> ## Documentation Index > Fetch the complete documentation index at: https://docs.major.build/llms.txt > Use this file to discover all available pages before exploring further. # Platform Agent > The AI assistant in the Major web app that builds apps, agents, skills, and workflows and answers questions about your data. The Platform Agent is the AI assistant you chat with in the [Major web app](/learn/web-app). Describe what you want and it plans the work, asks for approval where needed, and builds it: apps, agents, skills, and workflows. It can also query your connectors directly to answer questions about your data. ## Example requests * "How many deals did we close last quarter, by region?" * "Build an app that tracks open support tickets from our Postgres database." * "Create an agent that posts a summary of new Salesforce leads to #sales every morning." * "Write a skill that explains how our billing tables fit together." * "Make a workflow that runs the lead-scoring agent whenever a new Attio record is created." * "Add a date filter to the revenue dashboard and deploy it." ## What it can do | Capability | What it does | | - | - | | **Answer data questions** | Queries your [connectors](/learn/connectors/overview) and replies in the chat. For bulk work, such as paging through a full history, it writes and runs a script instead of calling tools one page at a time. | | **Build apps** | Creates and edits full-stack [apps](/learn/apps/overview) in a sandbox with a live preview, then deploys them. | | **Build agents** | Drafts an [agent's](/learn/agents/overview) prompt, attaches the connectors, apps, and skills it needs, and saves and publishes it. | | **Build skills** | Writes [skills](/learn/skills/overview) that agents load on demand. | | **Build workflows** | Builds [workflows](/learn/workflows/overview) and their [triggers](/learn/triggers/overview), and runs them to test. | | **Use what exists** | Calls your deployed apps' APIs, runs agents and workflows, and opens a deployed app in a side panel. | | **Set things up** | Asks you to add a connector, sign in to one, or enter an app's environment variables when the work needs it. | ## How it works ### Plans For complex, ambiguous, or long-running requests, the Platform Agent tells you its approach before it starts, or asks a question when there are meaningfully different ways to do the work. The mode selector in the chat composer has two modes: * **Auto** - the Platform Agent works through the request and pauses only for approvals. * **Plan** - the Platform Agent researches and writes a plan first. It appears as a **Plan review** card; click **Accept plan** to let it proceed, or **Decline plan** to redirect it. ### Sandboxes Apps, agents, skills, and workflows are each edited on a sandbox attached to the chat. Several can be attached at once, so one conversation can build an app and the agent it calls. A sandbox is held by one person at a time; if someone else is editing the same item, the Platform Agent tells you it is locked. Chats you start from an item's editor are pinned to that item, and its sandbox starts automatically. ### Tool cards Each action the Platform Agent takes appears in the conversation as a tool card, so you can see what it read, queried, edited, or ran. Plans, approvals, and setup requests appear as cards you act on directly. ## Approvals When the Platform Agent wants to use a tool that needs your sign-off, it shows a **Permission request** card with the tool name, the reason, and the arguments it will send. Choose: | Button | Effect | | - | - | | **Approve** | Run this call once. | | **Deny** | Block this call. The Platform Agent is told it was denied. | | **Always approve** | Run this call and save an always-allow rule for this tool in your chats. Offered for connector tools and app endpoints. | By default, read-only connector tools and app `GET` requests run without asking, and tools that write ask first. Actions such as running an agent or a database migration always ask. Manage your saved rules, or set **always allow**, **ask**, or **always deny** for any tool ahead of time, on the [Tool Permissions](/settings/tool-permissions) page. When you chat with a specific agent, that agent's [tool permissions](/learn/agents/tool-permissions) apply instead of yours. ## Models Pick a tier - **Smartest**, **Balanced**, or **Fastest** - from the model picker when you start a chat. Each tier maps to the model your organization configured for it. The model is fixed once the chat starts, and a chat with an agent uses that agent's model. Admins choose the model behind each tier in [Settings > Models](/settings/models). ## Conversation files Files the Platform Agent writes in its working directory, such as notes, scripts, and intermediate results, persist for the conversation, so you can pick up where you left off. ## Platform Agent and MCP The Platform Agent uses the same tools and skills as the [Major MCP server](/build/mcp). If you prefer to work in Claude Code, Codex, ChatGPT, Cursor, or another MCP client, connect it to Major and you get the same capabilities there. The main differences: | | Platform Agent | MCP client | | - | - | - | | **Where** | The Major web app | Your own AI client | | **Approvals** | Permission request cards and your [tool permissions](/settings/tool-permissions) | Your client's own tool approval settings | | **Connector and env var setup** | Setup forms open in the chat | You get a link to open in Major | ## Next steps Find your way around chat, apps, agents, and settings. Choose which tools run without asking in your chats. Get the same capabilities in your own AI client.