Gumloop vs Turbotic (2026)

Connectors are the integrations an agent connects to, including Gmail, Salesforce, Slack, Notion and 150+ more, with an All tab covering Gumloop-managed and customer-added connectors and a Custom tab filtering to custom MCP servers. The connectors added determine what the agent can access. A Tool Discovery toggle controls automatic tool finding, and tools within an integration can be restricted individually.

Connectors support API key authentication as well as OAuth. The gumcp-client system skill lets skill scripts call connected integrations directly from Python using a server__tool_name convention, with a list_tools script for discovering available tools. Connector coverage keeps growing, with DocuSign, Trello, Google Docs, Google Drive and Gong among recent additions.

Sourcedocs.gumloop.com agents and skills, gumloop.com changelogread 2026-08-31

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

Subagents let an agent delegate to other agents instead of handling everything in one conversation. An Agent node embeds an agent inside a workflow, receiving a prompt from upstream nodes and returning output downstream, and supports Loop Mode for batch processing, where each iteration starts a new conversation unless conversation IDs are tracked.

Workflows supply branching, conditional logic and loops, and subflows are reusable modular components callable from other flows and testable independently. Triggers start workflows on schedule, webhook, event or manually, and workflows and agents can invoke each other.

Sourcedocs.gumloop.com agent_node, agents and triggers pagesread 2026-08-31

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 carry a Triggers section supporting scheduled and app event triggers, with schedules written in plain language and converted by an AI-powered scheduler rather than cron.

An AI Managed toggle allows the agent to create, edit and manage its own triggers during a conversation, and a Create With AI path builds custom polling triggers that combine multiple services, query connected services for exact tool names and schemas, validate in an isolated sandbox and baseline state on first run. Webhook triggers give each agent a unique URL.

Workflow triggers cover time-based runs with retry configuration plus Gmail, Slack, Teams, Airtable, Notion, Google Sheets and form events, and Outlook triggers fire on new mail or relative to calendar events. Triggers auto-disable with notification after repeated failures.

Sourcedocs.gumloop.com triggers, ai_trigger_creation and agents pages, gumloop.com changelogread 2026-08-31

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

Company Brain connects knowledge sources, keeps them synced and gives agents company knowledge to search. Sources are attached whole through + Source or drilled into at the level of exact files and folders, and when a question touches internal knowledge the agent searches automatically, shown in chat as Searching Company Brain, and can open a full document for more context. Sync coverage extends to connected services, including Gong call recaps and transcripts. Knowledge is configured per agent alongside Connectors, Skills, Subagents and Triggers.

Sourcedocs.gumloop.com core concepts agents and gumloop.com changelogread 2026-08-31

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

Skills are reusable instruction packs the agent can read, follow, improve and create on its own. Skill Editing and Creation is on by default, so an agent updates the relevant skill after a user correction and applies it in later conversations.

Over months of normal use a skill can grow from a basic template to a full playbook, and Gumloop gives a worked example of an agent creating a skill to retain a described weekly process. Skill changes are saved automatically at the end of an agent turn, with file-level version history in an Edits tab recording what changed, when, and which agent changed it, plus usage tracking and an Activity timeline. Gumloop is explicit that skills are not conversation memory and must be reloaded when relevant.

Sourcedocs.gumloop.com core concepts skillsread 2026-08-31

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

Agents raise pending approval and input requests, and the right to reject has widened from the named recipient to anyone who can chat with the agent. Enterprise controls require human approval before expensive actions, alongside per-agent, per-team and organization-wide budgets and quota controls.

Per-tool authorization policies and restriction of which tools an integration can expose limit what an agent may do, connectors blocked by organization policy display as restricted with an on-the-spot access request, and skill creation can be disabled for a custom role so agents cannot save new skills. Skill Editing and Creation is a per-agent toggle.

Sourcegumloop.com enterprise page and changelog, docs.gumloop.com skillsread 2026-08-31

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

Gumloop says it complies with SOC 2 Type II and GDPR, and it keeps a trust center at trust.gumloop.com. Controls include role-based and attribute-based access control, per-tool authorization policies, full traceability with every call tied to a specific user, agent or service principal, a live inventory of every MCP server in use, and centrally managed secrets that never sit in plaintext locally.

Identity platform integration extends the customer's identity system of record to agents, with SCIM provisioning and per-group permission ACLs. Enterprise controls add restriction of which models teams may use, connector restriction by organization policy with request-access, and per-agent, per-team and organization-wide budgets and quotas.

