Framework

The selfdriven
Agent Roster

Every AI agent active in a selfdriven engagement holds a delegated KERI credential — a cryptographic proof of what it is authorised to do, issued by the accountable human conductor. No agent operates outside its bounded scope.

AI agents with bounded authority

In a selfdriven engagement, no AI agent operates with open-ended access. Every agent in the roster has a defined domain, a scoped authority credential issued via KERI delegation, and a time-limited mandate tied to the specific engagement.

The Agent Roster is the live registry of agents active in your engagement — what each agent is authorised to do, who delegated that authority, and how to verify it independently.

Delegation, not configuration

Traditional AI systems rely on configuration files and API keys to define what an agent can access. If those credentials are compromised or misconfigured, the scope of the breach is opaque. selfdriven agents receive authority through KERI delegated inception events — cryptographic, auditable, and revocable.

Every agent in the roster has a verifiable chain of authority from the issuing conductor to the specific task scope, anchored in the Key Event Log.

The Roster

Domain agents across the 8 Areas of Focus

selfdriven maintains a standing roster of specialist AI agents, each aligned to one or more Areas of Focus. For any engagement, a subset of these agents is delegated and activated by the assigned human conductor.

DIRECTION AGENTS
Strategy & Governance
Enterprise strategy synthesis, regulatory mapping, governance framework design.
  • Strategy Agent — synthesises market signals into strategic options
  • Governance Analyst — maps regulatory requirements to operational controls
  • Regulatory Mapper — tracks APRA, ASIC, AUSTRAC obligations
ENGAGEMENT AGENTS
Community & Partnerships
Ecosystem mapping, stakeholder analysis, partnership strategy.
  • Partner Scout — identifies and evaluates partnership opportunities
  • Community Analyst — maps stakeholder networks and influence patterns
  • Ecosystem Mapper — models industry relationships and dependencies
ENABLEMENT AGENTS
Technology & Capability
Technical architecture review, capability gap analysis, build vs buy assessment.
  • Architecture Analyst — reviews technical stack and identifies gaps
  • Capability Assessor — maps current vs required organisational capabilities
  • Build-Buy Evaluator — structures make/buy/partner decision frameworks
PROTOCOLS AGENTS
Risk & Compliance
Risk identification, compliance mapping, control framework design.
  • Risk Analyst — identifies, scores and monitors engagement-specific risks
  • Compliance Auditor — maps controls to regulatory requirements
  • Reporting Agent — generates board-ready risk and compliance reports
SUSTAINABILITY AGENTS
Finance & ESG
Financial modelling, ESG assessment, materiality analysis.
  • Financial Modeller — builds scenario-based financial projections
  • ESG Assessor — maps material ESG factors and reporting obligations
  • Impact Analyst — quantifies social and environmental impact claims
PROCESSES AGENTS
Operations & Delivery
Process mapping, automation assessment, service delivery optimisation.
  • Process Mapper — documents and models current-state workflows
  • Automation Assessor — identifies automation opportunities and ROI
  • Delivery Optimiser — structures delivery cadence and milestone tracking
ORGANISATIONAL AGENTS
People & Change
Organisational design, change readiness, talent gap analysis.
  • OrgDesign Agent — models organisational structures and spans of control
  • Culture Analyst — assesses change readiness and cultural alignment
  • HR Architect — identifies talent gaps and capability build pathways
ACCOUNTABILITY AGENTS
Governance & Assurance
Audit trail management, credential verification, assurance reporting.
  • Audit Trail Agent — anchors all engagement actions to the KERI KEL
  • Credential Verifier — validates ACDC credentials and authority chains
  • Assurance Reporter — generates cryptographically evidenced assurance outputs
Delegation Model

How agent authority works

Every agent in an engagement receives authority through a formal cryptographic delegation — not a configuration file, not an API key, but a verifiable KERI credential chain.

Human Conductor

  • Holds the master AID for the engagement
  • Issues delegated inception events (dip) to activate each agent
  • Issues ACDC credentials scoping each agent's domain and time limit
  • Can revoke any agent credential at any time via a rotation event
  • Is the sole accountable party — agents act as extensions of conductor authority

AI Agents

  • Each holds a delegated AID derived from the conductor's AID
  • Authority is bounded by the ACDC credential issued at activation
  • Can only act within the domain, scope, and time window specified
  • All actions generate interaction events (ixn) anchored to the KEL
  • Cannot self-authorise, self-escalate, or exceed their delegated scope
Verification

Verify any agent's authority independently

You don't need to trust selfdriven's word that an agent is authorised. The KERI credential chain is independently verifiable by any party with access to the engagement KEL.

01
Request the agent AID
Any agent active in your engagement can provide its AID and the AID of its delegating conductor on request.
02
Resolve the KEL
The Key Event Log for the agent's AID shows the delegated inception event, the scope credential, and all subsequent interaction events.
03
Verify the delegation chain
The delegation traces back to the conductor's AID and from there to the selfdriven Foundation's vLEI-anchored root identity.
04
Confirm scope & time bounds
The ACDC credential specifies exactly what the agent is authorised to do, in what domain, and until what date — all cryptographically bound.