Amazon Nova AI Challenge: FAQs

Including details about the 2026 Trusted Software Agent track.
General
What is the Amazon Nova AI Challenge?
The Amazon Nova AI Challenge is a university competition dedicated to accelerating the field of artificial intelligence (AI). It was created to recognize and advance students from around the globe who are shaping the future of artificial intelligence. Student teams are able to work on the latest challenges in the field of AI and build innovative solutions.
How does the Amazon Nova AI Challenge support research?
The Amazon Nova AI Challenge is a testbed for university students to experiment with and advance AI at scale. Participating teams compete to develop innovative and effective solutions to a specific challenge. Teams receive a number of forms of support, including stipends, AWS credits, and consultation and mentoring from the Amazon Nova AI Challenge team.
How do I contact Amazon if I have question about the challenge?
If you can't find an answer to your question, please email: amazon-challenge@amazon.com.
Competition details
What is the goal of this year's challenge?
The goal of the 2026 Amazon Nova AI Challenge: Trusted Software Agents track is to make effective AI systems that remain responsible and safe for all, with a focus on the task domain of agentic systems that assist users in the development of full stack web applications. The ultimate goal of the competition is to identify ways for LLM-enabled systems to handle more complex development tasks while anticipating and mitigating safety risks.
What is in scope for this competition?
The Amazon Nova AI Challenge: Trusted Software Agents track is focused on ensuring LLMs supporting AI-assisted software development remain safe, reliable, and trustworthy. For the 2026 Nova AI Challenge, we will focus on web application development as the coding task domain, with verifiable pass/fail conditions as the primary utility measure for a model developer’s system. We will continue with the “tournament-style” format used in 2025, where ten university teams — five model developer (defense) teams and five red (attack) teams compete in a series of interactive tournaments. There is an increased emphasis on advances in utility (ability to handle more complex development tasks) in parallel with safety (avoiding vulnerabilities and risk of exploits as systems handle more complex tasks) this year. Also, red teams will build systems that detect and exploit vulnerabilities in the applications built by model developer teams. 
How is this Trusted Software Agent track different than the Trusted AI track?
The Amazon Nova AI Challenge: Trusted Software Agents track is a natural extension of the Amazon Nova AI Challenge: Trusted AI track. Both focus on ensuring the safety of coding assistants. Trusted Software Agents adds additional emphasis on advances in coding utility and the domain has expanded from simpler code generation to software engineering tasks such as full stack web development. In the Trusted Software Agents track, the red teams will focus on using LLMs to identify potential vulnerabilities and exploits in applications; whereas the Trusted AI track focused on getting LLMs to generate malicious or vulnerable code.
Why should I participate?
There are multiple benefits of participating in the Amazon Nova AI Challenge: Trusted Software Agents track, including:
  1. Dynamic feedback: Teams will get the opportunity to test their systems against best-in-class competitors. Unlike static benchmarks, the challenge evaluations are dynamic and multi-turn and evolve as both sets of teams refine their systems over the course of the competition.
  2. AWS services: Participating teams will receive training, support, and access to the full suite of AWS services, with monthly AWS credits to support the cost of training and execution of their systems.
  3. IP ownership: Teams retain ownership of their work and associated IP, and are encouraged to publish their research after Amazon’s review.
  4. Stipend: Each team chosen for the Amazon Nova AI Challenge: Trusted Software Agents track will receive sponsorship in the amount of $250K. Funding is intended to support roughly two full-time students and one month of faculty time.
  5. Cash prizes: For model developer teams, the top ranked team will receive $250K and the second ranked team will receive $100K. Red teams will also receive $250K for the top ranked team and $100K for the second ranked team. All cash prizes will be divided equally among the students on the team.
When is the finals event?
The finals event will be held in September 2026. This is a closed-door event and participating teams are not invited to the Finals event.
Can we use other funding to help us participate in this challenge?
Yes, you may use other funding to support your team, subject to the terms described in the Challenge Rules. External funding must be disclosed to Amazon.
Can we publish our research from participation in the Amazon Nova AI Challenge: Trusted Software Agents track?
Yes, in fact publishing research papers as an outcome of your work on the Amazon Nova AI Challenge: Trusted Software Agents track is required for all teams participating in the competition, although teams may not publish any Amazon confidential information, as described in the Challenge Rules. The Amazon Nova AI Challenge requires all teams to submit a technical paper to be included in the challenge proceedings. Your team will not be selected for the finals if your team does not submit a technical paper for inclusion in the proceedings. Papers will be published online at the end of the competition and made publicly available through the Amazon Science website. Teams may also publish research papers in third-party publications and conferences, as long as all papers are provided to Amazon for review and approval at least two weeks before the submission deadline.
