Agentic Attribution of Cloud Resource Ownership
Organizations: Sola Security
Abstract
Security tools raise findings across cloud environments, and AI agents now investigate and prioritize them. A finding is still resolved by people: it has to reach the people responsible for fixing it and accountable for the resource it concerns. Ownership is the organizational context that decides who that is. Where recorded, it is declared by hand in configuration management databases or owner tags and goes stale unless kept current; accounts are shared, and automation creates much of the infrastructure. The knowledge sits in work records, code history, audit logs and identity directories, encoded in each organization's own conventions. Recovering it poses four challenges: the signal is scattered across sources, none of them authoritative; the conventions that carry it differ between organizations; reaching an owner takes multi-hop links; and those related to a resource differ in the strength of their relation. We define ownership as a set of entities, people or teams, each related to the resource by one of five patterns ordered by strength. We present a reference architecture for agentic ownership attribution that derives ownership from these records instead of declaring it: it profiles an organization offline into tested signal procedures and an ownership playbook, then attributes each resource with a coordinator agent and parallel investigators, with confidence computed by rules. On 100 resources of 50 Amazon Web Services (AWS) resource types in one organization, we pool the architecture's candidates with those of an unprimed general-purpose agent and verify every evidence piece against the records. The architecture reaches 92.1% weighted recall and 86.6% weighted precision, against 54.8% and 77.4%, at 0.55 times the agent's cost per unit of coverage. The difference lies in people who build and change resources without an explicit owner, found through work records and code history.
Figures & tables
| Pattern | Definition | Strength |
|---|---|---|
| Explicit owner | The entity’s name, username or email appears in the resource’s name or in metadata recorded on it, or a recorded action shows the entity created it | Highest |
| Direct work | Builds, changes, runs or answers for this resource, or for the thing it exists for | Highest |
| Indirect work | Builds, changes, runs or answers for something around the resource (its environment, the infrastructure beneath it, related resources); the link to this resource is inferred | Intermediate |
| Relies on it | Uses the resource or its system, builds on top of it, or reports problems while using it | Low |
| Peripheral | A weak link (a mention, a look-alike), or no pattern fits | Lowest |
| Non-human identity | Service account, machine user, role used by software | Not an owner |
| Criterion | Metric | Architecture | Baseline agent |
|---|---|---|---|
| Coverage | Weighted recall | 92.1% | 54.8% |
| Success rate | 99 of 100 | 89 of 100 | |
| Correctness | Weighted precision | 86.6% | 77.4% |
| Rejected candidates | 12 | 10 | |
| Cost | Per resource, uncached list prices | $0.63 | $0.68 |
| Per resource, per unit of weighted recall | $0.68 | $1.24 |
| Relation | Pool | Architecture | Baseline agent |
|---|---|---|---|
| Explicit owner | 49 | 47 | 48 |
| Direct work | 141 | 131 | 53 |
| on resources without an explicit owner | 123 | 117 | 47 |
| Indirect work, relies on it, peripheral | 40 | 20 | 29 |
| Total | 230 | 198 | 130 |
| Source | Architecture (198) | Baseline agent (130) |
|---|---|---|
| Cloud resource metadata: tags, names, linked resources | 81% | 75% |
| Person directories | 68% | 17% |
| Work-tracking tickets | 65% | 52% |
| Pull requests and commits | 46% | 2% |
| Code-hosting logins, teams and repositories | 28% | 3% |
| Cloud audit log activity | 18% | 29% |
| Resources | Architecture | Baseline agent | |
|---|---|---|---|
| Data and storage | 21 | 95% | 44% |
| Compute and containers | 20 | 94% | 59% |
| Security and secrets | 14 | 93% | 66% |
| Network foundation | 18 | 89% | 45% |
| Events, messaging and operations | 13 | 89% | 72% |
| Traffic and APIs | 14 | 88% | 61% |
Cloud Computing
Cloud computing studies on-demand delivery and management of compute, storage, and services across distributed infrastructure.
See all 52 papers