K211617 · Infrascan, Inc. · OPT · Feb 9, 2022 · Ophthalmic
Device Facts
Record ID
K211617
Device Name
Infrascanner
Applicant
Infrascan, Inc.
Product Code
OPT · Ophthalmic
Decision Date
Feb 9, 2022
Decision
SESE
Submission Type
Traditional
Regulation
21 CFR 882.1935
Device Class
Class 2
Attributes
Pediatric
Indications for Use
The Infrascanner is indicated for the detection of traumatic supratentorial hematomas of as small as 3.5mL and as deep as 2.5 cm from brain surface, but not both at the same time, as an adjunctive device to the clinical evaluation in the acute hospital setting of adult patients and pediatric patients aged 2 years and older with suspected traumatic supratentorial intracranial hematoma. The device is indicated to assess patients for CT scans but should not serve as a subsitute for these scans, the device should only be used to rule in subjects for the presence of hematoma, never to rule out. The Infrascanner is indicated for use by Physicians, or under the direction of a physician, who has been trained in the use of the device.
Device Story
Infrascanner uses near-infrared spectroscopy (NIRS) to detect traumatic supratentorial hematomas. Device inputs include regional NIR light absorbance measurements from the patient's head; sensor is optically coupled via two disposable light guides in a 'hairbrush' configuration. Principle of operation relies on differential intracranial hemoglobin concentration between hematoma sites and normal brain tissue. Used in acute hospital settings by trained physicians or under physician direction. Examination takes approximately two minutes. Output provides information regarding potential hematoma development; clinicians use this to assess the need for CT scans. Device serves as an adjunctive tool to clinical evaluation; it is intended to rule in hematomas, not rule them out. Benefits include early identification of potential intracranial hematomas in head trauma patients.
Clinical Evidence
Clinical study enrolled 464 patients (aged 6 months–18 years) in emergency departments; 344 met inclusion criteria. Study complemented by literature meta-analysis. Results: Sensitivity 88.9% (2-12 yrs) and 85.7% (12-18 yrs); Specificity 72.3% (2-12 yrs) and 73.4% (12-18 yrs). Diagnostic performance was independent of age, hair/skin color, and race. Bench testing used multi-layered solid/liquid optical phantoms (silicone, intralipid, carbon black, titanium dioxide) to simulate human tissue, confirming repeatability, reproducibility, and agreement across age groups and skin types.
Technological Characteristics
Noninvasive NIRS-based sensor. Class I NIR-based sensor. Optically coupled via two disposable light guides in 'hairbrush' configuration. Materials include silicone (phantom), carbon black (absorber), titanium dioxide (scatterer). Connectivity: Standalone. Dimensions/form factor: Handheld sensor. Software: Embedded. Sterilization: Not specified.
Indications for Use
Indicated for adult and pediatric patients aged 2 years and older with suspected traumatic supratentorial intracranial hematoma (as small as 3.5mL and as deep as 2.5 cm). Used as an adjunctive tool to clinical evaluation in acute hospital settings to rule in hematoma presence; not for ruling out hematoma or as a substitute for CT scans.
Regulatory Classification
Identification
A Near Infrared (NIR) Brain Hematoma Detector is a noninvasive device that employs near-infrared spectroscopy that is intended to be used to evaluate suspected brain hematomas.
Special Controls
In addition to the general controls of the Act, the Infrascanner is subject to the following special controls:
*Classification.* Class II (special controls). The special controls for this device are:(1) The sale, distribution, and use of this device are restricted to prescription use in accordance with § 801.109 of this chapter;
(2) The labeling must include specific instructions and the clinical training needed for the safe use of this device;
(3) Appropriate analysis/testing should validate electromagnetic compatibility (EMC), electrical safety, and battery characteristics;
(4) Performance data should validate accuracy and precision and safety features;
(5) Any elements of the device that may contact the patient should be demonstrated to be biocompatible; and,
(6) Appropriate software verification, validation, and hazard analysis should be performed.
{0}------------------------------------------------
February 9, 2022
Image /page/0/Picture/1 description: The image contains the logo of the U.S. Food and Drug Administration (FDA). On the left side of the image is the Department of Health & Human Services logo. To the right of the HHS logo is the FDA logo, which consists of the letters "FDA" in a blue square, followed by the words "U.S. FOOD & DRUG" in blue, with the word "ADMINISTRATION" underneath.
