BETA
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.
-
How the output should be structured.
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 can be written in any of 50 widely-spoken languages, and you can ask for the Report in any of the 50 languages.
-
Identify a destination Metric for the Report.
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 output report, specify “Please don’t display charts in the output 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.
🎓 Sample instructions
-
“Do a variance analysis on @Monthly_sales on @Version between Actuals and Q426 Reforecast for current month”.
Note
You cannot directly compare two separate Metrics (for example, “Product_SKU1_sales” compared to “Product_SKU2_sales”). Instead, you can create a single Metric with a comparison Dimension, such as a Dimension with Items “Product_SKU1_sales” and “Product_SKU2_sales”. Then you can use an instruction such as:
-
“Do a variance analysis between the Items ‘Product_SKU1_sales’ and ‘Product_SKU2_sales’ in Metric @SKU_level_sales”.
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”.
Time Series analysis
Compare data over multiple time periods, instead of between just two time periods or Scenarios.
🎓 Sample instruction
-
“Find trends from the last 18 months in Metric ‘sales by sku’.”
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 capability of referencing advanced existing Views, such as highly formatted tables and waterfall charts, is still in development.
Advanced calculations
Currently, certain advanced calculations are partially supported, such as:
-
Difference between Metrics
-
Show results as a %
🎓 Sample instructions
-
“Calculate the gap between @Ordered Quantity and @Delivered Quantity”
-
“Show the variance difference as a percentage”
Others are in development, such as:
-
Cumulative operations (e.g. YTD, QTD, ...)
-
Advanced ‘Show Value As’
-
Ratios with different aggregation levels
If a calculation doesn’t work as expected, it could be due to these current limitations. A workaround would be to create a dedicated Metric for the calculation.
Dos and Don’ts
-
Currently, the Agent can only access Metrics with data type Number.
-
Ensure that your Metrics have the correct default time aggregator defined in Metric settings. Otherwise the Agent may sum together non-cumulative data points such as FTEs or exchange rates.
-
Snapshots are not supported.
-
Shared Scenarios are supported, but local Scenarios are not.
-
Member-based variables are not supported.
-
Avoid referencing pre-calculated variance Metrics. The Agent computes variances itself, and using pre-aggregated values can lead to incorrect results.
-
You cannot reference Views in the Instructions.