Emergent vs v0 by Vercel (2026)

The build agent wires outside services into each app in two ways. Integrations with a playbook follow a tested setup recipe for services such as Stripe, PayPal, Shopify, Razorpay, Paystack, SendGrid, Resend, Twilio, ElevenLabs and the OpenAI, Anthropic and Google models, and a few bill a small credit fee per run.

Anything else with a public API is coded in against the customer's own key. Teams can also register their own MCP servers under Manage Agents, giving the agent tools to read schemas, run queries, post to Slack or open Jira tickets while it builds. Servers are entered as JSON in the mcpServers format, and each tool list is cached for five minutes.

Sourcehelp.emergent.sh/connect-your-toolsread 2026-10-09

GitHub integration covers repository import, sync, branch creation and pull requests directly from chat, with environment variable import and one-click deployment to Vercel. Database and data platform connections include Supabase, Snowflake and Amazon services, designs import from Figma, and generation draws on the shadcn component registry, screenshots and attachments.

Vercel Connect adds scoped integrations for Slack, GitHub, Snowflake, Salesforce, Notion and Linear with any other service addable via OAuth or API, spanning chat, source control, data warehouse, CRM, documents and ticketing. The Platform API wraps the whole lifecycle for embedding into external tools, bots and pipelines.

SourceShip 2026 announcement 2026-06-17 and vercel.com/blog/build-your-own-ai-app-builder-with-the-v0-platform-api; businesswire.com/news/home/20260617093685/en/vercel-brings-new-agent-framework-full-stack-capabilities-and-enterprise-controls-to-its-agentic-infrastructure-platformread 2026-08-30

Every conversation runs as a long lived Temporal workflow in which the agent reasons, calls a tool, reads the result and repeats, up to 10,000 tool calls per message and four hours of wall clock time. A main agent plans the work and spawns subagents for testing, design, code review and integration setup, which run in parallel workflows and report back.

Three agents set the workflow when a job starts: E-1 builds step by step, E-2 checks that the pieces it builds fit together, and E-3 runs E-1 as a subagent under its own loop for large, open ended goals. Runs end on named stop reasons such as end_turn, handoff, max_iterations and insufficient_credits, and a handoff passes the task to another agent.

Sourcehelp.emergent.sh/how-the-agent-runs-workflow-stop-reasonsread 2026-10-09

Work in v0 is delegated to subagents, which draw on v0 credits along with other supporting agent work even when a ChatGPT plan covers the main responses. Its sandboxes ship pre-installed coding agents such as Claude Code that run inside the project, routed through the AI Gateway under the team's model rules. Within a chat the agent plans, generates, runs a live dev server, opens branches and pull requests and deploys.

Sourcev0.app/docs (ChatGPT plan, pre-installed agents, agentic features)read 2026-09-29

Work reaches the builder when a person sends a message. A builder picks an app type (Full Stack App, Mobile App, Landing Page or Brainstorm), chooses an agent and types a prompt in the web workspace at app.emergent.sh or its mobile web app, and a new job can also start from an imported GitHub repository. In Plan mode the build waits until the plan is approved. On the self serve plans nothing starts a build on a schedule, a webhook or an event, so the agent works only while someone is driving it. The apps it makes can run scheduled jobs of their own once published.

Sourcehelp.emergent.sh/start-with-your-idearead 2026-10-09

Users reach v0 through the v0.app web application and its in-browser editor, and programmatically through the Platform API. Vercel positions the API for embedding app generation into external tools, bots, command line tools, customer systems and custom agents, with sync, async and streaming execution as separate endpoints for interactive UIs or background pipelines, and chats can start from a GitHub repository, which Vercel presents as a sign it wants v0 in CI/CD. There is no event trigger, scheduled run or inbound chat or ticketing channel.

Sourcevercel.com/blog/build-your-own-ai-app-builder-with-the-v0-platform-api and the v0 Platform API v2 betaread 2026-08-30

Each build draws on the job's own material: the whole conversation, the workspace code and files, the database structure, the key names in .env, and files attached to chat such as screenshots, Figma exports, PDFs, CSVs and specs. MCP servers add schemas, documents and live rows from outside systems. Pro raises the context window to one million tokens, long chats are compacted automatically, and a fork starts from an editable summary of the history. Context is gathered for each run from these sources, and the builder keeps no searchable index of a company's wider documents.

