# PlungeAI Guide > How to use PlungeAI: your account, and the guides to Agency, Consulting, Ocean Code and Ocean Build. - [PlungeAI Guide](https://www.plungeai.com/guide/get-started/overview.md): How to use PlungeAI: one account, then a guide for each product. Agency, Consulting, Ocean Code and Ocean Build. - [Sign in and your account](https://www.plungeai.com/guide/get-started/account.md): One PlungeAI account opens every product. Sign in at the door, www.plungeai.com/dashboard, with a code we email you, a passkey or your company's single sign-on. - [Your company and team](https://www.plungeai.com/guide/get-started/company-and-team.md): Every PlungeAI account acts for a company. Its owner and admins keep its details, domains and sign-in policy, invite members and decide what each role and each product lets them do. - [Billing](https://www.plungeai.com/guide/get-started/billing.md): How each PlungeAI product bills your company, and Settings › Billing: the wallet, top-ups and auto-recharge, invoices and refunds, payment methods, billing details, plans and limits. - [Getting help](https://www.plungeai.com/guide/get-started/getting-help.md): Ask a question, report a bug or request a feature or a connector in Requests at www.plungeai.com/request, and follow it to its answer. - [PlungeAI Agency](https://www.plungeai.com/guide/agency.md): How to use PlungeAI Agency: Agency Studio for clients, the Dashboard for the agency team, and how the system works underneath. - [For clients](https://www.plungeai.com/guide/agency/for-clients.md): How to use Agency Studio, your workspace at agency-studio.plungeai.com: brief us, review what we make, set your goals and budget, and manage your plan. - [Getting in](https://www.plungeai.com/guide/agency/for-clients/getting-in.md): You do not sign up in Agency Studio: the agency invites you. - [Welcome checklist](https://www.plungeai.com/guide/agency/for-clients/welcome-checklist.md): The Welcome page tracks your setup in a fixed order and links each step to the page where it happens. It also holds the two things you do yourself early on: connect Google and send your first brief. - [Your brand](https://www.plungeai.com/guide/agency/for-clients/your-brand.md): Everything we make reads your brand profile and your approved claims. The Brand page is where you check them and keep them current. - [Goals & budget](https://www.plungeai.com/guide/agency/for-clients/goals-and-budget.md): Only your approver sets these. The agency reads them and cannot change them. - [Sending a brief](https://www.plungeai.com/guide/agency/for-clients/sending-a-brief.md): A request is one brief. Approvers send it from Requests › New request (or from Welcome). - [Planned work](https://www.plungeai.com/guide/agency/for-clients/planned-work.md): Planned work is work we start for you on a rhythm, without a new brief each time. Your approver sets it on the Planned work page; everyone else reads it. It draws only on a monthly plan's included pieces; a card on file is never charged for it. - [Reviewing work](https://www.plungeai.com/guide/agency/for-clients/reviewing-work.md): Work reaches you after the automatic QA gate and a person at the agency. The Review page lists everything waiting for your decision, grouped by request. - [Assets, performance, publishing](https://www.plungeai.com/guide/agency/for-clients/assets-performance-publishing.md): Approved and published work, each piece with its disclosure line and its rights record. Usage rights are assigned to you on delivery. See AI disclosure and Rights. - [Your lead](https://www.plungeai.com/guide/agency/for-clients/your-lead.md): Your account lead is a named person at the agency. The sidebar card shows their name and reply time ("Replies within 24 hours" with the agency's default). - [Learnings](https://www.plungeai.com/guide/agency/for-clients/learnings.md): Once a month, from the month's first Monday at your digest hour, we write a note on what we learned on your account: the winning pieces, the revisions and their reasons, the tests that ran, and what is proposed next. Every number in it comes from your stored results. It is mailed to everyone in … - [Team & notifications](https://www.plungeai.com/guide/agency/for-clients/team-and-notifications.md): Your approver invites teammates by email as approver or viewer (up to 20 invites a day), sees who invited whom and whether an invite was accepted, and removes people. The last approver cannot be removed: invite another first. - [Trust & controls](https://www.plungeai.com/guide/agency/for-clients/trust-and-controls.md): Three switches your approver