Gumloop vs StackAI (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

Roughly ninety app nodes each come with their actions, inputs, configurations and outputs spelled out.

Classes represented include CRM and sales with Salesforce, HubSpot and Outreach, ERP with SAP, NetSuite and Oracle, ITSM and ticketing with ServiceNow, Jira, Linear, ClickUp and Zendesk, HR with Workday, data warehouses and databases with Snowflake, Databricks, BigQuery, Azure SQL, Synapse, MongoDB, MySQL and PostgreSQL, vector stores with Pinecone and Weaviate, storage and documents with SharePoint, Box, OneDrive, Egnyte, Google Docs and Excel, communications with Slack, Teams, Gmail, Outlook and Missive, financial data with SEC EDGAR, Pitchbook, Crunchbase, Fred and Yahoo Finance, plus Docusign, Stripe, Miro, Notion, Airtable, Smartsheet, Coda and a Custom API node. An MCP node connects to any Model Context Protocol server.

Sourcedocs.stackai.com apps treeread 2026-08-31

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

In the AI Agent node, Subflow Tools let an agent call another flow as a tool with its own tools, knowledge sources, main and advanced settings. Logic nodes cover AI Routing for branching the model decides, If/Else for deterministic branching, Loop Subflow for iteration, and Code and Python Code for custom logic, with a Delay node for pacing and a StackAI Project Node for invoking another project. StackAI also gives guidance on orchestrating AI agents, common architectures, handling errors and fallback, detecting the first run, and skipping or replacing a node.

Sourcedocs.stackai.com core nodes, logic and guides treesread 2026-08-31

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

Trigger Nodes start automated workflows in two ways.

Event based triggers run the moment something happens, such as a new Gmail or Outlook email, a Typeform submission, a Stripe payment, a new Zendesk ticket or another StackAI workflow finishing, with filters on conditions such as sender, label or attachments, and time based triggers run once at a set date and time or recur hourly, daily or weekly.

Both start the workflow without a person initiating it. End-user interfaces add Form, Chat Assistant, Website Chatbot, Slack App, Microsoft Teams, WhatsApp and SMS through Twilio, Batch Run and API.

Sourcedocs.stackai.com Trigger Node page and end-user interfaces treeread 2026-09-29

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

Knowledge bases can be created and used by an AI agent in two ways, through knowledge base nodes and tools, with a Knowledge Base app node for search and retrieval over indexed documents and a Knowledge Bases REST endpoint. Connection and Knowledge Base Permissions restrict access independently of workflow access. A Dynamic Vector Store node builds retrieval at runtime, Search Connected Apps grounds against live systems, and Pinecone and Weaviate nodes query customer-managed vector databases. Chunking and embeddings are configurable, and Reducto and VLM nodes handle document parsing.

Sourcedocs.stackai.com knowledge bases, apps and core concepts treesread 2026-08-31

A new agent conversation starts empty, and context is kept within the chat and its sandbox files until the window fills. Search Past Conversations, on by default, lets the agent pull relevant snippets from earlier chats when they are needed. What carries forward otherwise is instruction rather than remembered fact.

Skills are reusable playbooks the agent can create and update after a correction, saved with version history, and self improve updates are written into the agent's own instructions once a person approves them. Reflections reviews recent tasks on a schedule and proposes instruction and skill changes for approval. Brain holds company knowledge from connected sources. No retention period or deletion path is stated for conversation history.

Sourcedocs.gumloop.com agent memory help, skills and reflections pagesread 2026-10-25

The Shared Memory node passes conversational context from one LLM node to another, with the builder choosing how many past interactions to forward, and StackAI warns that passing too many will overwhelm the receiving model's context window. That context is passed within a run, and no memory kept across sessions or learned over time is described. Browser session state that persists across runs and Canvas version history for each conversation belong to the browser and document features.

Sourcedocs.stackai.com Shared Memory node and complete documentation indexread 2026-08-31

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

Human in the Loop is one of StackAI's core nodes, and the first of its building challenges is constructing a procurement intake assistant that gathers missing details with HITL and confirms the final request before sending. Approval requests can be delivered in Slack with approve and disapprove controls, bringing human oversight into critical decision points. Workflow Notifications are available, and Project Controls lock workflows when in production. Feature Access lets an admin enforce governance standards over what builders may use.

Sourcedocs.stackai.com human-in-the-loop node, building challenges and security tree, stackai.comread 2026-08-31

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

Security and governance controls cover Security and Privacy, AI Governance, Role-Based Access Controls and Groups, Workspace and Folder Access, Project Controls, Feature Access for admin enforcement of governance standards, Connection and Knowledge Base Permissions, Authentication and MFA, an Agentic Development Lifecycle, and SCIM provisioning from the customer's identity provider with dedicated Okta and Entra guides.

