Budget Allocation Modeler
Allocates budget by explicit logic — not last year plus 10%.
Sonnetjson outputv1.0
Variable filler
Fill values and watch them flow into the prompt below. Nothing is stored.
budget
channel data
goals
constraints
The prompt
Allocate (or reallocate) a marketing budget across channels with explicit logic — not vibes, not last year +10%.INPUT: budget + period: {{budget}} | channel performance history: {{channel_data}} // spend, CAC/ROAS, volume, saturation signals per channelGoals: {{goals}} | constraints: {{constraints}} // committed contracts, minimum brand spend, etc.METHOD:1. Classify each channel: SCALE (efficient + headroom), HOLD (efficient, saturating — flag the saturation evidence), FIX (inefficient but strategic — cap as experiment budget with a kill criterion), CUT (inefficient, no thesis).2. Allocate: 70% to SCALE/HOLD by marginal efficiency, 20% FIX experiments with defined kill criteria, 10% new-channel exploration.3. Show per channel: allocation, expected output at that spend (state the assumption: linear vs. diminishing), and the review trigger (the number that forces reallocation).RULE: any channel with no performance data gets experiment-tier budget only, never scale budget.OUTPUT — ONLY JSON: { "allocations": [], "assumptions": [], "review_triggers": [], "unfunded_asks": [] }Tap the block to copy
inputs
- budget
- budget
- channel_data
- channel data
- goals
- goals
- constraints
- constraints
outputs
- Declared output: json.
v1.02026-07-17current
Published with the v1 library.
Honest known limits — every prompt has them.
- Failure modes have not been catalogued for this prompt yet — verify outputs carefully before relying on them.