Glossary
Plain definitions of the terms around AI agents that act on real systems.
- Agent action record
One durable entry for one thing an AI agent did, from the request to the result.
- Blast radius
Everything an AI agent can change with the access it has.
- Hash-chained log
A log where each entry carries the hash of the one before it, so a removed or edited entry breaks the chain.
- Logical decoding for agent audits
Reading what Postgres committed, row by row, and comparing it with what the agent said it did.
- MCP gateway
A proxy between AI clients and the MCP servers they call.
- Policy countersign
A rule that holds an agent's action until a person approves it.