How will the tournaments be run?
The Amazon Nova AI Challenge: Trusted Software Agents track will consist of a series of interactive tournaments held from early 2026 through summer 2026. Each tournament will consist of two phases: a build phase focused on coding utility performance and a validation phase focused on application security. 

In the build phase, model developers will interact with user simulators to implement new features for an existing web application. Their success will be determined using a suite of end-to-end test cases. In the validation phase, red team systems will have the opportunity to identify and exploit vulnerabilities in the applications created in the build phase. In addition to building their coding assistants, model developers will also be tasked with building simulations of malicious users, and red teams will be tasked with building simulations of benign users. In the build phase, the coding assistants will interact with both the benign user simulators and the malicious user simulators. The red teams will not have the opportunity to find vulnerabilities in the applications resulting from interaction with their own user simulators, and model developer bots will only be matched up with malicious simulators from other defending teams. At the conclusion of each tournament, teams on each side will be ranked with respect to their performance, and the results will be shared with each team.
How will developer teams be ranked in the tournament?
Model developer teams will be ranked based on a combination of their coding utility performance and the security of the resulting applications. Coding utility performance will measure the number of tasks completed successfully across interactions with multiple user simulators (task success rate). Security performance will measure the number of resulting applications in which the red team bots do not find any vulnerabilities or exploits (defense success rate).
How will red teams be ranked in the tournament?
Red teams will be ranked on a combination of their coding utility performance and their effectiveness at identifying and exploiting vulnerabilities in applications (attack success rate). Coding utility performance will measure the number of tasks completed successfully (task success rate) as their user simulator interacts with each of the model developer teams’ coding assistants. This motivates each red team to ensure their user simulator is realistic and effective. Attack success rate for red teams will be a measure of the number of applications from the build phase in which they successfully identify or exploit vulnerabilities. In the build phase, red teams have an indirect motivation to ensure the security of the applications built through interaction with their user simulator as in doing so they preclude the ability of other red teams to score attack success points on those applications.
Eligibility
Who can apply to participate?
The Amazon Nova AI Challenge: Trusted Software Agents track is open to full-time students (undergraduate or graduate) with some exceptions (see Challenge Rules). Proof of enrollment will be required to participate.
Can I participate if I don’t attend a university?
No. The Amazon Nova AI Challenge: Trusted Software Agents track is open only to full-time enrolled university students.
Do I need to be enrolled in a university program throughout my participation in the competition?
All participating team members must remain full-time students in good standing at their university while participating in the competition.
Do I need to be a certain age?
Participants must be at or above the age of majority in the country, state, province, or jurisdiction of residence at the time of entry.
Can I enroll if a family member is an Amazon employee?
Immediate family members and household members of Amazon employees, directors, and contractors are not eligible to participate. See Challenge Rules for additional restrictions.
Teams
How many teams will be selected to participate?
All applications will be reviewed and evaluated by Amazon. Up to ten teams will be selected to compete in a tournament style competition.
How many team members can our team have?
There is no minimum or maximum number of team members. All team members must be enrolled in their university throughout their participation. All teams will receive a $250,000 grant regardless of how many members are on their team.
Can students from different universities be on the same team?
No. Teams must be composed of students attending the same university.
Can one university have more than one team?
Yes, universities may have more than one team. Multiple teams cannot have the same faculty advisor.
Can I participate on two separate teams?
No. You can only be a part of one team for the duration of the competition.
Can undergraduate and graduate students work together?
Yes, teams may be composed of undergraduate and graduate students.
Do I need a faculty advisor?
All teams must nominate a faculty advisor and include the faculty advisor’s consent in the applications.
Can there by more than one faculty advisor in a team?
Yes, there may be up to three faculty advisors per team.
What is the role of the faculty advisor?
Faculty advisors will advise students on technical direction and be a sounding board for new ideas, similar to a graduate school advisor. They will also act as the official representative from the university for this competition.
Can we add or remove team members during the competition?
During the competition, there will be a period of time during which faculty advisors may request to remove or add members to the team, subject to approval by Amazon. See Challenge Rules for details.
Can we discuss our work with faculty or students who aren’t on our team?
Only team members may work on their systems. However, the faculty advisor and other students and faculty members at your university may provide support and advice to your team and may co-author technical publications and research papers.
Application process
How do we apply to participate in the challenge?
Begin the application via YouNoodle, which will be open only during the application period.
What do we need to apply?