sets; everyone else reads them. - [Billing](https://www.plungeai.com/guide/agency/for-clients/billing.md): Your plan in Agency Studio: monthly retainer or per piece, starting it, change orders, failed payments, credits, the outcome fee option, referrals and billing groups. - [For the agency team](https://www.plungeai.com/guide/agency/for-the-agency-team.md): How to run the agency from the Dashboard at agency-dashboard.plungeai.com. You sign in with your PlungeAI account. An owner or admin adds you by email first, and the invite is linked to you the first time you sign in with that email. - [Roles](https://www.plungeai.com/guide/agency/for-the-agency-team/roles.md): There are five roles, ranked: owner above admin above strategist above reviewer above viewer. A role may do everything the roles below it may do. The table names the lowest role each action needs; the server checks it on every call, so a button you cannot use is also refused if you call the API. - [The daily loop](https://www.plungeai.com/guide/agency/for-the-agency-team/the-daily-loop.md): Most of the work runs by itself (see Production and The clock). Your day is the four places where the pipeline waits for a person, in this order. - [The Dashboard nav](https://www.plungeai.com/guide/agency/for-the-agency-team/the-dashboard-nav.md): The sidebar has twelve sections. Each page opens with an "About this section" note; this is the short version. - [Running a client](https://www.plungeai.com/guide/agency/for-the-agency-team/running-a-client.md): A client goes from lead to first request in this order. The client page's onboarding checklist shows the same steps with what is done. - [Requests](https://www.plungeai.com/guide/agency/for-the-agency-team/requests.md): The board shows one column per status, left to right: Proposed, Intake, Queued, In production, QA failed, Internal review, Client review, Revision, Approved, Published, Delivered, Cancelled. Every allowed move is drawn in the request lifecycle; a move outside it is refused. A client's brief … - [Brand operations](https://www.plungeai.com/guide/agency/for-the-agency-team/brand-operations.md): The brand work of the agency team: the website draft, claims, learned lines, the block list and brand kit, librarian proposals and versions. - [Billing operations](https://www.plungeai.com/guide/agency/for-the-agency-team/billing-operations.md): Plans, checkout links, invoices, refunds, the outcome fee, billing groups, referrals and the margin page, from the Dashboard. - [Settings](https://www.plungeai.com/guide/agency/for-the-agency-team/settings.md): An admin edits the agency settings: the quote limit ($25 by default), the margin floor (65%), the cost rates used in quotes, the revision fee, the hosting bill and Stripe fee estimate, the weekly digest schedule, the operations Slack webhook, the packages, and three switches for the client side … - [When something stops](https://www.plungeai.com/guide/agency/for-the-agency-team/when-something-stops.md): The pipeline opens one exception per cause and subject, so a repeated refusal does not pile up rows. Retry is offered where the request can re-enter the pipeline; for the others, act on the request and dismiss the row, or let the fix resolve it. - [Scheduled jobs](https://www.plungeai.com/guide/agency/for-the-agency-team/scheduled-jobs.md): The platform scheduler runs the agency's jobs; the Dashboard has no clock of its own. Agency jobs runs every job below, in this order, every 5 minutes. Agency run reconcile also runs reconcile-runs every minute. Each job decides for itself whether this pass has work; one failing job never stops … - [Data, export, erase](https://www.plungeai.com/guide/agency/for-the-agency-team/data-export-erase.md): The agency keeps its own data, apart from the rest of the platform: three D1 databases (agency-db for clients, brands, requests, deliverables and reviews; agency-billing for plans and the ledger; agency-events for the timeline, the outbox and performance rows), a KV cache of read-fast copies … - [How it works](https://www.plungeai.com/guide/agency/how-it-works.md): The system underneath both apps: where things run, how a request moves, what the pipeline and the QA gate do on their own, how the brand learns, where the money goes and what runs on the clock. - [The system map](https://www.plungeai.com/guide/agency/how-it-works/the-system-map.md): PlungeAI Agency is three web apps on Cloudflare. They keep the agency's data in their own databases and use the Ocean platform for everything that thinks or generates: workflow runs, models, run outputs, brand cards and