InfraScan, Inc. % Angela Mallery Principal Product Development Strategist NAMSA 400 US-169 Minneapolis, Minnesota 55441
## Re: K211617
Trade/Device Name: Infrascanner Regulation Number: 21 CFR 882.1935 Regulation Name: Near Infrared (NIR) Brain Hematoma Detector Regulatory Class: Class II Product Code: OPT Dated: January 6, 2022 Received: January 10, 2022
### Dear Angela Mallery:
We have reviewed your Section 510(k) premarket notification of intent to market the device referenced above and have determined the device is substantially equivalent (for the indications for use stated in the enclosure) to legally marketed predicate devices marketed in interstate commerce prior to May 28, 1976, the enactment date of the Medical Device Amendments, or to devices that have been reclassified in accordance with the provisions of the Federal Food, Drug, and Cosmetic Act (Act) that do not require approval of a premarket approval application (PMA). You may, therefore, market the device, subject to the general controls provisions of the Act. Although this letter refers to your product as a device, please be aware that some cleared products may instead be combination products. The 510(k) Premarket Notification Database located at https://www.accessdata.fda.gov/scripts/cdrh/cfdocs/cfpmn/pmn.cfm identifies.combination product submissions. The general controls provisions of the Act include requirements for annual registration, listing of devices, good manufacturing practice, labeling, and prohibitions against misbranding and adulteration. Please note: CDRH does not evaluate information related to contract liability warranties. We remind you, however, that device labeling must be truthful and not misleading.
If your device is classified (see above) into either class II (Special Controls) or class III (PMA), it may be subject to additional controls. Existing major regulations affecting your device can be found in the Code of Federal Regulations, Title 21, Parts 800 to 898. In addition, FDA may publish further announcements concerning your device in the Federal Register.
Please be advised that FDA's issuance of a substantial equivalence determination does not mean that FDA has made a determination that your device complies with other requirements of the Act or any Federal statutes and regulations administered by other Federal agencies. You must comply with all the Act's requirements, including, but not limited to: registration and listing (21 CFR Part 807): labeling (21 CFR Part
{1}------------------------------------------------
801): medical device reporting of medical device-related adverse events) (21 CFR 803) for devices or postmarketing safety reporting (21 CFR 4, Subpart B) for combination products (see https://www.fda.gov/combination-products/guidance-regulatory-information/postmarketing-safety-reportingcombination-products); good manufacturing practice requirements as set forth in the quality systems (QS) regulation (21 CFR Part 820) for devices or current good manufacturing practices (21 CFR 4, Subpart A) for combination products; and, if applicable, the electronic product radiation control provisions (Sections 531-542 of the Act); 21 CFR 1000-1050.
Also, please note the regulation entitled, "Misbranding by reference to premarket notification" ( 21 CFR Part 807.97). For questions regarding the reporting of adverse events under the MDR regulation (21 CFR Part 803), please go to https://www.fda.gov/medical-device-safety/medical-device-reportingmdr-how-report-medical-device-problems.
For comprehensive regulatory information about medical devices and radiation-emitting products, including information about labeling regulations, please see Device (https://www.fda.gov/medicaldevices/device-advice-comprehensive-regulatory-assistance) and CDRH Learn (https://www.fda.gov/training-and-continuing-education/cdrh-learn). Additionally, you may contact the Division of Industry and Consumer Education (DICE) to ask a question about a specific regulatory topic. See the DICE website (https://www.fda.gov/medical-device-advice-comprehensive-regulatoryassistance/contact-us-division-industry-and-consumer-education-dice) for more information or contact DICE by email (DICE@fda.hhs.gov) or phone (1-800-638-2041 or 301-796-7100).