Once you have selected your team members, team leader, and faculty sponsor, you are ready to begin the application process. You may apply to both roles and if you do so Amazon will assign one of the two roles to your team.
Do all team members have to apply?
We prefer that the team leader submit an application on behalf of the whole team. In case a team lead has not been chosen, then any member of the team may submit an application. Each team should only submit one application, and it must include all of your team members’  and Faculty advisors’ information.
Is there an application fee?
There is no application fee.
How will teams be selected to participate?
All applications will be reviewed by a panel of experts from Amazon. Teams will be selected based on the following criteria: (1) the technical merit of the approach; (2) the novelty of the ideas; and (3) an assessment of the team’s ability to execute their plan. Please be sure to provide enough detail in your application to enable evaluation of your proposal.
Grants and prizes
Do we get a grant or other support to participate in the Amazon Nova AI Challenge: Trusted Software Agents track?
Up to ten teams will be sponsored to participate in the competition. Each sponsored team’s university will receive a $250,000 research grant to help fund the team’s participation. In addition each participating team will receive AWS credits to support the development of their system, and support from the Amazon Nova AI Challenge team.
How can the grant be spent?
The grant is intended to support two full-time students for the duration of the competition and one month of the faculty advisor’s salary. No more than 35% of the research grant may be allocated to administrative fees. Entrant Teams will be expected to use the stipend towards any uncovered costs associated with bootcamp and or summit (if any). If your team would like to use the funds in another manner, your faculty advisor must receive approval from Amazon before doing so.
What are the prizes for winning the competition?
From the evaluation at the finals event, the two top ranked model developer teams and top two ranked red teams will receive awards. The two teams placed 1st in each role (i.e., red team and developer team) will receive $250,000 each, and the two teams in 2nd place will receive $100,000 each.
US, CA, San Francisco
The Artificial General Intelligence (AGI) team is looking for a passionate, talented, and inventive Member of Technical Staff with a strong deep learning background, to build industry-leading Generative Artificial Intelligence (GenAI) technology with Large Language Models (LLMs) and multimodal systems. Key job responsibilities As a Member of Technical Staff with the AGI team, you will lead the development of algorithms and modeling techniques, to advance the state of the art with LLMs. You will lead the foundational model development in an applied research role, including model training, dataset design, and pre- and post-training optimization. Your work will directly impact our customers in the form of products and services that make use of GenAI technology. You will leverage Amazon’s heterogeneous data sources and large-scale computing resources to accelerate advances in LLMs. About the team The AGI team has a mission to push the envelope in GenAI with LLMs and multimodal systems, in order to provide the best-possible experience for our customers.
US, CA, San Francisco
The Artificial General Intelligence (AGI) team is looking for a passionate, talented, and inventive Member of Technical Staff with a strong deep learning background, to build industry-leading Generative Artificial Intelligence (GenAI) technology with Large Language Models (LLMs) and multimodal systems. Key job responsibilities As a Member of Technical Staff with the AGI team, you will lead the development of algorithms and modeling techniques, to advance the state of the art with LLMs. You will lead the foundational model development in an applied research role, including model training, dataset design, and pre- and post-training optimization. Your work will directly impact our customers in the form of products and services that make use of GenAI technology. You will leverage Amazon’s heterogeneous data sources and large-scale computing resources to accelerate advances in LLMs. About the team The AGI team has a mission to push the envelope in GenAI with LLMs and multimodal systems, in order to provide the best-possible experience for our customers.
US, CA, San Francisco
The Artificial General Intelligence (AGI) team is looking for a passionate, talented, and inventive Member of Technical Staff with a strong deep learning background, to build industry-leading Generative Artificial Intelligence (GenAI) technology with Large Language Models (LLMs) and multimodal systems. Key job responsibilities As a Member of Technical Staff with the AGI team, you will lead the development of algorithms and modeling techniques, to advance the state of the art with LLMs. You will lead the foundational model development in an applied research role, including model training, dataset design, and pre- and post-training optimization. Your work will directly impact our customers in the form of products and services that make use of GenAI technology. You will leverage Amazon’s heterogeneous data sources and large-scale computing resources to accelerate advances in LLMs. About the team The AGI team has a mission to push the envelope in GenAI with LLMs and multimodal systems, in order to provide the best-possible experience for our customers.
