AWS INFRASTRUCTURE COST AUDIT
Most AWS overspend isn't in one place — it's spread across compute, storage, networking, AI inference, and idle infrastructure. We audit your entire AWS setup and tell you honestly where the money is going, what's worth cutting, and what to do about it.
No console access required. Written report with specific findings and projected savings.
WHERE THE MONEY GOES
These are the five places we look first. Most teams have at least two of them.
01
Every failed API call that retries is billed at full token cost. If your error handling is optimistic — retry three times, log the failure — you're paying for the same tokens two or three times on every flaky request. In a high-throughput pipeline, this adds up fast and shows up nowhere obvious in your dashboard.
02
Agentic systems that pass full conversation history on every step compound quickly. A ten-step agent with a 4,000-token context isn't spending 40,000 tokens — it's spending closer to 220,000 if the context grows linearly. Most teams don't model this until the bill arrives.
03
Retrieval-augmented pipelines that stuff the top-k chunks into the prompt regardless of relevance are paying for tokens the model ignores. The fix is usually a reranker or a tighter similarity threshold — not a model change. But it requires someone to look at the retrieval logs, not just the inference costs.
04
EC2 instances reserved for peak load sitting at 20% utilisation. S3 buckets accumulating data nobody queries. RDS instances sized for a future that hasn't arrived. NAT Gateway traffic that could be routed more cheaply. These aren't engineering failures — they're the natural result of moving fast. They're also straightforward to fix once someone looks.
05
GPT-4o and Claude Sonnet are excellent. They're also 10–50× more expensive than the models below them for tasks that don't require their capability. Classification, summarisation, routing, and extraction are often running on frontier models because that's what the team started with. A routing layer that sends simple tasks to a smaller model can halve the inference bill without touching output quality.
HOW IT WORKS
01
Get in touch and tell us which AWS services you use, roughly what you're spending, and where you think the money's going. No AWS console access required at this stage.
02
We audit your infrastructure and produce a written report with specific findings, projected savings, and prioritised recommendations. If there's nothing material to cut, we'll say so clearly and explain why. We have no incentive to manufacture a problem.
03
The output is a clear, actionable document — not a slide deck. It shows your current spend, where the waste is, what to fix first, and projected savings from each recommendation. Where implementation work is needed, we can introduce you to the engineering partner we trust to fix it.
COMMON QUESTIONS