What the exit interview collector costs
Leaver volume is low and each leaver produces at most two responses, so this is the smallest workload in the series. Fourteen responses a quarter is a business of perhaps eighty people with ordinary turnover. Here is where each cent goes.
Key takeaways
- About $1 a month at 14 responses. Roughly $1 at 50 responses.
- One Bedrock read per response is the only line that scales. Everything else is rounding.
- Nothing is always-on, so a quiet month genuinely costs almost nothing.
- At most two model calls per leaver, ever. There is no ongoing processing at all between quarters.
- The duplicate test runs before the read, so resends are free.
- The three real risks: a retry loop, storage nobody expires, and a bigger model than the job needs.
The bill at three volumes
These are US East prices at the time of writing, at three volumes that bracket most small businesses. Find the bar closest to your own and read across.
Line by line
| Line | At 14 responses | How it scales |
|---|---|---|
| Bedrock read | $0.03 | Linear. One call per response, roughly 1,800 in and 200 out tokens. |
| SES | $0.01 | Linear. About 2 messages per response. |
| DynamoDB + S3 | $0.28 | Storage grows with what you retain, not with throughput. |
| Lambda + SQS | $0.12 | Linear, and effectively free at this scale. |
| CloudWatch | $0.16 | Flat, if you set retention. Unbounded if you do not. |
| Secrets Manager | $0.40 | Flat. One secret, $0.40 a month. |
| AWS Budgets | $0.46 | Flat. Two actions, so you find out before the bill does. |
One model call per response, ever. A leaver who answers both asks costs two calls in total and then nothing for the rest of the system’s life.
The three ways this bill surprises you
Every one of these has happened to somebody, and all three are cheap to prevent.
- Re-classifying on every report run. Classification happens once per response and the result is stored as counts. Re-running the model at report time to regenerate themes would multiply the cost and, worse, would make trends unstable.
- Storing the raw text on the aggregate. Not a cost risk but the one that matters: an aggregate table that carries the original sentences is one query away from being a quote generator.
- Log retention left at never. This system runs a few times a quarter. Without a retention setting, logs will be the entire bill, and exit-interview logs are exactly the logs you least want kept indefinitely.
What it costs when nothing happens
This matters more than the headline number for a seasonal business. In a month with nothing to process the bill is the fixed band: Secrets Manager at forty cents, AWS Budgets at forty-six, and a few cents of storage. Call it a dollar. There is no instance to stop and nothing to remember to turn off.
- Management
- Analytics
- Front-end & mobile
Set these on day one
- A dead-letter queue on every SQS queue, with a maximum receive count of three.
- Thirty-day retention on every CloudWatch log group. There is no default that is safe.
- An S3 lifecycle rule on the object prefix, tiering at 90 days and expiring at your actual record-keeping horizon.
- Two AWS Budgets actions — one that emails at half your expected spend, one at double it. The second is how you find out about a loop in an hour instead of a month.
- Provisioned concurrency: none. Nothing here is latency-sensitive enough to justify paying for a warm function.
Next: the same system drawn for engineers — service names, resource identifiers, IAM scopes, table schemas and the model id.
All posts