# Envelope > Envelope designs your multi-agent workflow. Describe what you need, get a complete AI agent design — roles, skills, models, tools, and handoffs — and export without code. Full content index (writing, blog, docs, guides, pricing, tools, roles, library, schema, MCP): https://openenvelope.org/llms-full.txt Per-page Markdown: Append `.md` to any page URL to get a clean plain-text version, e.g. https://openenvelope.org/docs/schema.md or https://openenvelope.org/writing/composable-ai-thesis.md Envelope is where multi-agent workflows get designed before they get built. Non-technical stakeholders describe what they need in plain language; Envelope structures it into a complete AI agent design — roles, skills, models, tool access, and handoffs. The output is a structured, exportable spec — no code required to design, no ambiguity when handing off. ## Homepage [Envelope](https://openenvelope.org/): The multi-agent generator. Users describe their AI workflow in natural language; Envelope structures it into a complete AI agent design — roles, skills, models, tool access, handoffs, and access policies — which can be exported as a structured JSON spec. Free to start. Designs can be shared via read-only link, exported to JSON, or handed off to an engineering team for implementation. ## For agencies [Envelope for Agencies](https://openenvelope.org/agencies): Dedicated landing page for agencies — marketing, dev shops, and consulting firms — who want to design and deliver AI agent workflows to clients. Covers the three-step flow (design → spec → hand off to client IT), use cases by agency type, and the multi-client workspace model. Positioned as the multi-agent generator for agencies building AI retainers and recurring AI workflow deliverables. ## Pricing [Pricing](https://openenvelope.org/pricing) — [Markdown](https://openenvelope.org/pricing.md): All plans are free during beta. Plans: Free ($0 — 5 saved designs, canvas, JSON export, share link, MCP server access), Pro ($9/mo — unlimited designs, version history, REST API access), Team ($39/mo — collaborators up to 10 seats, GitHub publish, org-wide design library), Enterprise (custom — SSO, private cloud, audit log). Founding Member lifetime deal available: $99 one-time for permanent Team access. Pricing kicks in after beta. ## Free tools [AI Agent Spec Validator](https://openenvelope.org/validator): Free tool. Upload or paste a `.envelope.json` agent spec and get an instant score across security, role clarity, structure, completeness, and model hygiene — plus AI feedback on prompts. No sign-in required to run a check. Free to use. ## Key concepts - **Design** — the act of describing and structuring AI agents: naming roles, assigning tools, defining reporting lines, and setting access rules. Input is natural language; output is a structured JSON spec. - **Spec / team definition** — the structured JSON output of a design session. Follows the open Envelope schema. Readable by engineers, storable in Git, directly implementable. - **Agent role** — a named function in the team (e.g. "Lead Researcher", "Triage Agent") with a defined scope, tool access, model preference, and reporting relationship. - **Tool** — a connected service or API an agent can use (HubSpot, Slack, GitHub, Stripe, and 500+ more). Tool assignments are declared in the design, credentials are provided at implementation time. - **Reporting line** — the hierarchical relationship between agents in the team. Defines who delegates to whom and how outputs flow through the pipeline. - **Access policy** — per-agent outbound HTTP access controls. Declared in the design; enforced at runtime by the implementing platform. - **Human gate** — a checkpoint where a human must review or approve before the pipeline continues. Declared in the design at key decision points. - **Version** — designs are versioned. Each published version is immutable; editors work on drafts. Existing implementations keep running until upgraded. - **Export** — the design is exported as a JSON file following the open Envelope schema. This is the handoff artifact for IT teams. - **Handoff** — the process of passing the exported spec to an IT or engineering team for implementation on their chosen runtime. ## Open schema The Envelope schema is an open specification (Apache 2.0). Any platform can implement a conforming runtime. The schema `$id` is `https://schema.openenvelope.org/team/v1.json`. Designers don't need to know the schema — Envelope produces it automatically