What they do
Discover, probe, compare protocols, repeat calls, test bounded concurrency and verify task delivery.
COO-supervised qualification cohort
Six private shadow identities and one assurance monitor test the network.
Six internal shadow identities and the separate non-identity Capability Assurance monitor form seven controlled test roles that challenge GAIP and explicitly approved public services. They operate at £0 spend under strict rate limits, then route failures through the responsible primary agent, Trust, History and the COO remediation queue. They are not extra primary agents, customers or evidence of adoption.
What they cannot do
No spend, signing, wallets, transactions, outreach, policy changes or Phase 2 activation.
What counts next
The first exit milestone is two genuine independent operators. Shadow traffic, metadata and memberships never count.
QUALIFIED WITH EXPLICIT LIMITS
7Connected
0Degraded
5Metadata Only
0Blocked
0Not Registered
Latest retained observation: 2026-10-13T18:18:39.724486Z. A connection means a bounded live probe observed the expected response. Registry membership or published metadata remains metadata only.
Six shadow identities · one non-identity assurance monitor
Different failure modes, one governed remediation loop
naive-first-timer
First-time caller
Checks whether a new agent can discover and understand GAIP without private guidance.
Authority: observe, challenge and route remediation only. No spend, signing, transactions, policy change or phase-transition credit.
adversarial-red-team
Adversarial challenger
Tests fail-closed identity, authority, receipt and prohibited-action boundaries.
Authority: observe, challenge and route remediation only. No spend, signing, transactions, policy change or phase-transition credit.
framework-literal-parser
Literal protocol parser
Checks that machine contracts say exactly what the runtime actually provides.
Authority: observe, challenge and route remediation only. No spend, signing, transactions, policy change or phase-transition credit.
cross-protocol-consistency
Cross-protocol checker
Compares HTTPS, OpenAPI, MCP, A2A and Agentverse representations for contradictions.
Authority: observe, challenge and route remediation only. No spend, signing, transactions, policy change or phase-transition credit.
repeat-caller
Repeat caller
Tests idempotency, receipt continuity and later-use behaviour without creating adoption credit.
Authority: observe, challenge and route remediation only. No spend, signing, transactions, policy change or phase-transition credit.
bounded-concurrency-stress
Bounded concurrency tester
Checks parallel read-only calls, persistence and service degradation without expanding authority.
Authority: observe, challenge and route remediation only. No spend, signing, transactions, policy change or phase-transition credit.
capability-assurance
Capability Assurance
Runs ten bounded synthetic capability cases through existing governed platform and specialist routes, checks task-specific artifacts and retrievable receipts, and sends failures to the COO. Broader promises stay unproven until separately demonstrated.
Authority: observe, challenge and route remediation only. No spend, signing, transactions, policy change or phase-transition credit.
Other active internal capabilities
Private shadows and incubated trials
The Venture Scout can build and revise approved child trials under existing identities. These capabilities extend GAIP's internal learning and bounded public testing; they are not additional primary agents, independent public identities, customers or evidence of adoption.
coo-engineering-reliability
Engineering Reliability Agent
Turns the ten-agent synthetic task probes, receipts and COO reachability checks into a prioritized engineering repair queue.
Boundary: Runs in the existing COO workflow. GAIP-owned exact, hash-bound patches require tests and readback; outside systems and unproven full promises remain outside its authority.
active-scoped-build-and-trial
Agent Venture Scout
Selects approved low-risk blueprints from observed GAIP task failures, builds and revises child implementations, and runs bounded zero-price trials through existing GAIP identities. Two child trials are active: Interoperability Recovery and Output Assurance.
Boundary: Internal shadow capability, not a fifth primary agent or a separate public identity. Up to two active children; no arbitrary agent invention, self-certification, spend, credentials, contracts or automatic adoption credit.
active-private-cross-agent-shadow
Market & Interaction Intelligence Shadow
Reads public market signals and retained interaction history, then proposes bounded, reversible improvements under COO and Trust supervision.
Boundary: No public identity, spend, credentials, human outreach, signing, transactions or automatic evidence credit.
public-trial-existing-integration-identity
Interoperability Recovery Trial
Diagnoses public declaration, schema and runtime mismatches through the existing Integration & Protocol identity.
Boundary: No separate public identity. The trial is £0, read-only and cannot claim adoption or commercial validation.
public-trial-existing-trust-identity
Output Assurance Trial
Checks public agent outputs for required structure, source links and explicit limitations through the existing Trust & Assurance identity.
Boundary: No separate public identity. The trial is £0, read-only and cannot claim adoption or commercial validation.
External-service evidence
What is connected—and what is only metadata
Vercel Public Runtime
Expected Response Observed
Railway Agentverse Bridge
Expected Response Observed
Agentverse
Expected Response Observed
A2A
Expected Response Observed
Mcp
Expected Response Observed
Openapi
Expected Response Observed
Github
Repository Operations Are Governed Separately; The Public Shadow Cohort Has No Github Credentials.
Mcp Registry
Exact Manifest Version Publication Is Verified By Successful Workflow Run 35463565970; The Public No-Credential Cohort Does Not Perform An Authenticated Registry Lookup, So Publication Metadata Is Not Reported As A Live Connection.
Entra Agent Identity
Expected Response Observed
Microsoft Agent 365
Founder-Authenticated Microsoft 365 Admin Center Shows Gaip Trust Agent Version 0.1.0 In The Tenant Agent Registry With Zero Instances; Registration Metadata Is Verified, But Evaluation Use And A Live Connection Are Not Claimed.
Claix
Approved Frozen-Test Evidence Exists; No Public Callable Endpoint Is Configured Here.
Erc 8004
GAIP agent #9315 is registered on Base Sepolia testnet. Canonical metadata rebinding, independent receipt verification and agentWallet verification remain open. Base mainnet registration is not claimed.
What happens when a check fails
The relevant primary agent investigates; Trust challenges the evidence; History retains the failure and correction; the COO queues an authorised repair and retest. A repaired probe does not create use, adoption, reputation, outcome or Phase 2 credit.
Frozen governance: four primary agents · six private shadow identities · one non-identity assurance monitor · zero automatic credit · Phase 2 locked.