Sincerely,
Jay Gupta Assistant Director DHT5A: Division of Neurosurgical, Neurointerventional and Neurodiagnostic Devices OHT5: Office of Neurological and Physical Medicine Devices Office of Product Evaluation and Quality Center for Devices and Radiological Health
Enclosure
{2}------------------------------------------------
## Indications for Use
510(k) Number (if known) K211617
Device Name Infrascanner
#### Indications for Use (Describe)
The Infrascanner is indicated for the detection of traumatic supratentorial hematomas of as small as 3.5mL and as deep as 2.5 cm from brain surface, but not both at the same time, as an adjunctive device to the clinical evaluation in the acute hospital setting of adult patients and pediatric patients aged 2 years and older with suspected traumatic supratentorial intracranial hematoma. The device is indicated to assess patients for CT scans but should not serve as a subsitute for these scans, the device should only be used to rule in subjects for the presence of hematoma, never to rule out. The Infrascanner is indicated for use by Physicians, or under the direction of a physician, who has been trained in the use of the device.
| Type of Use (Select one or both, as applicable) |
|-------------------------------------------------|
|-------------------------------------------------|
X Prescription Use (Part 21 CFR 801 Subpart D)
| Over-The-Counter Use (21 CFR 801 Subpart C)
#### CONTINUE ON A SEPARATE PAGE IF NEEDED.
This section applies only to requirements of the Paperwork Reduction Act of 1995.
#### *DO NOT SEND YOUR COMPLETED FORM TO THE PRA STAFF EMAIL ADDRESS BELOW.*
The burden time for this collection of information is estimated to average 79 hours per response, including the time to review instructions, search existing data sources, gather and maintain the data needed and complete and review the collection of information. Send comments regarding this burden estimate or any other aspect of this information collection, including suggestions for reducing this burden, to:
> Department of Health and Human Services Food and Drug Administration Office of Chief Information Officer Paperwork Reduction Act (PRA) Staff PRAStaff@fda.hhs.gov
"An agency may not conduct or sponsor, and a person is not required to respond to, a collection of information unless it displays a currently valid OMB number."
{3}------------------------------------------------
# 510(k) SUMMARY
| Date | February 9, 2022 |
|-------------------------------------------------------------------------------------------|---------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------|
| Submitter's Name,<br>Address, Telephone<br>Number, Contact<br>Person and Date<br>Prepared | InfraScan, Inc. 3508 Market Street<br>Philadelphia, PA 19104<br>Phone: 215-387-6784<br>Facsimile: 215-386-2327<br>Contact Person: Baruch Ben Dor, CEO |
| Name/Address of<br>Sponsor | InfraScan, Inc.<br>3508 Market Street<br>Philadelphia, PA 19104 |
| Name of Device | Infrascanner Model 2000 and 25000 |
| Common or Usual<br>Name | Near Infrared (NIR) Brain Hematoma Detector |
| Classification Name | OPT (21 C.F.R. §882.1935) |
| Predicate Devices | InfraScan Infrascanner K120949 (Model 2000) and K200203 (Model 2500) |
| Indications for Use | The Infrascanner is indicated for the detection of traumatic supratentorial hematomas of as small as<br>3.5mL and as deep as 2.5 cm from brain surface, but not both at the same time, as an adjunctive device<br>to the clinical evaluation in the acute hospital setting of adult patients and pediatric patients aged 2 years<br>and older with suspected traumatic supratentorial intracranial hematoma. The device is indicated to<br>assess patients for CT scans but should not serve as a substitute for these scans, the device should only<br>be used to rule in subjects for the presence of hematoma, never to rule out. The Infrascanner is indicated<br>for use by Physicians, or under the direction of a physician, who has been trained in the use of the<br>device. |
| Device Description | The device is a noninvasive device, which uses near-infrared spectroscopy ("NIRS") to provide early<br>information about the possible development of traumatic supratentorial hematomas in patients<br>presenting to hospitals with head trauma. This technology involves comparing regional differences in<br>absorbance of NIR light. The application of NIRS to hematoma evaluation is based on the principle that<br>intracranial hemoglobin concentration will differ where a hematoma is present, compared to hemoglobin<br>concentrations in normal intracranial regions. The system consists of a Class I NIR-based sensor. The<br>sensor is optically coupled to the patient's head through two disposable light guides in a "hairbrush"<br>configuration. Examination with the Infrascanner is performed through placement of the sensor on<br>designated areas of the head that represent the most common locations for traumatic hematoma. The<br>examination is designed to be performed within two minutes. |
