Memory isolation with row-level security, not application code
Caller identity comes from auth, each memory carries its scope, and Postgres row-level security enforces the boundary. Nothing in the request body can cross it.
Tagged
security
← All postsThe hardest problem in multi-agent teams is scoping
Past one person, the hard question is scope: who may touch what, on whose behalf, with what budget, with what record. The organization has to answer it.
What are spend caps for AI agents, and how do they work?
Spend caps stop an agent loop from draining a budget. On CoreSpeed an org wallet threshold and per-key monthly caps refuse metered calls before a tool runs.
What is a plain-English approval policy?
Sentences, read in full for every write an agent makes. Every save is a version, Test policy runs a hypothetical call, and a default you pick covers the gaps.
What is an agent identity (and why not just an API key)?
An agent identity is a principal of its own, with an id, keys, an owner who answers for it, and reach limited to shared connections. A personal API key acts as you.
What is an audit trail for AI agents?
An audit trail records what each agent did, as whom, and how it ended. CoreSpeed keeps one per org: action, actor, outcome, code and cost, never the prompt.
What is credential custody for AI agents?
Credential custody means the agent asks for an action and the platform performs it with the right account. The agent never holds the token, so a leak exposes no app credential.
When to bring your own OAuth app (Google, Microsoft, Meta) and how
Google, Microsoft and Meta gate shared OAuth apps behind review. An org admin registers your own app: paste client_id and client_secret, match the scopes.
Why your agent should never hold an OAuth token
An agent that holds a token can leak it through a prompt, a log or a transcript. Credential custody lets a platform act with the right account instead.