> ## Documentation Index > Fetch the complete documentation index at: https://docs.tilt.io/llms.txt > Use this file to discover all available pages before exploring further. # Advisor workflows > How clients, accounts, model portfolios, and optimization proposals fit together in Tilt. Tilt helps an advisor define reusable model portfolios, apply them to client accounts, and review proposed changes against each account's saved holdings and settings. Tilt Agent can guide each task in chat. Inspect the relevant state before asking it to make a change. An explicit optimization request authorizes a run; inspect its inputs first if you are not ready to submit one. ## The objects you work with | Object | What it represents | What to check | | --------------------- | --------------------------------------------------------------- | ------------------------------------------------------------------- | | Client | A person or entity your organization manages. | The correct client identity and organization. | | Account | A client's holdings and account-specific settings. | Holdings freshness, assigned model, and restrictions. | | Model portfolio | A reusable allocation built from sleeves. | Sleeve structure, target weights, and implementation choices. | | Optimization proposal | A saved result for one account's holdings, model, and settings. | Status, proposed holdings and trades, drift, costs, and exceptions. | A sleeve is a building block of a model portfolio. It can represent an asset class or another investment implementation. A model supplies target allocation to assigned accounts; account settings can tailor how Tilt implements that model. [Build a model portfolio](/advisor/build-model-portfolio) walks through both levels. Model portfolio and sleeves feed an assigned client account; its saved holdings and settings feed optimization; optimization returns a proposal for advisor review. ## Find your way around Start in a chat with Tilt Agent. Name the client, account, or model you want to work on. Tilt Agent can show the current state in a message or table, ask for a decision, and provide the next action. A workflow card shows which step is current or blocked. Open a linked account or proposal when you need its full review view. Return to the chat to ask a follow-up about the same client and account. For example, ask: **"Show me the portfolio assigned to Taylor Morgan's account and its sleeve weights."** The production demo account uses **Aggressive Portfolio**. Check the client and account named in the reply before asking for a change. If you advise more than one organization, select the organization you mean before starting account work. Taylor Morgan's Optimization tab shows Aggressive Portfolio as the selected portfolio and a chart of its inherited sleeve weights. ## A review boundary An optimization produces a proposal. Running it, reading its reports, or opening its review view does not place an order. Trade approval and brokerage execution require separate review in the account interface. [Review a rebalance](/advisor/review-rebalance) covers that boundary. ## Choose a task Define sleeves and weights, choose implementation settings, and assign a model to an account. Check readiness, run an optimization, and inspect the saved proposal. Set up a new client and account, then check what is ready for optimization. Assign a shared model and add client-specific settings. Find the source of an effective setting and inspect Dynamic Rules. Find account setup, holdings, and proposal exceptions across clients. Confirm a cohort, follow each result, and review its proposals. Examine a proposal's evidence and compare account scenarios. Inspect drift, cash, tracking-error, or exposure policies. The [Portfolio Optimization API guide](/customization/guide) covers API integration. The pages here describe advisor work in Tilt.