> ## Documentation Index > Fetch the complete documentation index at: https://docs.getinteract.com/llms.txt > Use this file to discover all available pages before exploring further. # Agent Builder > Configure the orchestrator, subagents, tools, and model overrides that power your agent. > [!WARNING] > > This page describes the **previous multi-agent runtime**. For Data Analyst agents, see [Building agents](https://docs.getinteract.com/agents/building-agents.md). The **Agent Builder** tab is the core of your agent configuration. It shows a visual canvas of how your agent is structured — the orchestrator at the top, connected to one or more subagents below. Click any node on the canvas to open its settings panel on the right. ## How the canvas works ```mermaid theme={null} flowchart TB O[Orchestrator] --> DQA[Database Query Agent] O --> DAA[Data Analysis Agent] ``` Each node represents a component of your agent. The orchestrator receives every user message first, decides what needs to happen, then delegates tasks to its subagents. Results flow back up to the orchestrator, which assembles the final response. ## Orchestrator settings The orchestrator is the "brain" of your agent. Click the **Orchestrator** node to configure it. ### System prompt The system prompt tells the orchestrator who it is, what it does, and how it should behave. Write this in plain language — the model interprets it at the start of every conversation. **A good system prompt includes:** * The agent's role and purpose * Which markets, brands, or data domains it covers * Key metrics and how they're defined * Any formatting preferences (e.g. "always include a summary row", "use tables for comparisons") * Escalation rules (e.g. "if ROAS drops below 2, flag it as a concern") **Example:** > You are a paid search analyst for the Dutch and Belgian markets. Your job is to analyse Google Ads performance using the BigQuery connector. Always present campaign data with dimensions by market, campaign, and time period. Define ROAS as revenue divided by ad spend. Highlight campaigns where CPA exceeds the target set in the campaign name. > [!TIP] > > The more specific your system prompt, the less the agent needs to guess. Every business rule you define here is one less thing you need to repeat in your questions. ### Context Three checkboxes control what background knowledge the orchestrator has access to: | Setting | What it includes | Default | | - | - | - | | **Global context** | Agent-specific context you've written for this agent — table descriptions, business rules, column explanations. Edited via the **Global Context** panel on this same card. | On | | **Organization context** | Shared business facts about your organisation — market definitions, metric standards, naming conventions. Managed centrally in [Settings → Context](https://docs.getinteract.com/agents/context.md). | Off | | **Organization events** | Shared, time-bounded facts — campaigns, downtime, and other events that explain anomalies in the data. Managed centrally in [Settings → Context](https://docs.getinteract.com/agents/context.md). | Off | > [!TIP] > > Organization context and organization events are configured once for the whole workspace, not per agent — enabling the checkbox is all that's needed to give this agent access to the current, shared version. Turn them on for any agent that would benefit from company-wide facts or known anomalies; leave them off for narrowly scoped agents where that context would just be noise. ### Model override By default, the orchestrator uses the model selected in the **General** tab. To use a different model for this component specifically, select one from the **Model override** dropdown. The orchestrator handles coordination and reasoning, so a capable model like Claude Sonnet works well here. *** ## Subagents Subagents are specialists that the orchestrator calls to perform specific tasks. The subagents available to you depend on your [agent type](https://docs.getinteract.com/deprecated/agents-overview.md#agent-types). > [card] Database Query Agent > > **What it does:** Generates and runs SQL queries against your BigQuery connector. > > **When to use it:** Any time your agent needs to retrieve data from your warehouse. > [card] Data Analysis Agent > > **What it does:** Interprets query results — computing summaries, identifying trends, formatting charts. > > **When to use it:** When you want the agent to reason about the data, not just return raw rows. ### Configuring a subagent Click a subagent node on the canvas to open its settings panel. #### System prompt Like the orchestrator, each subagent has its own system prompt. For most agents, you can leave this blank — the subagent's built-in instructions are already optimised. Override only if you have specific requirements, such as: * Restricting which tables the Database Query Agent should query * Telling the Data Analysis Agent to always format numbers in a specific currency #### Context The same three context checkboxes described above — global context, organization context, and organization events — are available per subagent, each with its own default. Enable them to give the subagent the same background knowledge as the orchestrator, or configure it differently if the subagent needs a narrower scope. #### Model override You can set a different model per subagent. Common patterns: | Component | Suggested approach | | - | - | | **Orchestrator** | Claude Sonnet — strong reasoning for coordination | | **Database Query Agent** | Claude Haiku — fast and cost-effective for SQL generation | | **Data Analysis Agent** | Claude Sonnet — handles complex interpretation and formatting | *** ## Tools Tools extend what a subagent can produce. Each subagent has a set of tools you can enable or disable. Enabled tools appear as options the agent can use when answering a question. ### Data Analysis Agent — available tools | Tool | What it produces | | - | - | | **Timeseries chart** | Interactive line, bar, or area charts from time-based data | | **Chart (advanced)** | Full ECharts visualisations for more complex chart types | | **Data sheet** | A large scrollable data table, opened in the right panel | | **Rich table** | A formatted table with progress bars, currency formatting, ratings, and tags | | **Report** | A branded, multi-section report with text, tables, charts, and highlights — exportable to PDF | | **Suggestions** | Follow-up question suggestions shown at the end of the agent's response | | **Save learning** | Lets the agent record observations about your data as it works, for review under Settings → Learnings | ### Database Query Agent — available tools (Multi-Agent Swarm only) | Tool | What it does | | - | - | | **Data sheet** | Returns query results as a formatted sheet directly from the query agent | | **Hand off to Data Analysis** | Passes results to the Data Analysis Agent for further interpretation | | **Data evaluator** | Validates query results before returning them | | **Skills** | Gives the agent access to a curated knowledge library (for example data warehouse and paid ads expertise) it can load when relevant | | **Save learning** | Lets the agent record observations about the data schema or query patterns as it works | > [!NOTE] > > In the **Data Analysis Agent** type, the Database Query Agent's tools are fixed — it always runs metadata lookup, data exploration, and SQL queries internally. Tool selection only applies to the orchestrator in this mode. This documentation is built and hosted on [Mintlify](https://mintlify.com), a developer documentation platform.