Base44

Prebuilt integrations cover AI, email, file storage, payments and messaging, with Airtable, Slack, Stripe and Zapier named in the documentation index. Beyond the first party set there is a community integrations list with a Create Integration flow and per integration approval status, so third parties publish connectors others can adopt (Explorium documents its own onboarding through it).

Enterprise admins control which external services are available, manage shared versus app user credentials separately, and can block specific connectors across apps, Superagents and in app agents. Superagents themselves connect outward to third party applications and reach users over WhatsApp and Telegram. The Wix distribution adds Stores, Bookings, Blog, Events, Restaurants and CRM as context sources.

Sourcedocs.base44.com developer documentation, base44.com enterprise pages and Wix App Market listingread 2026-07-30

A Superagent splits a complex request into independent sub-agent tasks that run in parallel in the background, shows each in a task panel, lets the user stop the work while keeping finished results, and combines the outputs into one response. Superagent workflows are built from a chat description into scheduled or triggered multi-step runs managed from a Workflows page, and app workflows automate multi-step work on schedules, data changes or connector events.

Sourcedocs.base44.com/superagents/subagents and setting-up-workflowsread 2026-09-29

Agents get scoped data access, not a knowledge layer. They are grounded in the application's own data entities, with the documentation describing AI assistants defined with custom tools and data permissions, and each entity supporting granular create, read, update and delete permissions. On the Wix surface, agents answer using the merchant's live site data.

Superagents additionally reach connected business systems. No document ingestion, no embedding or vector store, no retrieval augmented generation surface, no knowledge base object and no citation or grounding attribution is documented, so there is no indexed document layer or cited retrieval.

Sourcedocs.base44.com developer documentation and Wix App Market listingread 2026-07-30

The vendor documents approval steps in the Superagent: before it sends a change to an app it asks for the owner's approval and names the app it is about to change, it asks for approval before installing a skill (answerable Yes or No in WhatsApp), and other actions that need approval are handled in the Superagent in Base44. Security settings carry per-agent permission toggles, with Update data and Delete data advised only when the role needs them; interactive actions run under the chatting user's own permissions; and enterprise admins can block connectors and disable Superagents across the whole workspace.

Sourcedocs.base44.com/superagents/customizing-your-superagent and enterprise documentationread 2026-09-29

A first-party trust center at base44.com/security names SOC 2 Type II and ISO 27001, plus GDPR. Data is protected by TLS 1.2+ in transit and AES-256 at rest, with secrets held in cloud KMS, and the program includes OWASP-based penetration testing, threat modeling, secure design and code review. There is also an active bug bounty program and a third-party vendor risk program covering every supplier.

SSO through the organization's own IdP is enforced across the workspace and every app inside it, alongside SCIM provisioning with automatic joiner and leaver sync, OAuth 2.0 connectors, IP allowlisting by address, range and subnet, and domain-based access control. Enterprise workspaces are opted out of model training by default, which for a platform that ingests the customer's prompts and application code is the commitment that matters most. Two-way GitHub export lets a customer run their own security and compliance scanners over the generated code. The platform runs on Wix's enterprise security infrastructure.

Sourcebase44.com/security trust center and base44.com/enterpriseread 2026-07-30

Every Superagent workflow run is recorded, with an Activity tab listing each run's date, workflow, status and duration and per-workflow run history, success rate and average runtime, and the agent can be asked in chat what happened in a run; sub-agent tasks are shown in a task panel.

The documentation index describes an app Logs page recording user activity and function calls through to schema and integration changes, an Audit Logs API with filterable event types, and a workspace-owned-key Monitoring API for enterprise admins.

The per-call record is described only in the documentation index entry for the app Logs page, and the Superagent run record shows status rather than the actions taken.

Sourcedocs.base44.com setting-up-workflows, llms.txt index and enterprise documentationread 2026-09-29

The owner turns Superagent memory on or off and scopes it as separated, remembering facts and history within each conversation, or shared, remembering across all conversations so what the agent learns in one is available everywhere. Under Personalization the user can review what the Superagent has learned about them and delete memories they no longer want it to use, and the agent can change how it uses memory when the owner asks in chat. No retention period is stated.

Sourcedocs.base44.com/superagents/customizing-your-superagentread 2026-09-29

Enterprise workspaces can choose where workspace app data is stored, across the US, EU or UK, to meet data sovereignty and compliance requirements, and the enterprise documentation states that applications are hosted on continuously monitored private infrastructure. No on-premises, air-gapped, customer VPC or self-hosted deployment is documented; the platform is SaaS on Wix infrastructure. The pricing page FAQ states two-way GitHub sync exports the full source code to the customer's repository.