on export from the natural-language design session. - [Schema reference](https://openenvelope.org/docs/schema) — [Markdown](https://openenvelope.org/docs/schema.md): Full field-by-field reference for the `envelope-team` JSON schema — all fields, types, constraints, and examples. - [Schema versioning policy](https://openenvelope.org/docs/schema/versioning-policy) — [Markdown](https://openenvelope.org/docs/schema/versioning-policy.md): How the schema evolves, what counts as a breaking change, version lifecycle. ## REST API [API reference](https://openenvelope.org/api-docs) — [Markdown](https://openenvelope.org/api-docs.md): Interactive REST API reference for Envelope. Call agents over HTTP, authenticate with an API key, pass conversation threads, and get responses. Available on Pro and Team plans. Covers authentication, all endpoints, request/response shapes, and error codes. ## Agent integration - [Envelope Skill](https://openenvelope.org/SKILL.md): Operating manual for AI agents — when to use Envelope, how to authenticate, the discover → generate → confirm → save workflow, gate handling, and rules (confirm before writing, never handle secrets, discover before creating). - [MCP server](https://openenvelope.org/docs/mcp) — [Markdown](https://openenvelope.org/docs/mcp.md): Connect to Envelope tools through MCP at `https://mcp.openenvelope.org/api/mcp`. Covers all 16 tools: list installs, run team, continue/reject gates, generate team, create team, update team, install, model routing, and more. - [Claude Code plugin](https://openenvelope.org/docs/claude-code) — [Markdown](https://openenvelope.org/docs/claude-code.md): Install the Envelope skill in Claude Code — teaches Claude to generate valid `.envelope.json` team definitions from plain-English descriptions. ## MCP & Claude Code Envelope runs a hosted MCP server at `https://mcp.openenvelope.org/api/mcp`. Connect it to Claude.ai or ChatGPT to work with your designs from any conversation. - [Connect to Claude.ai](https://openenvelope.org/guides/claude-ai) — [Markdown](https://openenvelope.org/guides/claude-ai.md): Add Envelope as a custom connector in Claude.ai — browse designs, export specs, and manage your team library from Claude conversations. - [Connect to ChatGPT](https://openenvelope.org/guides/chatgpt) — [Markdown](https://openenvelope.org/guides/chatgpt.md): Add Envelope as an app in ChatGPT via OAuth. Requires ChatGPT Plus, Team, or Enterprise. - [MCP Reference](https://openenvelope.org/mcp) — [Markdown](https://openenvelope.org/mcp.md): Interactive reference for all MCP tools — live curl examples, auth setup, error codes. - [Claude Code plugin](https://openenvelope.org/claude-code): Install the Envelope skill in Claude Code — teaches Claude to generate valid `.envelope.json` team definitions from plain-English descriptions. - [MCP documentation](https://openenvelope.org/docs/mcp) — [Markdown](https://openenvelope.org/docs/mcp.md): Full MCP server docs — tool list, auth, install instructions for Claude.ai and ChatGPT. - [Claude Code documentation](https://openenvelope.org/docs/claude-code) — [Markdown](https://openenvelope.org/docs/claude-code.md): Docs for the Claude Code plugin — what it does, how to install, usage examples. ## Blog - [From ops tool to design tool: why we pivoted](https://openenvelope.org/blog/design-tool-pivot) — [Markdown](https://openenvelope.org/blog/design-tool-pivot.md): The story of Envelope's pivot from an AI ops platform to a design tool — why the design-first framing unlocks a bigger market, and what the product looks like now. - [How agencies are productizing AI in 2026](https://openenvelope.org/blog/agencies-productizing-ai) — [Markdown](https://openenvelope.org/blog/agencies-productizing-ai.md): Practical guide for agencies packaging AI agent workflows as named monthly retainer deliverables. Covers the leverage play, delivery problem, and how Envelope solves it with reusable design templates. - [Run your Envelope teams from Claude and ChatGPT](https://openenvelope.org/blog/mcp-install) — [Markdown](https://openenvelope.org/blog/mcp-install.md): MCP server launch post — install steps for both clients, what each tool does, and the Claude Code skill. - [Schema launch](https://openenvelope.org/blog/schema-launch) — [Markdown](https://openenvelope.org/blog/schema-launch.md): The launch of the open Envelope schema — the open standard for agent definitions. ## Documentation - [Schema specification](https://openenvelope.org/docs/schema) — [Markdown](https://openenvelope.org/docs/schema.md): Full