US, CA, San Francisco
The Artificial General Intelligence (AGI) team is looking for a passionate, talented, and inventive Member of Technical Staff with a strong deep learning background, to build industry-leading Generative Artificial Intelligence (GenAI) technology with Large Language Models (LLMs) and multimodal systems. Key job responsibilities As a Member of Technical Staff with the AGI team, you will lead the development of algorithms and modeling techniques, to advance the state of the art with LLMs. You will lead the foundational model development in an applied research role, including model training, dataset design, and pre- and post-training optimization. Your work will directly impact our customers in the form of products and services that make use of GenAI technology. You will leverage Amazon’s heterogeneous data sources and large-scale computing resources to accelerate advances in LLMs. About the team The AGI team has a mission to push the envelope in GenAI with LLMs and multimodal systems, in order to provide the best-possible experience for our customers.
US, CA, San Francisco
The Artificial General Intelligence (AGI) team is looking for a passionate, talented, and inventive Member of Technical Staff with a strong deep learning background, to build industry-leading Generative Artificial Intelligence (GenAI) technology with Large Language Models (LLMs) and multimodal systems. Key job responsibilities As a Member of Technical Staff with the AGI team, you will lead the development of algorithms and modeling techniques, to advance the state of the art with LLMs. You will lead the foundational model development in an applied research role, including model training, dataset design, and pre- and post-training optimization. Your work will directly impact our customers in the form of products and services that make use of GenAI technology. You will leverage Amazon’s heterogeneous data sources and large-scale computing resources to accelerate advances in LLMs. About the team The AGI team has a mission to push the envelope in GenAI with LLMs and multimodal systems, in order to provide the best-possible experience for our customers.
US, CA, Sunnyvale
Prime Video is a first-stop entertainment destination offering customers a vast collection of premium programming in one app available across thousands of devices. Prime members can customize their viewing experience and find their favorite movies, series, documentaries, and live sports – including Amazon MGM Studios-produced series and movies; licensed fan favorites; and programming from Prime Video add-on subscriptions such as Apple TV+, Max, Crunchyroll and MGM+. All customers, regardless of whether they have a Prime membership or not, can rent or buy titles via the Prime Video Store, and can enjoy even more content for free with ads. Are you interested in shaping the future of entertainment? Prime Video's technology teams are creating best-in-class digital video experience. As a Prime Video technologist, you’ll have end-to-end ownership of the product, user experience, design, and technology required to deliver state-of-the-art experiences for our customers. You’ll get to work on projects that are fast-paced, challenging, and varied. You’ll also be able to experiment with new possibilities, take risks, and collaborate with remarkable people. We’ll look for you to bring your diverse perspectives, ideas, and skill-sets to make Prime Video even better for our customers. With global opportunities for talented technologists, you can decide where a career Prime Video Tech takes you! We are looking for a self-motivated, passionate and resourceful Sr. Applied Scientists with Recommender System or Search Ranking or Ads Ranking experience to bring diverse perspectives, ideas, and skill-sets to make Prime Video even better for our customers. You will spend your time as a hands-on machine learning practitioner and a research leader. You will play a key role on the team, building and guiding machine learning models from the ground up. At the end of the day, you will have the reward of seeing your contributions benefit millions of Amazon.com customers worldwide. Key job responsibilities - Develop AI solutions for various Prime Video Recommendation/Search systems using Deep learning, GenAI, Reinforcement Learning, and optimization methods; - Work closely with engineers and product managers to design, implement and launch AI solutions end-to-end; - Design and conduct offline and online (A/B) experiments to evaluate proposed solutions based on in-depth data analyses; - Effectively communicate technical and non-technical ideas with teammates and stakeholders; - Stay up-to-date with advancements and the latest modeling techniques in the field; - Publish your research findings in top conferences and journals. About the team Prime Video Recommendation/Search Science team owns science solution to power search experience on various devices, from sourcing, relevance, ranking, to name a few. We work closely with the engineering teams to launch our solutions in production.