Sourcedocs.base44.com enterprise documentation and base44.com pricing FAQread 2026-09-29

The vendor publishes a template marketplace at base44.com/templates describing more than one hundred ready-made app templates and design layouts built by the Base44 community, with category pages including community and creative tools, and instructions to pick a template, customize it with AI and launch.

The vendor's own blog documents the adoption flow, instructing users to browse the available templates, find one sharing similar workflows, clone it and ask Base44 to modify it, with a worked example of reusing a project management template's task assignment flow for an event app. The agent documentation separately documents skills as packaged reusable units, with up to ten attachable per agent and workspace skills shared across the workspace alongside app-level skills. These are application templates and reusable skills rather than prebuilt Superagents; generation remains the only documented route to creating an agent.

Sourcebase44.com/templates and category pages, base44.com blog, docs.base44.com AI agents documentationread 2026-08-31

The vendor documents Superagent workflows that run on a schedule, such as every morning or every Monday, or when a trigger happens, such as an email arriving in a connected Gmail account or a change to the agent's data, with Run Now, pause, archive and automatic pausing of repeatedly failing scheduled workflows; app workflows additionally react to data changes, publishes and payments. Superagents are reachable in Base44 chat and over WhatsApp (including groups), Telegram, iMessage, Slack channels with an agent handle, LINE and a Chrome extension, and a message sent on a channel mid-task joins the work in progress.

Sourcedocs.base44.com/superagents/setting-up-workflows and customizing-your-superagentread 2026-09-29

The vendor's agent documentation instructs users to select the model that powers their agent under an AI Model setting, keeping Automatic for fast cost-effective responses or choosing a model from Google Gemini, OpenAI GPT or Anthropic Claude for more advanced reasoning, with the setting applied per agent and switchable at any time.

Credit consumption is published per model tier, naming the Automatic default as based on Gemini 3.1 Flash Lite at approximately three credits per message, Gemini 3 Flash at moderate increase, and higher-end models such as GPT-5.6 Sol for complex analysis. Users on the vendor's public feedback forum report model selection being removed from the builder chat coding surface, which is a distinct surface from the agent setting and is not documentation.

Sourcedocs.base44.com AI agents for apps documentationread 2026-08-31

The vendor's documentation index lists a developer platform with a CLI (including agents and agent-skills pull and push), a typed SDK with an agents interface, backend functions, automations, an Apps API, Enterprise APIs, an Audit Logs API and a Monitoring API, personal access tokens, App MCP letting assistants such as Claude, ChatGPT and Cursor work with a published app's data, agents and tools, a documentation MCP and llms.txt index, and bring-your-own coding agent into the app editor.

Superagents can be reached with a personal access token. The pricing page FAQ states two-way GitHub sync exports the full source code, replacing the earlier frontend-only limitation.

Sourcedocs.base44.com/llms.txt and base44.com/pricingread 2026-09-29

A real iteration loop exists for the artifact being built: generate, preview instantly on built in hosting, inspect, and refine either by prompting again or through a visual editor that allows direct click to change edits to layout, copy and styling, with real time collaboration and version control tracking changes. Two way GitHub export lets a team run their own external security tooling and specialized compliance scanners over the generated code, which is customer controlled testing of an unusual kind.

What is absent is evaluation of the agent: no harness, no sandbox for rehearsing a Superagent against test inputs before it runs live on schedules and real events, no automated scoring, no regression testing when a prompt or integration changes. Third party reviews report that debugging consumes build credits without necessarily resolving the problem, which is a cost characteristic of the loop rather than a capability.

Sourcedocs.base44.com, base44.com/security and third party platform reviewsread 2026-07-30

Superagents complete tasks on the web from chat with no setup, in a cloud browser shown in a Live Browser view the user can follow, expand or close while the agent keeps working, with browser actions and data extractions metered per action and failed actions free. A first-party Superagent by Base44 Chrome extension lets the agent open tabs, click, type and read pages in the user's own Chrome, in its own tab group under Chrome's control banner and with the user's signed-in sessions, and falls back to the cloud browser when Chrome is not connected. Private network addresses are blocked.

Sourcedocs.base44.com/superagents/browser-controlread 2026-09-29