Sourcegumloop.com security solutions page, enterprise page and changelogread 2026-08-31

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

Gumstack traces every tool call through a single logging and analytics layer, with every call tied to a specific user, agent or service principal and detailed audit trails capturing where data is flowing across the organization. It provides a live inventory of MCP servers in use and extends visibility to agents running outside Gumloop.

Organization-wide credit usage is tracked in real time with per-agent and per-team budget attribution, and agents can pull credit usage and run history reports via data export tools. Skills carry file-level version history naming the editing agent plus an activity timeline of views, script runs and edits.

Sourcegumloop.com enterprise and security pages, docs.gumloop.com skills, gumloop.com changelogread 2026-08-31

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

Gumloop runs as managed SaaS or can be deployed into the customer's own cloud as a VPC in the region of their choice, with data remaining in infrastructure the customer controls, and for private infrastructure Gumloop deploys and operates the full stack inside that cloud. Gumstack can equally run on Gumloop's infrastructure or inside the customer's own VPC. Enterprise materials list virtual private cloud deployment and MCP server hosting among enterprise entitlements. Open-weight model inference is routed through US-based providers under Zero Data Retention with no post-inference storage.

Sourcegumloop.com security solutions page, enterprise page and docs.gumloop.com ai_modelsread 2026-08-31

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

Skills are packaged folders containing a SKILL.md plus optional scripts, references and assets, downloadable and uploadable as .md, .zip or .skill files and shareable through Owner, Editor, Viewer and Use Only roles, where Use Only permits running a skill without visibility of its contents.

Organization Skills lets admins centrally manage a shared skill library for the whole organization, including keeping it in sync with a GitHub repository, and Gumloop links public example skill repositories and follows the Claude Skills packaging convention. Two built-in system skills, skill-creator and gumcp-client, ship with every team. A Popular Skills carousel surfaces the most-used skills in a workspace, and a template library of prebuilt flows covers common patterns.

Sourcedocs.gumloop.com skills and organization_skillsread 2026-08-31

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

Agents can use top models from every major provider, chosen in Agent Preferences at the top of the agent's configuration, with Recommended and other presets plus the full list, and new models usually arrive within a day of public release.

Every model in the agent picker supports tool calling; models without tool calling appear only in workflow AI nodes, and several open-weight models including GPT-OSS 120B, Qwen3.5 397B and Kimi K2.6 are agent-exclusive. Open-source models are accessed through US-based providers under Zero Data Retention policies with a US-provider hosted badge, with data neither used for training nor retained after inference. Enterprise controls allow restricting which models teams can use.

Sourcedocs.gumloop.com ai_models and gumloop.com enterprise pageread 2026-08-31

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 Gumloop API creates agents, starts chat sessions and triggers automations programmatically, with authentication and OAuth 2.0, Python and JavaScript SDKs, and endpoints to list, create and update agents and their immutable versions, attach skills and MCP servers, create sessions, send and queue messages, upload files, resolve pending approvals, and create, update, download and delete skills.

A Gumloop CLI drives agents, sessions, MCP servers, Company Brain and skills from the shell, and the pricing page lists a Gumloop MCP among developer features. Each agent can also carry a webhook trigger URL. Custom MCP servers can also be added as connectors, which lets Gumloop call out to other tools.

Sourcedocs.gumloop.com llms.txt API reference and CLI sections, gumloop.com/pricingread 2026-09-29

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

Evaluations sit under each agent's Performance tab and score the agent's output. After every completed interaction an AI evaluator reads the full role-tagged transcript, including tool calls and results, and produces a grade, a pass or fail for each criterion with rationales, tags, extracted data points and optional sentiment, against quality criteria the customer configures.

The overall grade is set deterministically from which criteria failed, and a Notify grade sends notifications by email or Slack. Evaluations re-run when a conversation continues and can be backfilled after criteria change. Skill validation, sandbox-validated AI-created triggers and independently testable subflows sit beside it.

Sourcedocs.gumloop.com/core-concepts/evaluationsread 2026-09-29

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

The Gumloop Chrome extension turns any browser action into an automation, recording any action taken in the browser and replaying it as a repeatable automation.

It records actions on any website, replays recorded actions in Chrome and runs Gumloop automations on any webpage, for uses such as gathering and processing data from any webpage, automating tasks on websites that do not offer API access through Web Replays, and automating form filling and data entry, going beyond what traditional APIs allow. A separate web automation node handles authenticated sites and appears to be open only to some accounts.

Sourcechromewebstore.google.com/detail/gumloop/hpkeijgchoedhhdfjdjlaimanpmbnhjmread 2026-09-29

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