Sourcehelp.emergent.sh/a-tour-of-the-workspaceread 2026-10-09

Generation is grounded in context the customer supplies. A chat can start from a prompt, source code, a GitHub repository or a ZIP archive, and v0 can import an existing repository with its environment variables and work on it as well as creating new projects. Designs import from Figma, screenshots and attachments are accepted as multimodal input, and the shadcn component registry and design system conventions shape the structure of the output. There is no codebase index, retrieval layer, dependency graph or reasoning across files.

Sourcevercel.com/blog/build-your-own-ai-app-builder-with-the-v0-platform-api and vercel.com/blog/introducing-the-new-v0read 2026-08-30

Each job keeps its chat, code and build state across sessions, so a builder can close the workspace and come back, and the agent reads the whole conversation on every turn. Workflow state persists in Temporal, so an interrupted run resumes where it left off, and a job paused at zero credits picks up again once the balance is topped up. Less carries between jobs.

A fork condenses the history into a summary the builder can edit, early details can fade after repeated compaction, and subagents start fresh on every turn. What the agent knows about a builder or team in a new job is whatever sits in the code, the forked summary or the files attached to chat.

Sourcehelp.emergent.sh/checkpoints-undo-anythingread 2026-10-09

Team Memories sit beside team skills in the workspace. Members with edit access, or only owners and selected members when an owner restricts it, create, edit and delete team memories that everyone on the team can view and use. Chats and projects persist and resume, and the agent keeps context of earlier actions within a conversation. The agent writes no memory of its own that lasts beyond the conversation.

Sourcev0.app/docs (team skills and Team Memories and Skills settings)read 2026-09-29

Plan mode, switched on in the composer, returns a plan card with two buttons, Request changes and Looks good, let's build it, and nothing is built until the builder approves.

Build mode, the default, starts as soon as a prompt is sent, Plan mode is unavailable in Brainstorm and E-3 sessions, and in autonomous runs a feature called Auto-HITL answers the agent's own questions with sensible defaults so the run never pauses.

Spending and release controls sit beside the plan step: a maximum credit cap per prompt that asks before going over, a budget per session, cancel from the chat menu, and a live app that changes only when someone publishes it again.

Sourcehelp.emergent.sh/talk-it-throughread 2026-10-09

v0's terminal permission layer has three modes that persist across chats. In Ask mode the customer's allow, ask and deny rules apply, and v0 asks for confirmation on anything marked ask or unmatched. Auto, the default, runs a built-in allow list of read-only commands and asks before others it judges need it. Full skips the checks. MCP tool calls follow the same Ask, Auto or Full mode and Agent Permissions rules, which decide whether a call runs, asks for confirmation or is blocked. Work then lands as Git branches and pull requests with preview deployments.

Sourcev0.app/docs (Permission modes; MCP availability and approval)read 2026-09-29

Projects have four roles. Owners control billing, plan and deletion, Admins manage settings, members, the database and domains, Members chat with the agent and publish, and Viewers, on Enterprise only, see the app and its history.

Business adds single sign on through SAML or OpenID Connect and role based access control, Enterprise adds user groups and workspace wide two factor enforcement, and anyone can review and revoke active sessions. Emergent holds ISO 27001:2022 and SOC 2 Type I, with GDPR alongside them in its trust center, and its DPA sets out technical measures, breach notice within 72 hours and audit reports on written request. Secrets are encrypted at rest and data in transit, and customer personal data is kept out of model training under the DPA.

Sourcehelp.emergent.sh/team-roles-permissions-collaborationread 2026-10-09

Vercel holds a SOC 2 Type 2 attestation for Security, Confidentiality and Availability, and v0 is in the scope of that report, with details at security.vercel.com. Its controls include SAML SSO on Enterprise, directory sync groups (for example Okta SCIM) mapped to Access Groups, v0 roles separate from Vercel deployment roles, team-owner control over who may edit team memories and skills, owner acceptance before custom models can be used, pre-installed agents disabled by default on Enterprise, and data opt-out on Business and Enterprise.

