This guide is for people using AgentStack through the website (agentstack.tech): sign in, pick a project, and work in the dual-shell SPA (/user/* for operators, /dev/* for builders). It summarizes recent capabilities (RAG, CRM, Storefront Studio, sandboxes, access control) in plain language and points to deeper docs when you need API or automation details.
Language: This public documentation is English only.
Canonical routes: dual-shell/README.md (user vs dev hub) · Living Plane: docs.freshness.living.gen1
After you log in, open User or Dev shell and select a project. Surfaces you may see include:
| Surface | What you use it for |
|---|---|
| Overview / Discover | Project snapshot; capability map at /user/discover or /dev/discover |
| Project settings | Name, type, and project-level options |
| CRM | Contacts, companies, deals on the project (`/user |
| Assets / Storefront Studio | Catalog and studio seed (?mode=studio on assets) |
| Integrations / iPaaS | App Directory, OAuth connections, draft/live scenarios, DataMapper, runs |
| Agents / Bots | Fleet AI and bot studio |
| Support | Project support threads (staff/user) |
| RAG | Knowledge collections, ingest, semantic search, session memory |
| Storage / Sites | Files and hosted sites publish (/s/...) |
| Logic | Rules, triggers, flow editor |
| RBAC / Field access | Roles and response field masking |
| Docs cookbook | How-to hubs at /dev/docs/{build,scale,secure,operate,extend} |
Exact labels depend on your subscription and permissions.
Engineering passport (full shipped catalog for AI/investors): WHATS_NEW.md · monorepo FEATURES_SHIPPED
URL patterns (examples):
https://agentstack.tech/dev/projects/<projectId>/crm— CRM workspacehttps://agentstack.tech/dev/discover— capability discovery- Legacy
/dashboard/<projectId>?module=…may still redirect; prefer dual-shell paths above.
RAG (Retrieval-Augmented Generation) lets you attach searchable knowledge to a project: upload text, search by meaning, and (where enabled) keep a short memory of a conversation session so AI tools can stay on topic.
Typical workflow in the UI
- Open the project in Dev/User shell and go to the RAG surface (or Discover → RAG).
- Create a collection (a bucket for related documents).
- Add documents (text is chunked and indexed automatically).
- Run semantic search inside a collection.
- Optionally use session memory features if your workflow needs recent turns indexed for retrieval.
Limits depend on your subscription (collections, chunks, memory rows, etc.). If an action is blocked, check your plan or upgrade path on the site.
More detail (includes REST /api/rag/ and MCP for automations):*
RAG_PLATFORM_GUIDE.md
Sandboxes let you work in an isolated environment derived from your project: try changes, checkpoints, and (on supported plans) promotion flows back toward production — without replacing your live data blindly.
This is aimed at teams that need safe experimentation and controlled rollout. Day-to-day users may only see sandbox features if the product surface exposes them for your account.
Deeper technical guides (APIs, limits, flows):
- SANDBOX_PLAYGROUND_GUIDE.md — concepts, subscription gates, and patterns.
- SANDBOX_AND_ENVIRONMENTS.md — REST API and environment behaviour.
API reference: Swagger UI — look for Sandbox-related tags and OPENAPI.md.
AgentStack uses layered access:
- API keys — may be restricted to certain services (automation safety).
- Roles (RBAC) — who may open which parts of the product and call which APIs.
- Field Access Policy (FAP) — which fields appear in JSON for each role (read, mask, or hide).
As a project owner or admin, you may configure field access in the dashboard. As a member, you simply see what your role allows.
Readable overview: ACCESS_AND_FIELD_POLICY.md
Full policy format: FIELD_ACCESS_POLICY.md
CRM keeps contacts, companies, and deals on the active project. Open /user|dev/projects/<id>/crm. Automations can create contacts from webhooks or from checkout → CRM when an order completes.
Storefront Studio fills a product catalog / vitrine with low input (?mode=studio on assets): plan → apply → undo. Pair with Sites hosting for a public /s/... storefront.
Deeper: crm/README.md · how-to/crm/INTEGRATION_QUICKSTART.md
The Integration Hub (iPaaS) lets you:
- Browse the App Directory and install a starter
- Connect via OAuth (or API credentials where applicable)
- Author a scenario (draft → live) on the Logic canvas
- Map fields with DataMapper, run a dry test-step, then inspect runs
Natural-language “copilot” suggestions may appear as a preview — treat them as assistive, not a guaranteed LLM product.
Deeper: how-to/crm/INTEGRATION_QUICKSTART.md · support/INTEGRATION_QUICKSTART.md (integrations hub)
Publish static files or a ZIP to a live URL under /s/{project}/{bucket}/. Use Storage → Sites, the host-site public funnel, or MCP hosting.* from an IDE agent. The project hosting plane suggests next steps on the Host → Sell → Scale ladder.
Custom domains and guest publish-without-login are not general-availability marketing promises — see the capabilities matrix.
Deeper: hosting/HOSTING_GOLDEN_PATHS.md
Plans differ by projects, members, API usage, storage, RAG, sandbox features, support, and more.
Comparison table: subscription/SUBSCRIPTION_TIERS.md
Anonymous trial-style usage: subscription/ANONYMOUS_TIER.md
Pricing and billing UI: use agentstack.tech (Pricing / Billing). For raw API details, use Swagger.
The AI Builder may be presented as a demo of the ecosystem or temporarily unavailable on the public site. When it is off, use the rest of the dashboard, APIs, and MCP integrations for your workflows.
If you use MCP or plugins, start from the ecosystem index and the plugins list:
When you run more than one project (or work with partners who have their own AgentStack projects), ecosystem channels let you share named events and data-field updates across project boundaries—with access rules and a public field list so sensitive data stays internal.
In the product: open Project settings → Ecosystem to publish channels and manage grants. The marketing/docs site may also expose Ecosystem documentation at /ecosystem-docs.
Architecture and patterns (star, hub, B2B, multi-tenant, safety checklist):
ECOSYSTEM_API_IMPLEMENTATION.md
REST details and examples:
ECOSYSTEM_API_IMPLEMENTATION.md
| Topic | Document |
|---|---|
| Full doc index | README.md |
| Shipped features (detailed) | WHATS_NEW.md · FEATURES_SHIPPED (monorepo) |
| Ecosystem networks (cross-project) | ECOSYSTEM_API_IMPLEMENTATION.md |
| MCP + ecosystem index | MCP_AND_ECOSYSTEM.md |
| OpenAPI / Swagger | OPENAPI.md |
| REST API topics | api/README.md |