| Technological<br>Characteristics | The device remain unchanged from the predicate clearances<br>Bench testing comparing the subject device to the predicate using a pediatric laboratory model(s) of brain<br>hematoma as compared to adult laboratory models.<br>Testing included repeatability and reproducibility; agreement tests, and skin color tests; these results<br>established device performance metrics across a range of simulated hematoma sizes, depths, and for light<br>and dark skin and for bench hematoma models of adult and children 2 and above. |
{4}------------------------------------------------
Bench testing demonstrated that device functioned as intended. Testing comparing to the predicate was conducted using a hematoma model to provide an approximation of human tissue. Testing included repeatability and reproducibility. Results were consistent with the expected result. Performance was substantially similar for both models across a range of age groups, depths and sizes of hematomas, and for skin types. Additional laboratory testing demonstrated the comparability of the device and its predicate over the range of optical densities. Four types of tests were conducted in order to evaluate substantial equivalence Repeatability / Reproducibility to assess the degree of agreement between measurements conducted on . the same device. The repeatability and reproducibility test data involved repeat observations with three different systems for each of the two models. Model hematomas of 5 mL and 50 mL were evaluated at depths below the skull of shallow and deep ranges at 0 cm, and 3 cm . Agreement test to assess the degree of agreement between measurements conducted by Model 2000 and Model 2500. The agreement test data were collected for one system of each model for hematomas of size 5 mL and 50 mL . Skin color test to assess the effect of the skin color on the measurements conducted by Model 2000 and Model 2500. The evaluation of the potential impact of skin color was performed for both models with hematoma size of 5 mL at depths of 0 and 2 cm, and without a model hematoma in the tank . Pediatric test to assess the effect of age on the degree of agreement between measurements conducted by Model 2000 and Model 2500. The potential effect of age on the measurements by the two models was tested using one system of each model for hematomas of size 5mL and 50 mL at 0 and 3 cm depths, on the phantom side mimicking the head of a 6 months old A 4-corners approach was used the selection and testing of the hematoma size and depth and for the age groups Small (5 ml) and large (50 ml) hematomas ● Superficial (0 cm) and deep (2 and 3cm) hematomas . Adult (>18 years old) and infant (6 months old) ages were tested A mixed multi-layered solid and liquid optical head phantom mimicking human tissue was used in the test. For brain tissue optical parameters intralipid was used to control the scattering properties and a calibrated ink to control absorption properties. Modeled layers of skin, scalp, skull and CSF with the liquid brain layer and blood were used to simulate brain hematoma. Each of the phantom walls were built to mimic different age groups. Silicone was selected for building the phantom due to a close match to the mechanical properties of tissue. Carbon black was used as the absorbing agent, and Titanium Dioxide was used as the scattering agent. The optical absorption and scattering properties of each layer were confirmed further by optical frequency-domain measurement systems. The optical properties of the CSF laver were those of water. Thin neutral density (ND) Wratten 2 film filters were placed over the phantom to adjust the signal level to OD values observed in the clinical studies for patients with different skin color. The thickness of the film filters is similar to the thickness of human skin. Using those filters, the OD values in the new lab tests covered the range of OD to simulate light-skinned patients and OD to simulate dark skinned subjects. The attenuation values of the filters were selected to match the OD values observed in the clinical studies. The brain model was filled with water, intralipid for scattering and a black ink for absorption. This mixture created a simulation of brain tissue. Our approach is to use whole blood as a hematoma model was used in this test. The flat hematoma model was built using a rectangular frame, inserted into a ball, and filled with blood. The rectangular frame forced the shape of the hematoma to remain relatively flat. A clinical study was carried out in the Emergency Departments large urban quaternary care academic medical centers on males or females aged 6 months – 18 years. 464 patients were enrolled and 344 met inclusion for primary data analysis. In these patients, 10.5% had evidence of a hematoma on HCT, and 4.7% had qualifying hematomas. This clinical study data was complemented with a literature review meta-analysis to provide the following age-specific performance estimates and confidence intervals in the newly indicated pediatric population subgroups with comparison to the predicate adult population performance estimates: Clinical data Diagnostic performance was independent of age (divided by quartile), hair/skin color, and race. Diagnostic performance was independent of whether three (43% 149/344) or four (57% 195/344) brain regions were assessed.
