it_support · workflow

incident.io controls AI spending with per-prompt cost attribution and OpenAI project billing limits

incident.io hit OpenAI billing limits and temporarily broke all early-access AI features. As they expanded adoption — particularly Investigations, which costs 100x more than their other AI features — they lacked visibility into which features and code paths were driving spend.

How it works
Common implementation structure
How this type of workflow is generally built, generalized across documented cases — not tied to any one vendor's stack. Click any stage to read what happens there. Specific products that implement these stages appear in “Tools commonly seen” below.
Stage 1 · Per-prompt token attribution
Token usage is attributed to a named prompt type via Go reflection and piped into observability tooling.
Tools used
OpenAISlackGitHubGrafanaGoogle Secret ManagerTerraform
Outcome

incident.io now has control over production, development, and training AI costs, with per-prompt attribution, feature-level billing limits, daily Slack cost reports, and predictive backfill cost estimation, enabling teams to ship AI features confidently.

What failed first

Billing limits were breached and all early-access AI features broke. Without per-prompt tracking, the team had no way to attribute spend to features or code paths, and discovered weeks later they had been burning hundreds of dollars on bugs.

Results
Cost replaced100x
Source

https://incident.io/building-with-ai/controlling-costs

How we source this →

Grounding & classification
Source type: technical build writeup
30 fields verified against source quotes.
agentic workflowconversational aispeech to textsummarizationcall recordingcode diff prfailure mode describedmetric backednamed customerproduction runtime claimedtools describedworkflow describedsoftwarecost reductionemployee productivitytechnical build writeupit supportagentic task executionmonitor detect alert