Tools

Token usage optimizer

Compare prompt stuffing (docs + rules + examples every turn) against full documents, RAG chunks, and relevant facts from UniFact. Adjust inputs for your workload — illustrative estimates for sales and planning.

Privacy and event SOP questions; small corpus, high trust bar.

$97.14

Monthly savings (facts vs prompt stuffing)

80%

Context reduction per turn

$1166

Annual savings (same assumptions)

Workload inputs

Pricing & behavior

Context per agent turn

Prompt stuffing (docs + rules + examples)7.9k / 128.0k (6%)
Relevant facts2.5k / 128.0k (2%)

Estimated monthly cost by strategy (USD)

Prompt stuffing$118/mo
Full documents$60.05/mo
RAG chunks$43.97/mo
Relevant facts$20.56/mo
Input cost Output cost

Prompt stuffing = all documents plus rules, few-shot examples, and tool definitions re-sent each turn. Facts assume stable published context with higher cache hit rate.

Strategy comparison

StrategyContext / turnEffective turnsInput tokens / moTotal cost / mo
Prompt stuffing6.7k6.943.48M$118
Full documents3.2k6.422.53M$60.05
RAG chunks2.6k5.717.18M$43.97
Relevant facts1.3k4.48.91M$20.56

Optimization levers (ranked)

PriorityLeverEstimated impact
HighReplace prompt stuffing with retrieved facts~5.4k fewer input tokens per turn (80% on context vs stuffing baseline)
HighReduce repair turns (governed facts vs invented policy)~200% fewer effective turns vs doc approaches
MediumTrim stuffing overhead (rules, few-shot, tool defs)Prompt stuffing includes ~3.5k tokens of rules/examples beyond documents — audit system prompts
MediumPrompt caching on stable fact prefixUp to 90% off cached input — facts cache better than rotating doc dumps
LowScope facts per intent (not whole registry)Fact bundle size is reasonable for single-turn injection
Methodology & limits

Prompt stuffing is the anti-pattern baseline: every document plus bloated system prompts, examples, and schemas on every turn. Full documents omits that extra overhead but is still naive. RAG and facts reduce context; facts also cut repair turns when agents stop inventing policy.

Illustrative model only — validate against your provider billing. Documents remain the legal source of record; facts govern what agents may assert in operations.