StackAI

Roughly ninety app nodes are individually documented with actions, inputs, configurations and outputs.

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

The AI Agent node documents Subflow Tools, letting an agent call another flow as a tool with its own tools, knowledge sources, main and advanced settings. Logic nodes cover AI Routing for model-decided branching, 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. An Orchestrating AI Agents guide, a Common Architectures page, and Handling Errors and Fallback, Detecting the First Run, Skip a Node and Replace a Node cover operational patterns.

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

A Knowledge Bases tree documents creating a knowledge base, the two ways an AI agent can use one, knowledge base nodes and tools, and specific knowledge base features, 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 covers runtime-constructed retrieval, Search Connected Apps grounds against live systems, and Pinecone and Weaviate nodes query customer-managed vector databases. Chunking and Embeddings are documented as core concepts, and Reducto and VLM nodes handle document parsing.

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

Human in the Loop is a documented core node under the StackAI node family, and the first of the vendor's building challenges is constructing a procurement intake assistant that gathers missing details with HITL and confirms the final request before sending.

The product page shows a human-in-the-loop approval message delivered in Slack with approve and disapprove controls, described as integrating human oversight into critical decision points. Workflow Notifications are documented in the security tree, 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

A dedicated security and governance documentation tree covers 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. The product page carries SOC 2 Type II, ISO 27001, HIPAA and GDPR certification, 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

A dedicated Observability documentation section carries Analytics, Manager and Evaluator pages, and an Analytics REST endpoint is documented in the API reference. The product page shows an analytics dashboard reporting runs, users, errors and token usage and names audit logs alongside feature controls under Security and Governance.

Project Controls track versions during workflow development and the Agentic Development Lifecycle documents version control with pull requests and prompt diffs. Guides cover Getting Business Insights from Your Agent and Adding Advanced Logging for Analytics, the latter indicating some telemetry is builder-configured.

Sourcedocs.stackai.com observability tree, API reference and guides, stackai.comread 2026-08-31

The Shared Memory node is documented as passing conversational context from one LLM node to another, with the builder choosing how many past interactions to forward and the documentation warning that passing too many will overwhelm the receiving model's context window, which makes it a bounded context-passing mechanism rather than a persistence layer.

No cross-session, durable or learned memory feature appears anywhere in the complete documentation index. Browser session state persisting across runs is graded on Comp and Canvas per-conversation version history is a document feature, neither counted here.

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

The security and governance tree carries a dedicated On-Premise page, and a separate StackAI Auto CLI documentation set describes an enterprise CLI for deploying and managing StackAI on customer infrastructure, including engineering standards, a getting-started guide, migration from a legacy Docker deployment and a storage-api CVE upgrade plan.

Government Deployments is documented separately with guidance for provisioning Azure OpenAI in Azure Government. The product page states multi-tenant, VPC and on-premise deployment with Kubernetes, and the workflow builder documents 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

A Templates page sits in the workflow builder getting-started documentation and a Templates section is published on the product site. The StackAI Computer documentation directs users to open the Templates section and search for a named Content Writer template, describing it as a pre-built agent with a structured system prompt demonstrating end-to-end document generation.

Skills are documented as reusable instruction packs that AI Agents load on demand, a Prompt Library gives an overview of saved prompts and instructions, and a Common Architectures page documents reusable workflow patterns. Fourteen tutorial agents are documented as buildable examples including compliance, IT support, policy, Salesforce and web research agents.

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

Channels are documented individually as end-user interfaces: Form, Chat Assistant, Website Chatbot, Slack App, Microsoft Teams, WhatsApp and SMS through Twilio, Batch Run and API, with an Export View for deployment and Exposed Inputs for parameterisation.

Events are covered by a dedicated Trigger Node and a Typeform Trigger Node, by the Missive node which triggers workflows on incoming email, and by the Make node which triggers via webhook.

Scheduled execution appears as an established pattern in the building challenges, which include constructing a scheduled news workflow, and in the browser replay documentation, which describes a workflow that needs to run daily or on a trigger.

Sourcedocs.stackai.com end-user interfaces, inputs and apps treesread 2026-08-31

An LLM Hosting and Governance tree documents using multiple LLMs, running models hosted on Azure and AWS Bedrock in the customer's own account, and Local LLM for models on the customer's own infrastructure, alongside an LLM Provider Governance page described as controlling which LLMs the organisation has access to and where information is sent and stored.

A Using Multiple LLMs concept page and a How to Improve LLM Performance guide sit alongside, a Cerebras node adds a dedicated inference provider, and the product page states LLM agnostic operation with Anthropic, Meta, OpenAI, Google Gemini and Mistral named. A public LLM Leaderboard is published on the marketing site.

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

An API Reference section documents Run Flow, Knowledge Bases and Analytics endpoints, and a separate MCP Reference documents a StackAI MCP Server that exposes the platform to MCP clients. A StackAI Auto CLI is documented as 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. Deploying an interface as an API is documented as a first-class end-user surface alongside Exposed Inputs and signed URL generation.

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

The Observability section of the documentation carries a dedicated Evaluator page described as evaluating an agent's performance with an LLM-as-a-judge, alongside Analytics and Manager.

An Agentic Development Lifecycle page sits in the security and governance tree, the product page shows the workflow editor with version control, a pull request and a prompt diff, and Project Controls is documented as tracking versions during workflow development and locking workflows when in production.

Troubleshooting a Workflow and Handling Errors and Fallback are documented operational guides, and a Prompt Library stores saved prompts and instructions.

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

Browser Navigation Replay is a documented action that persists browser state including cookies, sessions and local storage across runs, created by recording a session through a bundled browser extension in a sandboxed browser and replayed later on a schedule or trigger; the vendor states that if a recording was captured while logged into a web application, that session state is preserved between runs so re-authentication is not needed, and it returns a step-by-step result payload plus a stream URL for observing execution in real time.

The same page directs users to Browser Navigation instead when the agent must reason its way through an unfamiliar or dynamic task. A separate HyperBrowser node documents automating browser tasks. The Terminal sandbox and Canvas actions on the same provider are code execution and document editing and are deliberately excluded from this grade.

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