To write effective instructions for the Analyst Agent, you need to guide it step by step, using explicit and structured language. Your instructions must specify which of the supported tools and capabilities the Agent is to use.
Essential and optional instructions
Your instructions must contain the following:
What data to analyze.
Which analysis steps to follow.
Optionally:
Include examples of how the Report’s wording should look.
Specify a tone and style for the Report (e.g. concise, executive-friendly, bullet-pointed).
Define a language for the Report. The instructions and Report can be in any of 50 widely-spoken languages.
How the output should be structured.
Instruction optimization
Be as explicit as possible:
When you know a specific Metric, Dimension or Application Variable is needed, use the Object picker: type @ to open a dropdown of eligible options. This way, even if the object names are updated at a later time, the Mission still runs. You can reference multiple objects in one instruction.
To have no charts in your Report, specify “Please don’t display charts in the Report.”
Only reference AI-enabled Metrics with the Number data type. Other types of Metrics are not supported at present. Metrics shared from other Applications are eligible.
Directly reference in plain text the Dimension Items you want to filter on.
ℹ️ Note
Agents cannot see formulas.
To improve clarity, paste your instruction into an LLM such as ChatGPT, preceded by guidance such as: “What do the following instructions for a Report mean? Can you reformulate them for better readability?”
Supported tools and capabilities
Choose from the below tools and reference them by name in your instruction. To see full examples of instructions to copy and adapt for your needs, see Instructions examples for the Analyst Agent.
Contribution analysis
Contribution analyses work well when your Metrics have multiple Dimensions to drill into. A contribution analysis identifies the key drivers in an aggregated value. For example:
🎓 Sample instructions
“Analyze @Revenue for Quarter = Q2 2025”
“Analyze @Revenue for @Quarter = Q2 2025 and show the top 5 contributing Countries.”
Choose which Dimensions are to be used to disaggregate your data by specifying them in the Object picker. If no Dimension is specified, the Agent automatically selects the three Dimensions that best explain the result. You can also ask the Agent to rule out certain undesired Dimensions, such as “currency”.
A powerful capability is the combined breakdown. The Agent looks for pairs of Dimensions (for example, Country–Product) that make key contributions.
Variance analysis
As with contribution analyses, variance analyses also work well when your Metrics have multiple Dimensions. Choose which Dimension is to be used to disaggregate your data by specifying the Dimension in the Object picker. If no Dimension is specified, the Agent automatically selects the three Dimensions that best explain the result.
Mention which two Dimension Items are to be compared, such as “actuals vs forecast”, “this month vs last month”, and specify the comparison Dimension. You don’t need to create a specific Metric that calculates the variance.
You can specify two different Metrics to be compared, allowing the following types of analysis:
Absolute differences between Metrics (e.g. Quota vs Target)
Ratios (e.g. Net Take Rate = Gross Profit / Gross Merchandise Value)
Growth calculations (e.g. showing one Metric as a % of another)
🎓 Sample instructions
“Do a variance analysis on @Monthly_sales on @Version between Actuals and Q426 Reforecast for current month”.
“Calculate Net Take Rate (NTR) (%) from @GrossProfit / @GrossMerchandiseValue”.
“Compare NTR in Q1 versus Q2. Is the change driven by @GrossProfit or @GrossMerchandiseValue”.
“Break down NTR by @Country and @Product. Show top 5 @Country and @Product combinations giving highest NTR”.
ℹ️ Notes
Since ratios don’t make additive contributions, avoid referring to “contributors” or “contribution” in the context of ratios. Instead, specify ratio and ranking, such as ”the top three countries by gross profit margin”.
When breaking down results by underlying Dimensions, the calculation only applies to Dimensions shared by both Metrics.
Filtering
You can ask the Agent to filter based on absolute and relative variances, using multiple conditions.
🎓 Sample instructions
“Show suppliers where Actual costs > 10K and Actual vs. Budget variance is above ±10%.”
“Analyze IT cost variation between Mar '25 and Feb '25 and highlight suppliers with changes over ±100%.”
The Agent can also filter on pairs of Dimensions, such as “Filter top 10 SKU–Product pairs” or “Show Department–Vendor combinations with variance above ±10K”.
Loops
The Analyst Agent can provide valuable insights by running analyses across multiple scopes, for example by Business Unit, Department or Cost Center. There is currently a limit of 15 Items per iteration.
🎓 Sample instruction
If your Dimension contains more than 15 Items, you can narrow the scope by specifying a filtered subset, such as:
“Repeat the analysis for the top 15 Departments driving the variance”
“Run the analysis for the Departments contributing the most”
This allows the Agent to focus on the most impactful items while staying within system limits.
Charts
Charts generated for Mission output hold dynamic data, while the text and figures are static. Charts are included by default unless you specify otherwise in your instruction. You can also manage charts and delete unwanted charts. The ability to reference advanced Views, such as highly formatted tables and waterfall charts, is still in development.
Snapshots
Compare Metrics between live Scenario data and Snapshots.
ℹ️ Note
Before using Snapshots in your analysis, ensure that the Scenarios functionality is activated in your Application. Otherwise, the Agent is unable to retrieve Snapshot data.
In your instructions, you must explicitly mention the Snapshot name in plain text. Always reference Snapshots by concatenating the Snapshot name and the Scenario name, as shown below.
🎓 Sample instructions
“For @Revenue, compare Scenarios ‘baseline’ to ‘Snapshot - 2025-11-07 - Baseline’"
If your Report does not use shared Metrics, you can retrieve data from any Snapshot within your current Application. If your Report does include shared Metrics, make sure the Snapshot you reference is a multiple-application Snapshot and includes both the current Application and any linked Applications containing shared Metrics.
Limitations
Shared Scenarios are supported, but local Scenarios are not.
Member-based variables are not supported.
Variables with names containing special characters are not supported (for example,
[d]CurrentMonth).Currently, the Agent can only access Metrics with data type Number.
Certain advanced calculations are not supported:
Time series analysis
Correlations
You cannot reference Views in the Instructions.
Scenario Variables that reference a snapshotted Scenario are not yet supported.
Dos and Don’ts
Ensure that your Metrics have the correct default time aggregator setting. Otherwise the Agent may sum together non-cumulative data points such as FTEs or exchange rates.
Avoid referencing pre-calculated variance Metrics. The Agent computes variances itself, and using pre-aggregated values can lead to incorrect results.