reference for the `envelope-team` JSON schema — all fields, types, constraints, and examples. Includes AgentDefinition, AccessPolicy, HumanGate, Schedule, and webhook event types. - [Ecosystem overview](https://openenvelope.org/docs/ecosystem) — [Markdown](https://openenvelope.org/docs/ecosystem.md): The builder/deployer model, NPM packages, and CLI tooling for engineers implementing Envelope specs. - [Platform integrations](https://openenvelope.org/docs/platforms) — [Markdown](https://openenvelope.org/docs/platforms.md): Supported runtimes for implementing an Envelope spec — Paperclip, Amazon Bedrock, Relevance AI, Envelope Managed, CrewAI, LangGraph, Vertex AI, Azure AI Foundry. - [Versioning](https://openenvelope.org/docs/versioning) — [Markdown](https://openenvelope.org/docs/versioning.md): How design versioning works — creating drafts, publishing without disrupting live implementations, rolling back. - [Access policy](https://openenvelope.org/docs/access-policy) — [Markdown](https://openenvelope.org/docs/access-policy.md): Per-agent network access controls — allowlist/denylist rules by hostname, method, and path prefix. - [Security & data flow](https://openenvelope.org/docs/security) — [Markdown](https://openenvelope.org/docs/security.md): What data reaches Envelope and what stays on your infrastructure. ## Guides - [Guides overview](https://openenvelope.org/guides): Index of all setup and how-to guides. - [Connect Claude.ai](https://openenvelope.org/guides/claude-ai) — [Markdown](https://openenvelope.org/guides/claude-ai.md): Add Envelope as a custom connector in Claude.ai — browse designs, export specs, and manage your team library from any conversation. - [Connect ChatGPT](https://openenvelope.org/guides/chatgpt) — [Markdown](https://openenvelope.org/guides/chatgpt.md): Add Envelope as an app in ChatGPT via OAuth. Requires ChatGPT Plus, Team, or Enterprise. - [Reading a spec](https://openenvelope.org/guides/reading-a-spec): How to read and interpret an exported agent spec — fields, agent structure, and handoff logic. - [Deploying from a spec](https://openenvelope.org/guides/deploying-from-spec) — [Markdown](https://openenvelope.org/guides/deploying-from-spec.md): How to hand off an exported spec to an engineering team or runtime for implementation. - [Git storage](https://openenvelope.org/guides/git-storage) — [Markdown](https://openenvelope.org/guides/git-storage.md): How to connect a GitHub repository so designs are stored and versioned there. - [Tool credentials](https://openenvelope.org/guides/tool-credentials) — [Markdown](https://openenvelope.org/guides/tool-credentials.md): How to add credentials for connected tools (HubSpot, Slack, GitHub, etc.) so agents can access them at runtime. ## Team library [AI agent library](https://openenvelope.org/library) — [Markdown](https://openenvelope.org/library.md): Browse public AI agent designs built on Envelope. Fork any team into your workspace and adapt it to your stack — free to start. ## Writing Envelope publishes practical guides and essays on multi-agent design, AI workflow automation, and the case for open standards. ### Topic hubs - [AI agents by team](https://openenvelope.org/writing/topics) — [Markdown](https://openenvelope.org/writing/topics.md): Index of all topic hub pages — links to the finance, HR, sales, and support hubs; entry point for browsing guides by business function. - [AI agents for finance teams](https://openenvelope.org/writing/finance) — [Markdown](https://openenvelope.org/writing/finance.md): Hub page for finance automation — links to all guides covering month-end reporting, invoice triage, budget monitoring, AP automation, and governance for financial AI agents. - [AI agents for HR teams](https://openenvelope.org/writing/hr) — [Markdown](https://openenvelope.org/writing/hr.md): Hub page for HR automation — links to all guides covering CV screening, employee onboarding, policy helpdesk, performance review prep, and offboarding agents. - [AI agents for sales teams](https://openenvelope.org/writing/sales) — [Markdown](https://openenvelope.org/writing/sales.md): Hub page for sales automation — links to all guides covering pipeline monitoring, account research, ICP scoring, lead enrichment, and CRM automation for Salesforce and HubSpot. - [AI agents for support teams](https://openenvelope.org/writing/support) — [Markdown](https://openenvelope.org/writing/support.md): Hub page for support automation — links to