StackAI
No-code platform for building and deploying AI workflows and agents on enterprise data.
StackAI is a no-code platform for building enterprise AI agents that do more than talk: they execute work end to end across the systems a business actually runs on. Where many agents stop at generating text, StackAI's premise is that value comes from agents that can reach into tools like CRMs, ERPs, ITSM systems, and document repositories to read data and take actions. Founded by two MIT PhDs, the platform lets teams design, test, deploy, and govern custom agents through a drag-and-drop canvas, without requiring engineering resources.
The defining capability is cross-system execution. A single StackAI agent can connect workflows, data, and actions across enterprise applications such as Salesforce, Slack, SharePoint, Snowflake, Google Workspace, and Oracle, pulling information from one system, synthesizing it, and triggering work in another. A compliance agent, for example, might pull contracts from a document store, check them against policy rules held in another system, and route flagged items to a channel for human review. The same pattern powers automations like customer-support triage, IT service requests, request intake, and task routing, often as multi-agent workflows that span several tools and domains.
Because its early customers came from heavily regulated sectors like financial services, healthcare, and professional services, StackAI was built with enterprise governance at its core. It offers controls to design, test, and govern agents through a structured deployment lifecycle, with the auditability and access management that make agent deployment viable where security and compliance matter, and it carries enterprise certifications including SOC 2 Type II, HIPAA, GDPR, and ISO 27001.
In May 2026, StackAI was acquired by Asana, which positioned the deal as the execution layer for its vision of an operating system for human-agent teams: StackAI reaches into the external systems where work happens, while Asana supplies business context, team workflows, and governance. StackAI continues to operate as its own product and brand following the acquisition, so it remains a distinct option for enterprises that need agents to act across the patchwork of tools their operations depend on, rather than only coordinating work inside a single application.
Vendor details
Canonical URL
https://www.stackai.com
Category
Agent builder
Company status
acquired
Use cases & customers
Target customers
Deployment options
In practice
Your process spans several systems: pull a contract from a document store, check it against rules in a CRM, and route exceptions for review. StackAI builds an agent that reads and acts across all of them, no code required.
You're in a regulated industry and can't deploy agents without auditability and compliance. StackAI offers governed agent deployment with access controls and certifications like SOC 2 Type II, HIPAA, GDPR, and ISO 27001.
Your team can plan work but your agents can't actually execute inside the tools where business runs. StackAI's no-code canvas connects agents to systems like Salesforce, Slack, and SharePoint to complete end-to-end workflows.
Capability coverage
11.5 / 14 capabilities · 82%
| Integrations & Tool CallingAgent Features research report + JSON Feature Rubric | Full |
|---|---|
| Workflow OrchestrationAgent Features research report + JSON Feature Rubric | Full |
| Knowledge Grounding & RAGAgent Features research report + JSON Feature Rubric | Full |
| Human Oversight & GuardrailsAgent Features research report + JSON Feature Rubric | Full |
| Security, Identity & GovernanceAgent Features research report + JSON Feature Rubric | Full |
| Observability & AuditabilityAgent Features research report + JSON Feature Rubric | Full |
| Memory & State PersistenceAgent Features research report + JSON Feature Rubric | Partial |
| Deployment & Data ResidencyAgent Features research report + JSON Feature Rubric | Full |
| Prebuilt Agents, Templates & PacksAgent Features research report + JSON Feature Rubric | Full |
| Triggers & Channel CoverageAgent Features research report + JSON Feature Rubric | Partial |
| Model Flexibility & RoutingAgent Features research report + JSON Feature Rubric | Full |
| APIs, SDKs & MCP ExtensibilityAgent Features research report + JSON Feature Rubric | Full |
| Testing, Debugging & OptimizationAgent Features research report + JSON Feature Rubric | Partial |
| Browser & Computer UseAgent Features research report + JSON Feature Rubric | Unable to verify |
Recent platform changes
Stack AI's E2B partnership now powers sandboxed Custom Code, Computer Use/RPA replay, and Browser Use on the StackAI platform.
View sourceStackAI introduced a Box integration for knowledge bases, workflows, conversational assistants, triggers, and write-back to Box. Also published a deployment-options guide covering multi-tenant cloud, dedicated cloud, private cloud/BYOC, and on-premise.
View sourceStackAI January release added human-in-the-loop, custom RBAC, SDLC environments, node run results, OpenAI web search, and multiple integrations.
View sourcePricing
Free (500 runs/mo) · Enterprise custom (per-seat)
runs
Included quota
Free ($0/mo): 500 runs/month, 2 projects, 1 seat, all core modules (Agents, Flow, Storage), multi-modal I/O, code/Python/JS logic, data loaders (web scraping, file upload, Google Drive, Notion), REST API, Slack bot, knowledge bases, document readers (PDF/Word/PPT), Discord community support. Enterprise (custom): custom runs + seats, unlimited projects, all features + data loaders, dedicated infrastructure, dedicated solution/forward-deployed engineers, on-prem + VPC deployment (AWS/Azure/GCP via Kubernetes), SSO (Okta/Azure AD/Google), RBAC/access control, audit logs, PII masking, data residency, SOC 2 Type II/HIPAA/GDPR/ISO 27001, HIPAA BAA, priority/dedicated support, custom domain.
