Create a Campaign Budget Allocator with Explicit Caps in Claude

A budget allocator is useful when you need to explore allocations while preserving the total budget, channel caps, and any unallocated balance. The result should make the underlying records easier to inspect and the next decision easier to explain. This guide develops a specific budget allocator with a source schema, operating rules, a fictional example, and observable review checks. It is intended for someone who already has the underlying material and needs a dependable way to organize it.

Product references checked: 7 October 2026. The examples and implementation specifications below are original editorial guidance. They illustrate expected behavior and have not been presented as a benchmark or as a completed tool tested inside another product.

Define the deliverable and its scope

This is a constrained planning simulation, not financial advice, a spending action, or measured campaign optimization.

Write the acceptance standard before asking Claude for a draft. A reviewer should be able to identify the planning budget, inspect the channel allocation, and understand the constraint result without guessing what a blank field means. Decide which records belong in the deliverable, which are out of scope, and who can confirm the final interpretation. Keep those choices visible in the working specification rather than leaving the assistant to supply convenient defaults.

Prepare the source package

Gather budget currency, planning period, channel IDs, approved minimums and maximums, and proposed allocations. Assign source IDs and preserve original wording wherever a small difference could change the outcome. Record the collection date and the version of each source. If two files disagree, keep both references and mark the conflict. Do not replace a disputed value with whichever one produces the cleanest display.

Use a small representative subset for the first draft. Include one ordinary record, one incomplete record, and one record that challenges an important rule. For this task, use the following as the incomplete-record check: Enter an allocation above a channel cap and identify the exact violated bound. Preserve the original package separately from the assistant's transformed output. A polished result is easier to audit when its IDs still lead back to the original supplied material.

Define the record schema

Treat planning budget as a deliberate part of the data model. The supplied total, currency, and period that constrain the scenario. Keep its representation consistent when you sort, filter, or revise the output. The channel allocation field has a different job: The proposed amount for an identified campaign or channel. Combining these fields into one sentence can hide the distinction the reviewer needs to inspect.

Pay particular attention to minimum commitment and maximum cap. The former means: A documented lower bound, including whether it is mandatory. The latter means: The approved upper bound for that channel in the same period. Store them separately and label both in the detail view or report. This makes disagreements visible at the exact point where they affect the result instead of burying them in a general note at the bottom.

Apply the task rules

Rule 1. Do not normalize allocations silently when the user's edits exceed the total budget.

Rule 2. Validate minimum and maximum bounds in the same currency and period as the total.

Rule 3. If required minimums exceed the budget, show infeasibility instead of manufacturing a feasible allocation.

Rule 4. An illustrative allocation is not a forecast of campaign performance or a recommendation to spend.

Make these rules inspectable alongside the budget allocator. Ask Claude to describe how each rule affects a record and what should happen when the supplied data does not establish an answer. A rule written in prose still needs a defined output state. Use an explicit missing, disputed, or not-applicable label where appropriate, and reserve a valid zero or an empty result for cases where it has a defined meaning.

Work through a fictional example

A fictional monthly budget is 1,000 units. Channel A has a 400-unit cap and Channel B has a 300-unit minimum. An allocation of 450 to A and 300 to B leaves 250 unallocated but violates A's cap. The interface must display both facts. Reducing A to 400 leaves 300 unallocated. If approved minimums across all channels total 1,100, the scenario is infeasible before any optimization is attempted. No expected return should be invented to choose a winner.

Use the example as a review fixture rather than as real operational data. Before generating the output, write down which fields should be populated and which should remain unresolved. Then compare the generated result with that expectation. If Claude supplies an unsupported value, correct the underlying instruction or calculation rule instead of merely editing the one visible record. Otherwise, the same error may return when the next record is processed.

Build the first version

Ask for the simplest interactive artifact that displays the schema and supports the specific review task. Start with the fictional example and an obvious detail panel. Keep the source data separate from display labels and interaction state. A selected row, a filter, or an open panel should change what the reviewer sees, not silently rewrite the underlying evidence. Add editing only to fields that the specification explicitly identifies as user inputs.

For the first interaction pass, prioritize unallocated balance: The budget minus the sum of current allocations, shown explicitly. Then add the constraint result behavior: Each violated bound or infeasible combination, with an explanation. Use visible text labels for both. Test the core logic before spending time on animation or visual polish. Provide a keyboard path through the controls and preserve a readable empty state when the selected view has no records.

A reusable prompt

Create a budget allocator from the supplied source package. Goal: explore allocations while preserving the total budget, channel caps, and any unallocated balance. Use these fields: Planning budget: The supplied total, currency, and period that constrain the scenario.; Channel allocation: The proposed amount for an identified campaign or channel.; Minimum commitment: A documented lower bound, including whether it is mandatory.; Maximum cap: The approved upper bound for that channel in the same period.; Unallocated balance: The budget minus the sum of current allocations, shown explicitly.; Constraint result: Each violated bound or infeasible combination, with an explanation.. Preserve source IDs. Rules: Do not normalize allocations silently when the user's edits exceed the total budget. Validate minimum and maximum bounds in the same currency and period as the total. If required minimums exceed the budget, show infeasibility instead of manufacturing a feasible allocation. An illustrative allocation is not a forecast of campaign performance or a recommendation to spend.. First explain the proposed data model and unresolved inputs. Then build the smallest usable version. Use only supplied facts; label the demonstration fictional. Do not invent approvals, thresholds, owners, or external integrations. Include an empty state and explain the expected result for these checks: Enter an allocation above a channel cap and identify the exact violated bound. Make required minimums exceed the budget and display an infeasible state. Reconcile the sum of allocations plus unallocated balance to the total.

Review behavior and edge cases

Check 1. Enter an allocation above a channel cap and identify the exact violated bound. Record the observed result beside the expected result. If the check fails, isolate the affected rule and request a focused correction before rerunning the same case.

Check 2. Make required minimums exceed the budget and display an infeasible state. Record the observed result beside the expected result. If the check fails, isolate the affected rule and request a focused correction before rerunning the same case.

Check 3. Reconcile the sum of allocations plus unallocated balance to the total. Record the observed result beside the expected result. If the check fails, isolate the affected rule and request a focused correction before rerunning the same case.

Repeat the checks after adding another source record or changing the presentation. A working first example does not prove every record is handled correctly. Pay attention to retained selections, stale derived values, and unexplained changes in the number of displayed records. For budget allocator work, the reviewer must be able to tell whether a difference comes from new evidence, an edited rule, or merely a changed view.

Maintain the reviewed version

Keep a version label, source cutoff, and short change record with the finished budget allocator. Record who approved the rules and which demonstration cases were reviewed. When the source package changes, preserve record IDs and revisit the checks affected by the change. Do not treat yesterday's verified result as evidence that today's replacement input is complete.

Before handing the output to another person, review its audience and the material it contains. Use a sanitized demonstration for general feedback when the real source package is confidential. Explain whether changes are saved, whether the output is a preview, and which source remains authoritative. If persistence or sharing is required, verify that behavior in the actual account and intended environment instead of assuming it from a successful preview.

Frequently asked questions

Sources and related reading

Consult the current primary references for account-specific availability and controls: Current Claude artifact documentation, Claude sharing documentation. The schema, examples, prompts, and review checks here are editorial recommendations rather than documented built-in features.

For broader context, read the related Claude workflow guide.