Checklist · European teams · Runtime controls

Check the runtime controls under each AI use case.

Talon’s category is the control plane for company AI use cases. Use this supporting technical checklist to test whether identity, effective policy, spend, failure paths, sessions, sensitive data, intercepted tools, destinations and evidence are handled deliberately.

AI use case runtime

[ ] one vault-bound agent key
[ ] one resolved effective policy
[ ] cost controlled before next call
[ ] transient failure path defined
[ ] asserted sessions explainable
[ ] sensitive data handled before egress
[ ] destination policy enforced
[ ] intercepted decisions evidenced
[ ] evidence integrity verifiable
Agent identityEffective policyCostReliabilitySessionsPrivacyDestinationsEvidence

Identity and policy checks

Can Talon tell which use case is acting and which rules apply?

CheckWhy it mattersTalon proof path
One agent identity is bound to the use caseFree-form application labels should not become the security principal.agent.key.secret_name points to one encrypted vault secret; the presented key resolves agent and tenant.
Unknown or conflicting keys fail closedAuthentication ambiguity can turn into cross-use-case access.Unknown keys return 401; identity mismatch returns 403; agent/admin key collision fails startup.
The effective policy is computed oncePrimary routing, fallback, reporting and evidence must not reinterpret controls differently.Organization baseline plus one agent override feeds one resolved snapshot and signed policy digests.
Organization constraints remain hardA use-case override must not weaken the company boundary.PII floor, provider/model restrictions, tier ceiling and intersected egress remain binding.
Security-sensitive configuration is strictA typo must not silently disable a control.Strict gateway decode, enum/minimum validation and unknown-field preflight.

Core operating checks

Can the company operate this use case consistently?

CheckWhy it mattersTalon proof path
Spend is attributable to the authenticated agentProvider bills alone do not explain which application or session spent.Per-agent cost views and agent-scoped session cost.
Budget decisions happen before provider accessAlerts after spend do not stop the next request.Configured per-request/per-agent limits and session soft caps.
Transient failure has an explicit pathAvailability recovery must not bypass policy.Configured fallback candidates with effective-policy re-check and linked evidence.
Runtime policy is sharedEach app should not reinvent model, provider, PII, tool and regional rules.Organization policy plus one agent override on supported intercepted paths.
Asserted sessions are explainableMulti-request runs need a coherent cost and outcome history.Session list, export, cost and verification scoped by tenant and authenticated agent.

European trust checks

Can the operating layer support security, privacy and residency review?

CheckWhy it mattersTalon proof path
Sensitive input is scanned before provider accessPolicy must run before data leaves when the path is governed.Built-in, Presidio-compatible or local scanner paths where configured.
PII action cannot be weakened below the organization floorOne application should not silently relax the company data boundary.An agent may tighten allow/warn/redact/block posture; weaker actions are ignored.
Destination policy is explicitEU/local intent should constrain actual provider paths.Hard sovereignty rules plus organization/agent egress intersection and candidate rejection.
Intercepted tool exposure is constrainedAgents should not automatically see or execute every available action.Gateway tool-schema policy and intercepted MCP/tool governance.
Runtime decisions are reviewableSecurity and audit teams need reasons, not only dashboards.Signed evidence, policy digests, export and verification.

Session and subagent semantics

Do not confuse workflow attribution with Talon authentication.

The Talon agent key authenticates the AI use case. Client-supplied session and subagent metadata explains work inside that boundary but is not independent workload attestation. Two agents using the same session text remain isolated.

[ ] agent key is stored outside YAML
[ ] session state is scoped to tenant + agent
[ ] subagent labels are treated as attribution
[ ] no policy decision trusts free-form subagent text
[ ] identical session ids across agents stay separate

Honest boundaries

An unchecked path cannot be governed by a checklist.

Local shell commands, file edits, browser actions and direct API calls that bypass Talon remain invisible. HMAC-signed evidence is tamper-evident, not magically immutable. Session caps are soft without atomic reservation. These boundaries belong in the review.

[ ] all critical provider paths cross the control plane
[ ] intercepted tool paths are identified
[ ] bypass paths are documented
[ ] soft budget semantics are understood
[ ] evidence integrity is sampled
[ ] legal conclusions stay outside the software claim

Use the checklist as a test plan

Turn every unchecked box into a reproducible experiment.

Create one real agent identity, route the relevant path through Talon, trigger an authentication, budget or policy decision, inspect the session or provider path, and verify the resulting evidence.