Sourcev0.app/docs (security and enterprise sections)read 2026-09-29

While an app builds, the workspace shows the agent's activity live: each tool call with the arguments passed and the result returned, subagent logs nested under the main agent that expand to show their own calls, the step count for the turn and the credits being spent.

A checkpoint is saved after every agent turn, publish history keeps up to three earlier production images tagged with a timestamp, and Account Settings breaks credit use down by agent runs, publishes and Universal Key calls. Enterprise adds audit logs and credit usage reports with an analytics dashboard. How long the Enterprise audit log keeps entries is unclear.

Sourcehelp.emergent.sh/custom-agentsread 2026-10-09

Vercel Connect carries full audit trails for each agent session's scoped token use, enterprise tiers offer audit logs and advanced analytics, and Vercel Agent correlates incidents to the deployment that caused them using traffic, traces and alerts. On the v0 surface, Git branches and pull requests plus preview deployments give a durable record of what was generated and shipped, and chats persist for review. These record credential use, deployments and code changes, not a step by step trace of the agent's own reasoning, and v0 keeps no replayable session record.

SourceShip 2026 announcement 2026-06-17 and vercel.com/blog/introducing-the-new-v0; businesswire.com/news/home/20260617093685/en/vercel-brings-new-agent-framework-full-stack-capabilities-and-enterprise-controls-to-its-agentic-infrastructure-platformread 2026-08-30

Emergent runs as a hosted service, and customer data is processed and stored in the United States, the EU and India under its DPA. Builders choose the hosting region of a published app themselves, US or EU, in the Resources tab of Manage Publishing, with the EU priced higher. App databases run on MongoDB Atlas in the United States unless moved.

Enterprise deploys apps into the customer's own cloud through a VPC setup and supports a self hosted database, and any published app can move to the customer's own MongoDB by a manual runbook. The build platform and its subprocessors stay where they are whatever region an app uses, and EU only hosting for all data goes through a request to the privacy team.

Sourcehelp.emergent.sh/where-your-data-is-storedread 2026-10-09

As a hosted service, v0 runs on Vercel's cloud. Generated code exports in full to a local machine or GitHub and deploys to Vercel, Business and Enterprise add data opt-out, and agent traffic stays with providers on Vercel's subprocessor list. There is no region list, customer environment or region selection for v0 itself. Vercel for Enterprise Apps and Agents can deploy inside a customer's own AWS account, but that covers the apps and agents customers deploy, and v0 generation is not said to run there.

Sourcev0.app/docs and vercel.com/blog/vercel-for-enterprise-apps-and-agentsread 2026-09-29

New jobs start from four app types, Full Stack App, Mobile App, Landing Page and Brainstorm, each on its own stack template (React with FastAPI and MongoDB, Next.js, Python only, or Expo for mobile), and from a choice of three build agents, E-1, E-2 and E-3, which are levels of one builder.

Integrations with a playbook package a tested setup recipe for each supported service, and the build page offers example prompts for websites, mobile apps, dashboards and SaaS tools. On Pro, builders make their own custom agents in a four step wizard covering the system prompt, tools and subagents. There is no gallery of finished apps or ready made agents to clone.

Sourcehelp.emergent.sh/how-apps-work-here-mental-modelread 2026-10-09

Generation draws on the shadcn component registry as a library of reusable, accessible React components, with design systems and project templates providing repeatable starting points, and the Platform API supports bring-your-own-context so teams can supply their own registries and conventions. Imported Figma designs act as further reusable inputs. v0 itself has no library of prebuilt agents, skills catalog, agent gallery or marketplace.

Sourcevercel.com/blog/introducing-the-new-v0 and vercel.com/blog/build-your-own-ai-app-builder-with-the-v0-platform-apiread 2026-08-30

Two choices shape a build. The agent dropdown sets the workflow, and a separate model selector picks the LLM that powers it, offered again when a fork opens, so a builder can move to another model when a provider slows down. Pro adds Ultra thinking and Maxx mode, a deeper reasoning toggle that costs significantly more credits.