the clock. This is the only place in this guide that names the internal … - [The request lifecycle](https://www.plungeai.com/guide/agency/how-it-works/the-request-lifecycle.md): A request has twelve statuses. The arrows are the only moves the code allows; anything else is refused. The colour of an arrow says who usually makes the move. - [Production](https://www.plungeai.com/guide/agency/how-it-works/production.md): The pipeline moves a request from brief to internal review without anyone pressing a button. When it cannot go on by itself, it stops and opens an exception (see When something stops). - [The QA gate](https://www.plungeai.com/guide/agency/how-it-works/the-qa-gate.md): The automatic QA gate checks every concept before a person sees it. It never sends work to a client by itself: a person decides every piece the gate passed or held, and can dispute or re-queue anything it failed. - [The brand brain](https://www.plungeai.com/guide/agency/how-it-works/the-brand-brain.md): The brand is a versioned document. The active version is written to a private brand card on the platform, and every production run reads that card. Decisions keep teaching it. - [Money](https://www.plungeai.com/guide/agency/how-it-works/money.md): Every amount the client pays, gets back or costs the agency is one line in the client's ledger. Stripe runs in test mode today. - [The clock](https://www.plungeai.com/guide/agency/how-it-works/the-clock.md): The platform scheduler drives everything that happens without a click. The full list is in Scheduled jobs. - [Who sees what](https://www.plungeai.com/guide/agency/how-it-works/who-sees-what.md): The server checks every call against the caller's role, so a hidden button is also a refused request. - [Glossary](https://www.plungeai.com/guide/agency/how-it-works/glossary.md): The words of PlungeAI Agency, from unit and concept to standing approval, share link and billing group. - [PlungeAI Consulting](https://www.plungeai.com/guide/consulting.md): How to use PlungeAI Consulting: the portal where your company follows its work, the dashboard where the firm runs it, and the rules underneath both. - [For clients](https://www.plungeai.com/guide/consulting/for-clients.md): This part is for the people at your company. The portal shows where your work stands, what waits on you, what you owe and what we delivered. Each page in the sidebar also answers in the concierge, the chat on every page. - [Getting in](https://www.plungeai.com/guide/consulting/for-clients/getting-in.md): The three ways into the Consulting portal: buy a size on the site, talk to us first, or accept a colleague's invite. - [Roles](https://www.plungeai.com/guide/consulting/for-clients/roles.md): Every person on your side has one of four roles. The sponsor sets them on the People page. - [Ordering a size](https://www.plungeai.com/guide/consulting/for-clients/ordering-a-size.md): We sell six boxes. Each box comes in three sizes. Each size on the price list states its price, what you get, what we need from you, its delivery days and its review rounds. The prices come live from our catalog. - [Your order and the fit check](https://www.plungeai.com/guide/consulting/for-clients/your-order-and-the-fit-check.md): After a self-serve purchase, the portal opens on Your order. It shows what you bought, the size's intake questions, what we need from you (access, data, people) and the start date. You can answer or edit the intake until the fit check. - [Signing and paying](https://www.plungeai.com/guide/consulting/for-clients/signing-and-paying.md): The sponsor signs and pays on Sign and pay. One flow covers both. - [Following the work](https://www.plungeai.com/guide/consulting/for-clients/following-the-work.md): The portal pages that show where your engagement stands, what waits on you, what we found and what comes next. - [Reviewing a delivery](https://www.plungeai.com/guide/consulting/for-clients/reviewing-a-delivery.md): Every delivery waits for your sign-off on Deliverables, or from the review link in your email. Approvers and sponsors decide; a technical lead decides on technical deliveries. - [Change orders](https://www.plungeai.com/guide/consulting/for-clients/change-orders.md): Work beyond a size is a change order. Change orders shows what changes, its price and its effect on dates. The sponsor accepts it with a typed name or declines it with a reason. Nothing in it runs before the sponsor accepts, and declining costs nothing. - [Billing](https://www.plungeai.com/guide/consulting/for-clients/billing.md): Billing holds all the money in one view: what is due now, what