Google-backed energy software company Tapestry has deployed its HyperQ AI platform to handle the initial site control review for PJM Interconnection's first reformed interconnection queue cycle.

In a blog post, the company claimed to have processed 811 generation applications representing 220GW of potential capacity in under an hour.

PJM is the US’ largest Regional Transmission Organization (RTO), which supplies power to 13 states and the District of Columbia. The RTO recently shifted from a first-come, first-served interconnection queue to a first-ready, first-served cluster framework under FERC Order 2023. The site control verification process confirms whether applicants have legal rights over the land where they intend to build, and has become a prerequisite for applications to advance.

According to Tapestry, its HyperQ platform processed 4,581 raw site control documents into 2,328 agreement bundles and ran 9,312 parallel compliance assessments, covering contract term, chain-of-title continuity, exclusivity, and minimum acreage requirements. The median processing time per assessment was six minutes 15 seconds, with 95 percent of tasks completed within 28 minutes.

The firm claimed that the process was 20 times faster than traditional manual review, though the comparison uses what the company describes as a conservative lower-bound anecdotal historical baseline of four hours per application.

The HyperQ platform uses multimodal AI to analyze PDFs, maps, and legal documents, returning page-level citations to PJM engineers who make the final compliance determinations. Tapestry contends the citation system has reduced the time engineers spend locating supporting documentation.

Tapestry said that it spent ten months working with PJM to integrate the tariff requirements into the system's logic, using a dataset of 234 historical queue applications to refine performance. The company said that HyperQ completed reviews for 99 percent of applications in under an hour.

Following this, Tapestry said that it intends to extend the AI system into electrical data reviews, including single-line diagrams and equipment specifications, and eventually to a developer-facing tool allowing applicants to pre-validate submissions before formal filing.

The RTO signed a partnership agreement to deploy Tapestry’s agentic AI system last April. Tapestry is a Google X 'moonshot project' that, through the use of AI, is building what they say is the first unified model of the grid. In doing so, the company hopes to help everyone who plans, builds, operates, and manages the grid to optimize energy flow and bring more diverse sources of energy online.