Additive Snack · 18 Mar 2025 · 34m · Episode 2
Isabelle Hachette, CEO of Interspectral, explains how her company applies AI and data fusion from medical imaging to additive manufacturing process monitoring. She details their software platform, AM Explorer, which ingests multi-sensor data to provide automatic error detection and root cause analysis for metal 3D printing. Hachette discusses how these insights help companies like Volum E reduce inspection time by 90% and accelerate the transition from prototyping to certified production.
Where this conversation describes AI being used to build or deliver a product. Part of the AI in practice tracker.
Quality & testInterspectral AM Explorer90% less time on image analysis
The software uses AI to automatically detect errors in additive manufacturing builds, reducing the time spent on manual image analysis by 90% for one customer.
“when they started using Explorer, they can really reduce the total amount, uh, go of the image analysis, maybe going from, yeah. 90% um, uh, less time of uh, using uh, in uh, image um, analysis.”
Isabel Hachette · Hear it at 6:56
Quality & testInterspectral AM Explorerup to €50,000 saved per machine per year
The AI solution helps manufacturers save significant costs by detecting faulty parts and job crashes early, avoiding expensive waste.
“we have seen some examples on where we can save up to €50,000 per machine and per year by using, uh, our solution.”
Isabel Hachette · Hear it at 26:23
Engineering & simulationInterspectral AM Explorer
The system uses a generically trained AI algorithm to detect errors in specific machine types, which can be retrained for specific applications or system models.
“So we have a, a generically trained algorithm for arrow detection on, for example, US systems. But we can also do, um, Uh, retraining if there is a specific um, application area or specific uh, model of the system, then we can do some retraining of that.”
Isabel Hachette · Hear it at 12:20
companies scaling up
Other shows on the same ground, closest first.
Hosts Daniel and Forbode discuss three engineering stories: an AI model by NIST that predicts flashover in fires using sensor data and simulations; NASA’s use of ultrasonic additive manufacturing (UAM) via subcontractor Fibrosnic to create complex, dissimilar-metal heat exchangers; and Levitate, a company founded by an amputee in partnership with the Technical University of Denmark, which offers affordable, plug-and-play athletic prosthetics using proprietary composite materials.
PhD candidate Yayati Jadhav and Professor Alireza Farimani at Carnegie Mellon University developed a self-correcting 3D printing system using a multi-agent AI framework. The system uses cameras and a vision language model to detect defects in real-time, allowing the printer to adjust parameters like flow rate and temperature mid-print. This closed-loop approach resulted in a 5X increase in peak load capacity and consistently identified failure points better than human experts. The hosts discuss how this technology could be retrofitted onto existing high-end machines to move beyond simple detection to autonomous correction.
Anna-Katrina Shedletsky, CEO and co-founder of Instrumental, explains how her platform uses AI and aggregated product data to optimize manufacturing and reduce waste. Drawing from her experience leading product design teams at Apple, including the high-risk Apple Watch program, she details how Instrumental helps companies close feedback loops in development and production. She highlights specific use cases, such as using unsupervised learning to correlate visual inspection data with functional test failures, to improve yield and accelerate time-to-market. Additionally, Shedletsky discusses her Women in STEM Mentorship Program and Instrumental's recent recognition on the Inc. 5000 list.
Jeff Mize, CEO of PostProcess Technologies, explains how his company automates the post-processing step of 3D printing to solve the industry's biggest bottleneck. He details the transition from manual labor to automated support removal and surface finishing, highlighting the role of data science and the 'Connected' software platform in creating a digital thread. Mize discusses the inflection point for additive manufacturing in production, particularly in medical, dental, and automotive sectors, and shares lessons from his Silicon Valley background on moving fast.
Priyansha Bagaria, founder and CEO of Loopr.ai, explains how her company uses AI-powered computer vision to automate quality inspection in aerospace, automotive, and general manufacturing. She details the deployment of their software applications, IQ Inspect for defect identification and IQ Verify for assembly verification, which are hardware-agnostic and integrate with existing camera infrastructure. Bagaria highlights key industry pain points, including the high cost of quality, labor shortages, and the loss of institutional knowledge as experienced workers retire, arguing that AI provides the consistency and scalability that human inspection cannot. She also discusses Loopr's strategic partnership with Microsoft and the importance of starting with high-value pilot projects to demonstrate clear ROI before scaling across factory floors.
The summary, chapters and topics are generated from the episode’s audio by this directory, not written by Additive Snack. The episode itself belongs to its publisher.