all guides covering ticket triage, first-response drafting, escalation monitoring, and quality review. - [The anatomy of a multi-agent](https://openenvelope.org/writing/anatomy-multi-agent) — [Markdown](https://openenvelope.org/writing/anatomy-multi-agent.md): What a multi-agent actually is — sub-agents, model routing, ordered vs. concurrent pipelines, human gates, and the design step that makes it all work. Foundational reference. - [The stitching problem](https://openenvelope.org/writing/stitching-problem) — [Markdown](https://openenvelope.org/writing/stitching-problem.md): Why most multi-agent systems fail at the connections between agents, not inside them — and why the fix is a design decision, not a better model or smarter prompt. - [What is AI workflow automation?](https://openenvelope.org/writing/ai-workflow-automation) — [Markdown](https://openenvelope.org/writing/ai-workflow-automation.md): How AI workflow automation differs from traditional automation (Make, Zapier, n8n), why AI agents change the model, and what good multi-agent workflow design looks like. - [AI agent memory: how agents remember context across tasks](https://openenvelope.org/writing/ai-agent-memory) — [Markdown](https://openenvelope.org/writing/ai-agent-memory.md): Agents don't remember by default. In-context, external, and procedural memory explained — when to use each and what to store. - [AI agents vs automation: when to use each](https://openenvelope.org/writing/ai-agents-vs-automation) — [Markdown](https://openenvelope.org/writing/ai-agents-vs-automation.md): Automation follows rules; agents make decisions. When to use each, where each breaks down, how they work together, and a decision guide. - [How to design an AI workflow before you build it](https://openenvelope.org/writing/design-ai-workflow) — [Markdown](https://openenvelope.org/writing/design-ai-workflow.md): Step-by-step process for designing a multi-agent workflow from objective to spec — agents, roles, tools, handoffs, pipeline structure, gates, and model assignments — before writing any code. - [Model routing in multi-agent workflows](https://openenvelope.org/writing/model-routing) — [Markdown](https://openenvelope.org/writing/model-routing.md): Why different agents in the same system should run on different AI models, how to match each role to the right model, and what model routing looks like in a worked example. - [AI agents need managers too](https://openenvelope.org/writing/ai-agents-need-managers) — [Markdown](https://openenvelope.org/writing/ai-agents-need-managers.md): Why governance is the infrastructure that makes AI agent delegation safe — defined scope, role-based access, audit trail, human gates. - [The model path won't solve coordination](https://openenvelope.org/writing/model-path-governance) — [Markdown](https://openenvelope.org/writing/model-path-governance.md): Better models won't solve the coordination problem. The execution layer is the governance layer. - [Why open standards matter for AI infrastructure](https://openenvelope.org/writing/open-standards-ai-infrastructure) — [Markdown](https://openenvelope.org/writing/open-standards-ai-infrastructure.md): The case for an open definition format for AI agents — portability, validators, registries. - [The platform trap in AI](https://openenvelope.org/writing/platform-trap-in-ai) — [Markdown](https://openenvelope.org/writing/platform-trap-in-ai.md): Choosing an orchestration platform is a format choice. Closed formats create lock-in denser than normal infra. - [Credentials, trust and the AI operator problem](https://openenvelope.org/writing/credentials-trust-operator-problem) — [Markdown](https://openenvelope.org/writing/credentials-trust-operator-problem.md): The three-party credential structure, access policy as enforcement, human gates for irreversible actions. - [Human in the loop and the autonomous agent problem](https://openenvelope.org/writing/hitl-autonomous-agent-problem) — [Markdown](https://openenvelope.org/writing/hitl-autonomous-agent-problem.md): Why keeping humans in the loop matters even as agents grow more capable. - [What makes a good agent role definition](https://openenvelope.org/writing/agent-role-definition) — [Markdown](https://openenvelope.org/writing/agent-role-definition.md): Roles vs prompts, agent scope and hierarchy, capabilities as constraints. - [The composable AI thesis](https://openenvelope.org/writing/composable-ai-thesis) — [Markdown](https://openenvelope.org/writing/composable-ai-thesis.md): Why