Environment Variables store encrypted secrets outside the workflow and resolve stage-specific values at runtime. StackAI holds SOC 2 Type II, ISO 27001, HIPAA and GDPR certification, with a Trust Center at trust.stackai.com, a SOC 2 report request form, published OpenAI and Anthropic data processing addenda, and a BAA signing route.

Sourcedocs.stackai.com security tree and stackai.com certificationsread 2026-08-31

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

The Analytics page gives node level information to follow the data flowing through a workflow, trace any actions taken at each step and find the node where an error originated, a record of the agent's run step by step. It also shows runs, users, errors and token usage over a time range, with an admin only switch to disable logs for sensitive workflows, the Manager view shows every conversation between users and agents, and an Analytics REST endpoint is available.

Sourcedocs.stackai.com Troubleshooting a Workflow, Analytics and Manager pagesread 2026-09-29

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

StackAI can run on premises, and the StackAI Auto CLI, an enterprise command line tool, deploys and manages StackAI on customer infrastructure, with engineering standards, a getting started guide, migration from a legacy Docker deployment and a storage-api CVE upgrade plan. Government deployments come with guidance for provisioning Azure OpenAI in Azure Government. StackAI offers multi tenant, VPC and on premise deployment with Kubernetes, and the workflow builder supports local LLM hosting and LLMs hosted on Azure and AWS Bedrock so inference can stay inside the customer's own cloud account.

Sourcedocs.stackai.com on-premise, government deployments and Auto CLI trees, stackai.com deploy anywhere sectionread 2026-08-31

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

Templates are offered in the workflow builder and on the product site. StackAI Computer users can open the Templates section and search for the Content Writer template, a pre-built agent with a structured system prompt that demonstrates document generation from start to finish. Skills are reusable instruction packs that AI Agents load on demand, a Prompt Library holds saved prompts and instructions, and common architectures give reusable workflow patterns. Fourteen tutorial agents can be built as examples, including compliance, IT support, policy, Salesforce and web research agents.

Sourcedocs.stackai.com templates, skills, prompt library and tutorials treesread 2026-08-31

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

StackAI supports multiple LLMs, models hosted on Azure and AWS Bedrock in the customer's own account, and local LLMs on the customer's own infrastructure, and LLM Provider Governance controls which LLMs the organization has access to and where information is sent and stored. Guidance covers using multiple LLMs and improving LLM performance, a Cerebras node adds a dedicated inference provider, and StackAI is LLM agnostic, naming Anthropic, Meta, OpenAI, Google Gemini and Mistral. A public LLM Leaderboard is published on its site.

Sourcedocs.stackai.com LLM hosting and governance tree, stackai.comread 2026-08-31

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

An API Reference covers Run Flow, Knowledge Bases and Analytics endpoints, and a StackAI MCP Server exposes the platform to MCP clients. The StackAI Auto CLI is an enterprise command line tool for deploying and managing the platform. Within workflows, a Custom API node calls arbitrary external endpoints, a Code Node and Python Code node run custom logic, and Exporting and Importing Projects plus Sharing Projects and Backup make agent definitions portable. An interface can be deployed as an API, alongside Exposed Inputs and signed URL generation.

Sourcedocs.stackai.com API reference, MCP reference, utils and interface treesread 2026-08-31

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

An Evaluator in the Observability section scores an agent's performance with an LLM as a judge, alongside Analytics and Manager. StackAI covers an Agentic Development Lifecycle, the workflow editor shows version control, a pull request and a prompt diff, and Project Controls track versions during workflow development and lock workflows in production. Guides cover troubleshooting a workflow and handling errors and fallback, and a Prompt Library stores saved prompts and instructions.

Sourcedocs.stackai.com Observability and Security in StackAI treesread 2026-08-31

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

Browser Navigation Replay persists browser state including cookies, sessions and local storage across runs. A session is recorded through a bundled browser extension in a sandboxed browser and replayed later on a schedule or trigger, and if the recording was captured while logged into a web application, that session state is preserved between runs so re-authentication is not needed.

Each replay returns a step-by-step result payload plus a stream URL for watching execution in real time. Browser Navigation is the choice when the agent must reason its way through an unfamiliar or dynamic task, and a separate HyperBrowser node automates browser tasks. The Terminal sandbox and Canvas actions on the same provider handle code execution and document editing.

Sourcedocs.stackai.com StackAI Computer and HyperBrowser nodesread 2026-08-31