Model providers in the data path include Anthropic, OpenAI, Google Gemini, xAI and Groq. The Universal LLM Key, which reaches 44 or more models from seven providers on Emergent credits or the customer's own provider keys, serves the apps being built rather than the builder.

Sourcehelp.emergent.sh/understanding-models-e1-e2-e3-maxxread 2026-10-09

A model picker in the chat composer lets users choose v0's own models or add custom models from the Vercel AI Gateway catalog, searched by model or provider, with reasoning effort and fast mode per model. On Enterprise, custom models unlock once a team owner allows them. Users can also connect a ChatGPT Plus or Pro plan to cover eligible responses from OpenAI models.

Sourcev0.app/docs (Choose a model, Add custom models, Enterprise model access)read 2026-09-29

Emergent also works as an MCP server for clients such as Claude Desktop or Cursor, with example tools that create an app from a prompt, publish a workspace and fetch build or runtime logs, and personal access tokens with scoped permissions reach an Emergent API. The server's address and full tool list are not given alongside those examples, so how much of the platform outside code can drive is unclear. On paid plans the Universal LLM Key also works as a LiteLLM compatible proxy for calling models from scripts and CI, restricted by IP, and code leaves through Save to GitHub.

Sourcehelp.emergent.sh/mcps-connectorsread 2026-10-09

The v0 Platform API gives programmatic access to the app generation pipeline through RESTful endpoints and a TypeScript SDK, covering creation and management of chats and projects.

The v2 public beta exposes the full app-building agent, not just a code endpoint, with VM-backed chats startable from a prompt, a GitHub repository or a ZIP archive, live dev server previews, follow-up messages, integrations and programmatic deployment to Vercel, and three execution modes offered as separate sync, async and streaming endpoints.

Vercel describes third parties building their own app builders, bots, command line tools and agents on it, and positions it for CI/CD pipelines. There is no MCP server.

Sourcevercel.com/changelog/v0-platform-api-now-in-beta and vercel.com/blog/build-your-own-ai-app-builder-with-the-v0-platform-apiread 2026-08-30

Testing sits in the agent's own toolset. A testing subagent, called through a run_tests tool or when a builder asks for it, writes unit, integration and end to end tests for the app, runs them and reports coverage, and when a test fails the agent fixes the code and runs the tests again.

E-2 adds a workflow that proves the services it builds actually work together, a Codex review subagent lints and scans pull requests for security and style, and testing runs include visual regression scans.

Builders can ask for specific checks, such as the checkout flow end to end, results show in chat with what failed and why, and mobile apps get TestFlight and APK test builds on paid plans.

Sourcehelp.emergent.sh/debugging-testing-with-the-agentread 2026-10-09

v0 generates code and runs it in a sandbox with live previews and a real dev server, so a person can see the application working before shipping, but there is no test generation, test execution, assertion, static analysis, evaluation harness or code quality engine. Evaluation is built into Vercel's separate eve agent framework, and Vercel Agent investigates production incidents, but neither is exposed through v0.

Sourcevercel.com/blog/introducing-the-new-v0 and v0.appread 2026-08-30

Agents can carry out tasks in a hosted web browser run by Browserbase, seeing and typing on pages, including ones the user is signed into, and content viewed or entered there is part of the data the platform processes. Firecrawl fetches web pages as a separate agent tool, and web search costs a small credit fee per query. Inside the app builder, the browser work Emergent describes is the preview server screenshotting the app under construction for the agent to check, so whether the builder drives the hosted browser on outside sites is unclear.

Sourceapp.emergent.sh/privacy-policyread 2026-10-09

Execution runs through programmatic surfaces throughout, namely a full-stack sandbox and, since v2, VM-backed chats running a real dev server with file operations, server actions and database connections, the GitHub API for branches and pull requests, and Vercel deployment APIs. Live previews render the generated application for a person to look at, not for the agent to operate. There is no browser control, screenshot capture, visual verification or way to operate software without a programmatic interface.

Sourcevercel.com/blog/introducing-the-new-v0 and the v0 Platform API v2 betaread 2026-08-30