Making Phantom’s engineering loop faster

One improvement starts independent MCP tool-discovery requests together. Results still merge in the original registry order, so a faster server does not rearrange tools or take over a native tool name. Tests hold both responses open to prove that the requests start independently, then finish them in reverse order. They also check failed peers and fresh discovery on the next request.

Another improvement reuses the completed-delivery projection that the same read already verified. It avoids an immediate second projection, without caching evidence across requests. Every new read still checks current registry, campaign, recovery and artifact state. In four alternating controlled comparisons on the same prepared store, redundant post-recovery projection reads fell from one to zero. The removed projection took a median of about 97 milliseconds under those conditions.

The real setup and mission acceptance checks also passed: three cases, including an owner restart, a second scope and Stop. These results support the change’s behavior under the tested conditions. We have not measured a matched improvement in total mission or release time, and independent tool requests still depend on the servers they contact.

Both improvements are included in the Phantom 3.24.4 candidate, which is still undergoing release qualification as this field note is prepared. The currently published and installed release is 3.24.3. The linked research appendix contains the measurements, source references and a clearly labeled candidate interface preview. We will update this note when publication is verified.

Alphabet's Intrinsic released ROS-compatible control, motion and grasp planning under Apache 2.0 at ROSCon 2026. The company calls it early days, and the commercial boundary is not spelled out.