composable, narrow multi-agent teams outperform monolithic agents. - [Narrow by design](https://openenvelope.org/writing/narrow-by-design) — [Markdown](https://openenvelope.org/writing/narrow-by-design.md): The argument for building multi-agent teams from narrow, specialised agents. ## Community [Envelope Community](https://openenvelope.org/community): The Envelope Discord — where designers, PMs, and engineers discuss AI agent design, share what they've built, and get help. Channels include #schema-discussion, #design-help, #showcase, and #platform-integrations. ## Templates by tool Envelope has dedicated pages for every supported integration, listing community designs that use that tool. Append `.md` to any tool URL for a clean plain-text version (e.g. https://openenvelope.org/tools/hubspot.md). - [HubSpot AI agents](https://openenvelope.org/tools/hubspot) — [Markdown](https://openenvelope.org/tools/hubspot.md) - [Slack AI agents](https://openenvelope.org/tools/slack) — [Markdown](https://openenvelope.org/tools/slack.md) - [Zendesk AI agents](https://openenvelope.org/tools/zendesk) — [Markdown](https://openenvelope.org/tools/zendesk.md) - [Salesforce AI agents](https://openenvelope.org/tools/salesforce) — [Markdown](https://openenvelope.org/tools/salesforce.md) - [GitHub AI agents](https://openenvelope.org/tools/github) — [Markdown](https://openenvelope.org/tools/github.md) - [Linear AI agents](https://openenvelope.org/tools/linear) — [Markdown](https://openenvelope.org/tools/linear.md) - [Stripe AI agents](https://openenvelope.org/tools/stripe) — [Markdown](https://openenvelope.org/tools/stripe.md) - [Notion AI agents](https://openenvelope.org/tools/notion) — [Markdown](https://openenvelope.org/tools/notion.md) - [Jira AI agents](https://openenvelope.org/tools/jira) — [Markdown](https://openenvelope.org/tools/jira.md) - [Gmail AI agents](https://openenvelope.org/tools/gmail) — [Markdown](https://openenvelope.org/tools/gmail.md) - [Intercom AI agents](https://openenvelope.org/tools/intercom) — [Markdown](https://openenvelope.org/tools/intercom.md) - [Freshdesk AI agents](https://openenvelope.org/tools/freshdesk) — [Markdown](https://openenvelope.org/tools/freshdesk.md) - [Airtable AI agents](https://openenvelope.org/tools/airtable) — [Markdown](https://openenvelope.org/tools/airtable.md) - [Asana AI agents](https://openenvelope.org/tools/asana) — [Markdown](https://openenvelope.org/tools/asana.md) - [Pipedrive AI agents](https://openenvelope.org/tools/pipedrive) — [Markdown](https://openenvelope.org/tools/pipedrive.md) - [Discord AI agents](https://openenvelope.org/tools/discord) — [Markdown](https://openenvelope.org/tools/discord.md) - [Twitter/X AI agents](https://openenvelope.org/tools/twitter) — [Markdown](https://openenvelope.org/tools/twitter.md) - [Shopify AI agents](https://openenvelope.org/tools/shopify) — [Markdown](https://openenvelope.org/tools/shopify.md) - [Twilio AI agents](https://openenvelope.org/tools/twilio) — [Markdown](https://openenvelope.org/tools/twilio.md) - [ClickUp AI agents](https://openenvelope.org/tools/clickup) — [Markdown](https://openenvelope.org/tools/clickup.md) - [Monday AI agents](https://openenvelope.org/tools/monday) — [Markdown](https://openenvelope.org/tools/monday.md) - [Microsoft AI agents](https://openenvelope.org/tools/microsoft) — [Markdown](https://openenvelope.org/tools/microsoft.md) - [SendGrid AI agents](https://openenvelope.org/tools/sendgrid) — [Markdown](https://openenvelope.org/tools/sendgrid.md) ## Role landing pages Envelope has pages for common agent roles in AI agent designs. Append `.md` to any role URL for a clean plain-text version (e.g. https://openenvelope.org/roles/sales.md). - [Sales roles](https://openenvelope.org/roles/sales) — [Markdown](https://openenvelope.org/roles/sales.md) - [Support roles](https://openenvelope.org/roles/support) — [Markdown](https://openenvelope.org/roles/support.md) - [Engineering roles](https://openenvelope.org/roles/engineering) — [Markdown](https://openenvelope.org/roles/engineering.md) - [Marketing roles](https://openenvelope.org/roles/marketing) — [Markdown](https://openenvelope.org/roles/marketing.md) - [Operations roles](https://openenvelope.org/roles/operations) — [Markdown](https://openenvelope.org/roles/operations.md) - [Finance roles](https://openenvelope.org/roles/finance) — [Markdown](https://openenvelope.org/roles/finance.md) - [HR roles](https://openenvelope.org/roles/hr) — [Markdown](https://openenvelope.org/roles/hr.md)