{5}------------------------------------------------
| | Infrascanner performance in pediatric and adult subgroups | | | |
|----------------------------|------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------|-------------------------|-------------------------|-------------------------|
| | 2-12 Years Old | 12-18 Years Old | Adults<br>K080377 | |
| | Total | 220 | 146 | 383 |
| | No Hematomas | 202 | 139 | 320 |
| | Hematomas | 18 | 7 | 63 |
| | Sensitivity | 88.9%<br>65.3% to 98.6% | 85.7%<br>42.1% to 99.6% | 74.6%<br>62.1% to 84.7% |
| | Specificity | 72.3%<br>65.6% to 78.3% | 73.4%<br>65.2% to 80.5% | 81.6%<br>76.9% to 85.7% |
| | PPV | 22.2%<br>17.8% to 27.4% | 14.0%<br>9.7% to 19.6% | 44.3%<br>37.8% to 51.1% |
| | NPV | 98.6%<br>95.2% to 99.6% | 99.0%<br>94.3% to 99.8% | 94.2%<br>91.4% to 96.2% |
| | PPV - Positive Predictive Value, NPV - Negative Predictive Value. | | | |
| | Sensitivity, specificity, PPV and NPV values include also the 95% confidence intervals | | | |
| Substantial<br>Equivalence | The subject device is as safe and effective as the predicate device. The subject device has the same<br>intended for use, technological characteristics, and principles of operation as its predicate device. Bench<br>data demonstrate the subject device performance in pediatric subjects is substantially equivalent to the<br>performance in adult subjects of the predicate. | | | |
| Conclusion | The conclusions drawn from the nonclinical and clinical tests that demonstrate that the device is as safe, as<br>effective, and performs as well as or better than the legally marketed device predicate | | | |
Two short videos show you everything — or skip straight to the written tutorial if you'd rather read. You can reopen this any time from the Tutorial button in the top bar.
Part 1 — Search, results, and everyday workflows 16 min
Part 2 — Embeddings: the galaxy map 3 min
1. Search: exact and fuzzy
Type a phrase like "coronary artery calcification" into the search box. You get two kinds of results. Exact results match the literal phrase — prefix searches work ("coronary artery calcificati") but suffix searches do not. Fuzzy results match on the meaning and intent of your phrase rather than the exact words, and are sorted by relevance score. Hover over the Exact or Fuzzy badge on any row to see exactly why it matched.
Use the checkboxes above the results to narrow: SaMD keeps only software-only devices, AI / ML keeps only devices with AI.
Exact vs. fuzzy search: what's the difference?
Exact matches on the literal phrase (prefix search works, suffix does not). Fuzzy matches on the meaning and intent of the phrase rather than the exact words. Hover over the badge on any row to see why it matched.
You search "coronary artery calcification" and want only software devices with AI. What two filters do you apply?
Narrow by SaMD (software-only devices), then narrow by AI/ML (devices with AI).
2. The results table
Scroll right in the results table. The intended use is extracted for you — no need to open the PDF. The device story gives a high-level snapshot of what the device does and how it's used. The AI Performance sub-table shows each output name, acceptance criteria, observed values, and development/test dataset descriptions — the same format Innolitics uses for regulatory strategy outputs, and the fastest high-level fingerprint of an AI device. It is AI-generated but has been very reliable in practice.
Where do you find a device's intended use without opening the PDF?
Scroll right in the search results table. The intended use column is extracted for you; no need to dig into the 510(k) summary PDF.
What does the AI Performance sub-table show, and why is it useful?
Output name, acceptance criteria, observed values, development dataset description, and test dataset description. It's the same format we use for regulatory strategy output and Fast 510(k) input, and the fastest high-level fingerprint of an AI device. AI-generated but reliable in practice.
3. Judging fuzzy relevance
Fuzzy results trail off in relevance as you scroll. Use three signals to decide how far down to go: the fuzzy badge explanations, the intended use column, and whether your target output (e.g., Cobb angle) still appears in the AI Performance sub-table. Once it stops appearing, you're past the relevant zone. A top hit with a low score (~0.4) and a stretched explanation is a hint the closest predicates are far away — the project may be headed for De Novo. Note the fuzzy search is a pattern match: it doesn't handle negation ("not") well, and hardware devices can appear — filter by SaMD/AI ML to cut them.