you paid, your credits, the payment schedule of your size, accepted change orders, your Care and your payment methods. Invoice shows one invoice and how to pay it. Sponsors act here; approvers read. - [Your team](https://www.plungeai.com/guide/consulting/for-clients/your-team.md): On People, the sponsor invites people, changes their roles and removes them. Everyone sets their own mail switches there. Billing and signature mail always reaches the sponsors, whatever the switches say. - [Data and exit](https://www.plungeai.com/guide/consulting/for-clients/data-and-exit.md): Data and exit shows the terms version you accepted and the data processing agreement. The sponsor can download all of your company's data there: documents, signature certificates, invoices and the timeline. The sponsor can also start offboarding, which opens a checklist for leaving cleanly. To … - [The concierge](https://www.plungeai.com/guide/consulting/for-clients/the-concierge.md): The concierge is the chat on every portal page. Ask it "Where are we?", "What do I owe?" or "What's waiting on me?". It answers with the same cards as the pages, and shows only what your role may see. Pin any answer to My dashboard. - [For the firm](https://www.plungeai.com/guide/consulting/for-the-firm.md): This part is for the firm. The owner runs everything from the dashboard, from the sidebar or from the chat. Each sidebar page also answers in the chat as a card, and the chat shows a confirm card before any change to money or scope. Agents prepare the work; the owner approves it. - [The day](https://www.plungeai.com/guide/consulting/for-the-firm/the-day.md): The owner's day in the dashboard: the morning briefing, the drafts to approve, the feed, who owes a signature and the exceptions. - [Approvals](https://www.plungeai.com/guide/consulting/for-the-firm/approvals.md): Every AI draft lands in Approvals before it reaches a client. Each shows to whom, why, a one-line summary and the draft. For each one. - [Sales](https://www.plungeai.com/guide/consulting/for-the-firm/sales.md): Leads, proposals, Discover engagements, capacity and clients: the sales pages of the dashboard. - [Delivery](https://www.plungeai.com/guide/consulting/for-the-firm/delivery.md): Engagements, milestones, deliverables, change orders, provisioning and client messages: the delivery pages of the dashboard. - [Money](https://www.plungeai.com/guide/consulting/for-the-firm/money.md): Revenue and margin, invoices, Care plans, usage and hours: the money pages of the dashboard. - [Settings](https://www.plungeai.com/guide/consulting/for-the-firm/settings.md): The firm's catalog of the six doors and Care, its capacity, its settings and the audit log. - [Scheduled jobs](https://www.plungeai.com/guide/consulting/for-the-firm/scheduled-jobs.md): These run on the platform scheduler. Each one makes drafts for Approvals or items for the Feed. None sends a client message by itself, except receipts and links. - [How it works](https://www.plungeai.com/guide/consulting/how-it-works.md): This part is for everyone: the same steps and rules hold under every box. Terms is the binding text; this page explains it. - [The five steps](https://www.plungeai.com/guide/consulting/how-it-works/the-five-steps.md): Pick a box, sign and pay, we deliver in days, you sign off, and it keeps running: the same five steps in every box. - [The money rules](https://www.plungeai.com/guide/consulting/how-it-works/the-money-rules.md): Paid before it starts, phase invoices, credit forward, late payment, Care and platform usage: the money rules under every box. - [The delivery clock](https://www.plungeai.com/guide/consulting/how-it-works/the-delivery-clock.md): Delivery is counted in working days. The clock starts on the day you completed what the size needs from you: access, data and people. It pauses while a sign-off or a to-do waits on you. Your portal shows the due date and the paused time. - [Glossary](https://www.plungeai.com/guide/consulting/how-it-works/glossary.md): The words of PlungeAI Consulting, from box and size to magic link and concierge. - [Ocean Code](https://www.plungeai.com/guide/ocean-code/overview.md): Ocean Code is a coding agent that lives in your terminal, keeps the thread of a session however long it runs, lets several sessions work on one Mac without stepping on each other, and answers from Slack when you are away. - [Quickstart](https://www.plungeai.com/guide/ocean-code/quickstart.md): Install Ocean Code, sign in, start a session in the terminal, and know where it keeps its files. - [Sessions that keep the