Agentic AI Atlasby a5c.ai
OverviewWikiGraphFor AgentsEdgesSearchWorkspace
/
GitHubDocsDiscord
iiRecord
Agentic AI Atlas · Voice Tool-Loop Governance (proposed)
agent-governance-impl:voice-governance@proposeda5c.ai
Search record views/
Record · tabs

Available views

II.Record viewspp. 1 - 1
overviewjsongraph
II.
AgentGovernanceImpl overview

agent-governance-impl:voice-governance@proposed

Reference · live

Voice Tool-Loop Governance (proposed) overview

PROPOSED out-of-band governance for a realtime voice agent's mid-conversation tool/decision loop. babysitter is a deterministic, fsync-per-step, replay-by-re-execution orchestrator and CANNOT sit in the sub-second audio turn; instead each governed tool is an async MCP tool whose handler drives an in-process babysitter run off the hot path. The run decomposes the workflow (ctx.task/ctx.parallel), enforces policy (PolicyEngine deny-on-dispatch), gates sensitive actions with ctx.breakpoint (auth./destroy. postures force owner-level human approval), and emits an append-only, checksummed, replayable journal as the audit trail. Governance latency is hidden behind filler speech + async/background tools so the audio path never blocks. See docs/research/voice-governance-bridge-spec.md.

AgentGovernanceImplOutgoing · 5Incoming · 0

Attributes

displayName
Voice Tool-Loop Governance (proposed)
status
proposed
agentVersionId
agent-version:babysitter@current
componentKind
voice-tool-governance
description
PROPOSED out-of-band governance for a realtime voice agent's mid-conversation tool/decision loop. babysitter is a deterministic, fsync-per-step, replay-by-re-execution orchestrator and CANNOT sit in the sub-second audio turn; instead each governed tool is an async MCP tool whose handler drives an in-process babysitter run off the hot path. The run decomposes the workflow (ctx.task/ctx.parallel), enforces policy (PolicyEngine deny-on-dispatch), gates sensitive actions with ctx.breakpoint (auth./destroy. postures force owner-level human approval), and emits an append-only, checksummed, replayable journal as the audit trail. Governance latency is hidden behind filler speech + async/background tools so the audio path never blocks. See docs/research/voice-governance-bridge-spec.md.
governedSurfaces
  • voice-agent-tool-call-loop
  • mid-conversation-workflow-decomposition
  • sensitive-action-execution
  • consequential-visual-tools (canvas-content, screen-share-vnc, external-video-metadata)
riskControls
  • policy-engine-deny-on-dispatch
  • breakpoint-approval-gates (auth./destroy. -> owner)
  • human-in-the-loop-mid-call
  • irreversible-action-guarding (disallow_interruptions/wait_for_playout pairing)
evidenceProduced
  • append-only-checksummed-journal
  • per-decision-replayable-audit-trail
  • voicecall-crd-governanceRuns-status

Outgoing edges

composes1
  • agent:babysitter·AgentProductbabysitter
depends_on2
  • source-ref:babysitter-sdk·SourceRef
  • agent-runtime-impl:voice-agent@proposed·AgentRuntimeImplVoice Agent Runtime (proposed)
implements1
  • extension-interface:governance·ExtensionInterfaceGovernance
realizes1
  • layer:14-governance·LayerGovernance

Incoming edges

None.

Related pages

No related wiki pages for this record.

Shortcuts

Open in graph
Browse node kind