How do you judge how far down fuzzy search results to go?
Use the relevancy signals: the fuzzy badge explanations, the intended use column, and whether the target output (e.g., Cobb angle) still appears in the AI Performance sub-table. Once it stops appearing, results are trailing off in relevancy.
4. Device detail page: chat and citations
Click a device name to open its detail page: device facts on the left, a chat window on the right. Ask something like "Describe the training data". The answer carries little citation bubbles — click one to jump to the highlighted passage in the source PDF, so you can verify every AI answer against the document. There's also a Download PDF button for sharing.
How do you verify an AI chat answer on the device detail page?
Click the citation bubbles to jump to the relevant highlight in the source document.
Reading rule for every project: how many summaries do you read in full?
At least the three most relevant 510(k) or De Novo summaries, in full. After that, use targeted chat questions to confirm your memory quickly. The tool supports this professional habit — it doesn't replace it.
5. Side-by-side comparison
Select multiple rows in the results table (aim for under ~10), then open the PDF Viewer tab. Ask one question — it goes to all selected devices in parallel, each with citations. This is the fastest way to compare and contrast devices: training data, PCCP scope, how they handled adding new scanners, and so on.
What does the side-by-side PDF viewer mode do?
Select multiple devices, open the PDF viewer tab, and ask one question (e.g., "Describe the training data"). It queries all selected devices simultaneously with citations, so you can compare and contrast quickly.
6. Collections
With rows selected, go to the Collections tab and create a labeled collection (e.g., "Cobb Angle Project"). Reload that selection any time — before a client call, pull up the collection and ask questions across all of its devices at once.
How do you save a set of selected devices for later use?
Select the rows, go to the Collections tab, and create a labeled collection (e.g., "Cobb Angle Project"). You can reload the selection anytime and carry it into the PDF viewer and other tabs that support selections.
7. Product codes and the regulations tree
Click a product code in the results to jump to it in the regulations tree — identification text, sibling product codes, and devices you can open in a PDF viewer on the right. Click a regulation number to see its identification, special controls, and related product codes. You can also search by product code or regulation number at the top of the tree. Always read the special controls if any exist for your device — it broadens your search and sharpens pre-kickoff research.
What can you do from the regulations tree view?
Browse product codes and regulation numbers, read the identification text and special controls, browse sibling product codes, open device PDFs on the right, and search by product code or regulation number at the top of the tree.
8. Chart view
Click Show Chart and segment by regulation number (or product code) to see which regulations dominate your result set. Clicking a regulation takes you into the regulations tree. Great for spotting that most matches are, say, hardware laparoscopic devices — a cue to go back and filter.
How do you see which regulations dominate a search result set?
Click "Show Chart" and segment by Regulation Number. Clicking a regulation takes you to the regulations tree.
9. The predicate graph
Open the Predicates tab for a family-tree view of predicate relationships. Click a node to trace its parents and children; selections from search carry over pre-selected. Commonly predicated devices are worth reading — a lot of people predicated them for a reason. The visual lineage is also handy on client calls, e.g. to show how a predicate family evolved and justify why your predicate still holds.
In the predicate graph, why are commonly predicated devices worth reading?
A lot of people predicated them for a reason. Clicking a node traces parents and children, and selections from search carry over pre-selected.
10. Embeddings: the galaxy map
The Embeddings tab plots every matching document in a 2-D "galaxy map" where semantically similar devices cluster together. Hover or click clusters to explore, and let AI label the clusters for you. Embeddings beat product codes for grouping: two devices can carry different product codes (LLZ vs. QIH) yet do the same thing — the embedding captures the meaning of the intended use and device story. This is also exactly how retrieval-augmented generation (RAG) works under the hood, and it makes a great visual on client calls.
Try it yourself
Head to the search page and work through a few of these AI/ML fuzzy searches to build intuition: perivascular fat on CT · aortic valve calcification opportunistic screening on noncontrast CT · breast cancer prediction on digital pathology slides · autism detection · gestational age prediction · a hearing aid that can also detect a pulse · foundation model based analysis of ECG · large language models · penetration test. Watch how the relevance scores, intended use, and AI Performance tables tell you when results stop being meaningful.