thread](https://www.plungeai.com/guide/ocean-code/tideline.md): The tideline keeps a session's context window bounded while nothing is lost, so a session stays fast and affordable for hours of work and hundreds of steps and can be reopened days later with its history intact. Patent pending. - [Several sessions, one Mac](https://www.plungeai.com/guide/ocean-code/sessions-together.md): Ocean Code sessions on one machine see each other, stay off each other's files, learn from each other's ledgers, send each other requests you decide on, and can be reopened from anywhere by a four-character code. - [Work modes](https://www.plungeai.com/guide/ocean-code/work-modes.md): Who decides how agents work together on your prompt — the model, Jev, or you with one of seven diagrams. Each diagram is one small file the TUI draws from and the engine runs from. - [Long runs and sub-agents](https://www.plungeai.com/guide/ocean-code/long-runs.md): A run is bounded by the money and time you set, stops cleanly with a reason, and is driven by the plan it writes; sub-agents work in a dock above the prompt, background jobs run as long as they need, and a session keeps working for hours and hundreds of steps. - [Editors and your terminal](https://www.plungeai.com/guide/ocean-code/editors-and-terminal.md): Ocean Code runs inside Xcode and Zed over the Agent Client Protocol with the same engine and sessions as the TUI, and in the terminal it draws only what changed, follows your display's refresh rate and shows images inline where the terminal can. - [Ocean TUI](https://www.plungeai.com/guide/oceancode/tui.md): Ocean TUI is the terminal interface of oceancode. A plain oceancode execs Ocean TUI (ocean-tui); the TUI and the Ocean engine run in one process over typed ACP channels — no HTTP between UI and engine. --db, --directory, --listen and --verbose are passed through. - [Xcode, Zed and other ACP editors — oceancode acp](https://www.plungeai.com/guide/oceancode/xcode.md): oceancode acp runs the Ocean engine as an Agent Client Protocol (ACP) agent on the process's stdin/stdout. An ACP editor — Xcode 26.6 and later, Zed, JetBrains, Neovim — starts the binary itself as a subprocess and talks newline-delimited JSON-RPC over the pipe. There is no URL, no port and no … - [Slack](https://www.plungeai.com/guide/oceancode/slack.md): Slack Remote lets you follow and drive your sessions from one Slack channel, from your phone or anywhere else. Every session has its own thread: you see what the agent wrote before it asks, answer its questions and permissions with a button or a reply, read its whole final answer, and send it … - [Plan mode and todos](https://www.plungeai.com/guide/oceancode/plan-mode-and-todos.md): Two separate things share the word "plan": the step list the model keeps as it works, and plan mode, an agent that researches and writes a plan file before anything is changed. - [Session ledger and export](https://www.plungeai.com/guide/oceancode/session-ledger-and-export.md): A long session in most coding agents grows an ever-larger context until it slows down, costs more per step and finally has to be summarized. oceancode keeps the session ledger instead: the model sees a bounded window of the newest turns, and everything older is kept verbatim on disk, never … - [Workflows](https://www.plungeai.com/guide/oceancode/workflows.md): A workflow is a file of tasks that oceancode runs in a fixed order: which agent does what, which tasks run at once, where a check or your approval stops the run. No model picks the next step. Five ship with oceancode — Spec, Build, Review, Secure and Research — beside Goal and Race, and you can … - [Configuration](https://www.plungeai.com/guide/oceancode/configuration.md): oceancode reads a JSON config file and a set of environment variables. Nothing needs to be configured to start — every key falls back to a built-in default. - [Permissions and sandbox](https://www.plungeai.com/guide/oceancode/permissions-and-sandbox.md): Ocean Code decides what a tool may do in three layers, from softest to hardest: - [Hooks](https://www.plungeai.com/guide/oceancode/hooks.md): A hook runs your own command (or an HTTP endpoint) at a fixed point in a run and hands back a typed decision the engine acts on. Hooks are configured in a Claude Code settings.json / hooks.json shape, so a hook you already wrote for Claude Code runs here unchanged. - [MCP servers](https://www.plungeai.com/guide/oceancode/mcp.md): An MCP server is an external process (or HTTP endpoint) that contributes tools, resources and prompts to a run. oceancode reads the same server-config files the other tools use, so a