceturbotic.com/resources/blog/turbotic-launches-automation-airead 2026-10-13

The Make MCP server lets MCP clients such as Claude and ChatGPT run scenarios and manage the Make account, including checking data stores and inviting organization members, with MCP toolboxes limiting which scenarios are exposed. The Make Developer Hub has the API documentation and the path for building custom apps.

Sourcehelp.make.com Make MCP server and developers.make.com API documentationread 2026-09-30

Turbotic AI, the assistant, issues API keys, allows programmatic access to its output only through its API and holds callers to rate limits, with the API reference behind a customer sign in. Inside Automation AI, each workflow opens to manual node editing and a code editor that explains what the code does. A developer outside the product has no public reference, SDK or MCP server to build against.

Sourceturbotic.com/termsread 2026-10-13

Debugging tools include the reasoning view, which explains each decision and helps when something goes wrong, the error handling tree, a common errors guide and advice to monitor agent behavior through output bundles. No evaluation, scoring, test dataset or regression testing is described.

Sourcehelp.make.com Introduction to Make AI Agent (New), AI agent best practices and error handling treeread 2026-09-30

Before publishing, a user runs a live test and reads the log of each step, and Automation AI writes, tests and fixes its own code while it builds, with version history to step back to. Testing is a run and a read of the log, with no saved test cases to rerun after a change.

Sourceturbotic.com/resources/blog/turbotic-automation-ai-tutorial-build-first-automation-step-by-stepread 2026-10-13

Agent tools are modules, scenarios, MCP server tools and other agents, and no browser, desktop or computer use is described for Make AI Agent (New). Web content reaches scenarios through app modules and HTTP requests, not through a browser Make runs for the agent.

Sourcehelp.make.com Introduction to Make AI Agent (New) and Make AI Agent (New) appread 2026-09-30

Turbotic sells browser automation alongside API work, for jobs that cross systems, APIs and browser tasks, but how a browser run is driven, by which engine and whether an agent operates the browser on its own, is left to a sales conversation. Automation AI itself is API first and writes custom code for each service, and Automation Orchestration watches the RPA robots that click through screens without steering them.

Sourceturbotic.com/resources/blog/turbotic-vs-zapier-enterprise-automation-comparisonread 2026-10-13