What is public
StackAI (stackai.com - enterprise no-code AI-agent / workflow builder, 'made by PhDs at MIT') publishes just TWO tiers on its pricing page: Free ($0/mo - 500 runs/month, 2 projects, 1 seat, Discord community support) and Enterprise (custom - custom runs + seats, unlimited projects, all features/data loaders, dedicated infrastructure + solution engineers, on-prem/VPC deployment, SSO, access control, SOC 2/HIPAA/GDPR, BAA). There is NO public self-serve paid mid-tier - anything beyond the free plan is a custom Enterprise quote (per-seat, sales-led). Billing is by 'runs' (agent/workflow executions).
Billing mechanics
Two published tiers only. Free is hard-capped at 500 runs/month, 2 projects, 1 seat. Enterprise is custom-quoted - billed per seat with a custom run allowance, scoped to your team size, feature needs, and deployment (multi-tenant cloud / dedicated cloud / VPC / on-prem). A 'run' is one execution of an agent/workflow. Enterprise unlocks dedicated infrastructure, a forward-deployed engineer, and the full governance/security stack; the free plan is for evaluation only.
Cost watchouts
Only two tiers - a 500-run free plan and custom Enterprise - so any real production use jumps straight to a sales-led Enterprise quote (poor fit for solo/self-serve buyers); third-party implementation costs are significant (estimates: $2K-$10K setup for SMBs, $10K-$50K enterprise; plus data-integration, RAG/knowledge-base, and custom-agent-build services); HIPAA BAA is Enterprise-only (free/any non-Enterprise use can't process PHI); LLM/model usage is on top (BYO keys, model-agnostic routing)
Variable cost rationale
Run-metered - the free plan is fixed at 500 runs/mo, and Enterprise run allowances are contract-negotiated; on top of platform runs you pay LLM model usage separately (BYO keys), so cost scales with run volume x model choice plus seat count
Additional watchouts
Only free + custom Enterprise - no public self-serve paid tier, so non-enterprise buyers hit a wall after 500 free runs/mo; Enterprise pricing is opaque (scoping call required); meaningful implementation/services costs on top of license; HIPAA BAA gated to Enterprise; some third-party 'Pro $199' / higher-free-quota claims are stale vs the current official page
Overage / add-ons
Free is hard-capped (500 runs/mo, 2 projects, 1 seat) - exceeding it means moving to a custom Enterprise plan (no self-serve paid upgrade path); Enterprise run allowances and seats are negotiated in the contract.
Sales call required
Mixed (some tiers require a call)
Free / trial
Free
Lowest paid plan
n/p
Commercial notes
Enterprise-first no-code agent builder (drag-and-drop visual canvas, RAG pipelines, multi-agent orchestration, 8 layers of governance); 'made by PhDs at MIT'; trusted by regulated/enterprise names (BAE Systems, Mayo Clinic, MIT, Nubank, Live Oak Bank, Raiffeisen, Voya, City of Santa Monica, Goodwill); positioned between Relevance AI (agent focus) and n8n/Make (workflow focus); competes with Flowise (OSS self-host), n8n, Make, Relevance AI
Key ambiguities
The official page shows ONLY Free + Enterprise - some third-party listings cite a 'Pro $199/mo (25,000 credits)' mid-tier and varying free quotas (2,000 credits or 10k runs), but these are NOT on the current official pricing page (Free is 500 runs/mo); Enterprise is fully custom (third-party estimates ~$50-$500/user/mo, unverified); StackAI measures usage in 'runs' while some sources translate to 'credits'
Cancellation / refund
Free plan (no card, 500 runs/mo, Discord support); Enterprise is custom-contracted (per-seat, annual, scoped via a demo/quote) - no self-serve paid checkout; on-prem/VPC options for needs; book a demo to scope Enterprise
Support SLA / resale
Community support on Discord (Free); Enterprise adds email to priority to dedicated support, a dedicated forward-deployed/solution engineer, 24/7 live support, SSO, RBAC, audit logs, on-prem/VPC, and a HIPAA BAA; 100+ native OAuth integrations (SharePoint, Salesforce, Workday, SAP, ServiceNow, HubSpot, Jira, NetSuite, S3, Slack, Teams); model-agnostic (OpenAI/Anthropic/Google/local, BYO keys)
Missing data
Enterprise pricing is fully custom (third-party estimates ~$50-$500/user/mo + $2K-$50K implementation, unverified). The official page shows only Free (500 runs/mo, 2 projects, 1 seat) and Enterprise - no public mid-tier (a 'Pro $199/mo' some third-parties cite is not on the current official page). Enterprise is unlimited/custom with on-prem/VPC options.
Related vendors
- Lindy — No-code AI agent builder focused on automating repetitive business…
- Activepieces — Open-source automation platform with a self-hosted Community Edition…
- Adopt AI — No code agent builder that turns existing applications and manual…
- Agent.ai — A marketplace and network of hundreds of prebuilt AI agents plus a…
- AgentX — No code platform to build, evaluate, and deploy multi agent…
- AI Library — No code enterprise AI platform to build and run AI agents across the…