server you configured for Claude Code, Cursor or OpenCode is picked up as-is. - [Capabilities and plugins](https://www.plungeai.com/guide/oceancode/capabilities.md): Skills, sub-agents, personas, commands and MCP servers are all capabilities, and oceancode finds them the same way: one discovery walk over five tiers, across four ecosystems, with a single rule for names that collide and a separate rule for what a capability is allowed to do. - [Bounding a long run](https://www.plungeai.com/guide/oceancode/bounding-a-long-run.md): A run is bounded by the money and time you set, not by an arbitrary step count. Set nothing and a run keeps going until the work is done (or the no-progress guard stops it, below). - [Work modes](https://www.plungeai.com/guide/oceancode/work-modes.md): A work mode decides how agents work together on your prompt. There are three answers to "who decides?": - [Jev decisions](https://www.plungeai.com/guide/oceancode/jev-decisions.md): Ocean Code can put small typed questions to TypeSafe Jev (System One, pinned model jev-1.13.0) at ten decision points — "would this command delete data?", "which block of this output answers the step?" — and use the answers as advice. Jev answers with probabilities: a noul (the probability of … - [Platform mode (PlungeAI connectivity)](https://www.plungeai.com/guide/oceancode/platform-mode.md): oceancode ships in two builds. The default build is the standalone coding agent and contains no platform code at all. The platform build is produced with - [Headless and server](https://www.plungeai.com/guide/oceancode/headless-and-server.md): oceancode runs without a UI two ways: a one-shot run for scripts and CI, and a long-lived serve that exposes the engine's HTTP surface to clients. In the terminal, Ocean TUI embeds the engine in its own process (see 19 · Ocean TUI); serve is the headless surface. - [CLI reference](https://www.plungeai.com/guide/oceancode/cli-reference.md): oceancode is one binary: oceancode [subcommand] [flags] [args]. With no subcommand it starts Ocean TUI. acp runs it as an editor agent, and serve, run, goal and workflow run it headless. 01 · Getting started explains the three boot shapes. This page lists every subcommand, its flags and its … - [Ocean TUI reference](https://www.plungeai.com/guide/oceancode/tui-reference.md): This page lists Ocean TUI's slash commands, keyboard shortcuts, mode ring, config.toml settings, themes and notification options. For how the TUI starts, its environment variables and what is wired to the Ocean engine, see Ocean TUI. - [HTTP API reference](https://www.plungeai.com/guide/oceancode/http-api.md): oceancode serve runs the engine as a long-lived HTTP server, by default on http://127.0.0.1:4096 (--port and --host change it; the default TUI shape takes --listen ). Every route below is relative to that base URL. HTTP basic auth is off until OC_SERVER_PASSWORD is set; then it … - [Build and run Ocean Code](https://www.plungeai.com/guide/oceancode.md): oceancode is one binary and one process. This page builds it, shows the two ways to start it, and lists where it keeps its files. - [Distribution and updates](https://www.plungeai.com/guide/oceancode/distribution.md): oceancode ships as two self-contained binaries: the engine oceancode and the terminal UI ocean-tui it launches, installed side by side. This page covers installing it, keeping it current, verifying a download, and removing it. Every download is checksummed, and every install channel agrees on … - [Operations](https://www.plungeai.com/guide/oceancode/operations.md): Running oceancode for a long time — days, not minutes — is a first-class case. This page covers the operational surface that keeps a long run healthy: a metrics scrape, database and ledger retention, the storage doctor, crash recovery, the session line, the event-bus drop counter, and log … - [Testing and gates](https://www.plungeai.com/guide/oceancode/testing-and-gates.md): Everything in oceancode is verified by one script — ./check.sh — and a handful of opt-in lanes on it. This page covers what those lanes are, and then the one test surface a terminal UI needs that unit tests cannot give it: the interface probe, which drives the real TUI over a pseudo-terminal … - [Ocean Build guide](https://www.plungeai.com/guide/ocean-build.md): Describe the app you want in your own words. Ocean Build asks what it needs to know until the brief is complete, then a crew builds the app on PlungeAI's own parts: screens on App UI, data on Ocean Base, automations on the platform's workflows and schedules. Every round is checked, reviewed and …