Glossary

The vocabulary of agentic spend governance

One-sentence definitions first, detail behind each link. These are the terms this site uses precisely and consistently — if a definition here ever disagrees with how a page uses the word, that is a bug worth reporting.

Agentic spend: Agentic spend is the money an autonomous AI system consumes deciding how to do its work, rather than the money a fixed application spends executing a known number of calls. Full entry
Agent cost observability: Agent cost observability is the ability to see what each AI agent, run, team, and customer costs, as opposed to seeing what an API key costs in total. Full entry
Cost defect: A cost defect is a pattern in code that makes an LLM workload cost more than the same behaviour would cost if written differently. Full entry
Cost per run: Cost per run is the total LLM spend attributed to one execution of an agent task, summed across every call, model, and agent that execution triggered. Full entry
Agentic spend governance: Agentic spend governance is the practice of attributing, budgeting, and enforcing LLM spend at the level of the agents that generate it, rather than at the level of API keys or accounts. Full entry
Multi-agent amplification: Multi-agent amplification is the compounding of LLM costs that occurs when agents invoke other agents, so one task multiplies into a tree of calls whose total is far larger than any node suggests. Full entry
Pre-call enforcement: Pre-call enforcement is a budget check that runs before an LLM request is sent to the provider, so an over-budget call is stopped before it costs anything rather than reported after it has. Full entry
Per-agent budget: A per-agent budget is a spending envelope scoped to one named agent, rather than to the API key, project, or account the agent shares with everything else. Full entry
Runaway agent loop: A runaway agent loop is an agent retrying or re-invoking itself without a terminating condition, generating LLM spend continuously until something outside the loop stops it. Full entry
Prompt prefix stability: Prompt prefix stability is the property that the opening bytes of a prompt are identical across calls, which is what allows a provider's prompt cache to match and discount repeated input. Full entry
Context regrowth: Context regrowth is the compounding cost of re-sending an entire conversation history with every turn, so total input tokens grow roughly with the square of the conversation length. Full entry
Tool result bloat: Tool result bloat is the cost incurred when large tool outputs — full API payloads, whole files, verbose logs — are inserted into an agent's context and then re-sent on every subsequent turn. Full entry
Cost attribution: Cost attribution is the assignment of every unit of LLM spend to the agent, team, feature, or customer that caused it, rather than leaving it aggregated under a shared API key. Full entry
Chargeback and showback: Chargeback is billing internal teams or external customers for the LLM costs they caused; showback is reporting those costs to them without moving money. Full entry
Fail-open vs fail-closed: A fail-open control stops controlling when its infrastructure is unreachable and lets traffic proceed; a fail-closed control blocks traffic instead, trading availability for guarantees. Full entry