US, WA, Seattle
Amazon's Price Perception and Evaluation team is seeking a driven Principal Applied Scientist to harness planet scale multi-modal datasets, and navigate a continuously evolving competitor landscape, in order to build and scale an advanced self-learning scientific price estimation and product understanding system, regularly generating fresh customer-relevant prices on billions of Amazon and Third Party Seller products worldwide. We are looking for a talented, organized, and customer-focused technical leader with a charter to derive deep neural product relationships, quantify substitution and complementarity effects, and publish trust-preserving probabilistic price ranges on all products listed on Amazon. This role requires an individual with excellent scientific modeling and system design skills, bar-raising business acumen, and an entrepreneurial spirit. We are looking for an experienced leader who is a self-starter comfortable with ambiguity, demonstrates strong attention to detail, and has the ability to work in a fast-paced and ever-changing environment. Key job responsibilities - Develop the team. Mentor a highly talented group of applied machine learning scientists & researchers. - See the big picture. Shape long term vision for Amazon's science-based competitive, perception-preserving pricing techniques - Build strong collaborations. Partner with product, engineering, and science teams within Pricing & Promotions to deploy machine learning price estimation and error correction solutions at Amazon scale - Stay informed. Establish mechanisms to stay up to date on latest scientific advancements in machine learning, neural networks, natural language processing, probabilistic forecasting, and multi-objective optimization techniques. Identify opportunities to apply them to relevant Pricing & Promotions business problems - Keep innovating for our customers. Foster an environment that promotes rapid experimentation, continuous learning, and incremental value delivery. - Deliver Impact. Develop, Deploy, and Scale Amazon's next generation foundational price estimation and understanding system
US, WA, Seattle
Here at Amazon, we embrace our differences. We are committed to furthering our culture of diversity and inclusion of our teams within the organization. How do you get items to customers quickly, cost-effectively, and—most importantly—safely, in less than an hour? And how do you do it in a way that can scale? Our teams of hundreds of scientists, engineers, aerospace professionals, and futurists have been working hard to do just that! We are delivering to customers, and are excited for what’s to come. Check out more information about Prime Air on the About Amazon blog (https://www.aboutamazon.com/news/transportation/amazon-prime-air-delivery-drone-reveal-photos). If you are seeking an iterative environment where you can drive innovation, apply state-of-the-art technologies to solve real world delivery challenges, and provide benefits to customers, Prime Air is the place for you. Come work on the Amazon Prime Air Team! We are seeking a highly skilled Navigation Scientist to help develop advanced algorithms and software for our Prime Air delivery drone program. In this role, you will conduct comprehensive navigation analysis to support cross-functional decision-making, define system architecture and requirements, contribute to the development of flight algorithms, and actively identify innovative technological opportunities that will drive significant enhancements to meet our customers' evolving demands. Export Control License: This position may require a deemed export control license for compliance with applicable laws and regulations. Placement is contingent on Amazon’s ability to apply for and obtain an export control license on your behalf.
IN, KA, Bengaluru
Alexa+ is Amazon’s next-generation, AI-powered virtual assistant. Building on the original Alexa, it uses generative AI to deliver a more conversational, personalized, and effective experience. As an Applied Scientist II on the Alexa Sensitive Content Intelligence (ASCI) team, you'll be part of an elite group developing industry-leading technologies in attribute extraction and sensitive content detection that work seamlessly across all languages and countries. In this role, you'll join a team of exceptional scientists pushing the boundaries of Natural Language Processing. Working in our dynamic, fast-paced environment, you'll develop novel algorithms and modeling techniques that advance the state of the art in NLP. Your innovations will directly shape how millions of customers interact with Amazon Echo, Echo Dot, Echo Show, and Fire TV devices every day. What makes this role exciting is the unique blend of scientific innovation and real-world impact. You'll be at the intersection of theoretical research and practical application, working alongside talented engineers and product managers to transform breakthrough ideas into customer-facing experiences. Your work will be crucial in ensuring Alexa remains at the forefront of AI technology while maintaining the highest standards of trust and safety. We're looking for a passionate innovator who combines strong technical expertise with creative problem-solving skills. Your deep understanding of NLP models (including LSTM and transformer-based architectures) will be essential in tackling complex challenges and identifying novel solutions. You'll leverage your exceptional technical knowledge, strong Computer Science fundamentals, and experience with large-scale distributed systems to create reliable, scalable, and high-performance products that delight our customers. Key job responsibilities In this dynamic role, you'll design and implement GenAI solutions that define the future of AI interaction. You'll pioneer novel algorithms, conduct ground breaking experiments, and optimize user experiences through innovative approaches to sensitive content detection and mitigation. Working alongside exceptional engineers and scientists, you'll transform theoretical breakthroughs into practical, scalable solutions that strengthen user trust in Alexa globally. You'll also have the opportunity to mentor rising talent, contributing to Amazon's culture of scientific excellence while helping build high-performing teams that deliver swift, impactful results. A day in the life Imagine starting your day collaborating with brilliant minds on advancing state-of-the-art NLP algorithms, then moving on to analyze experiment results that could reshape how Alexa understands and responds to users. You'll partner with cross-functional teams - from engineers to product managers - to ensure data quality, refine policies, and enhance model performance. Your expertise will guide technical discussions, shape roadmaps, and influence key platform features that require cross-team leadership. About the team The mission of the Alexa Sensitive Content Intelligence (ASCI) team is to (1) minimize negative surprises to customers caused by sensitive content, (2) detect and prevent potential brand-damaging interactions, and (3) build customer trust through appropriate interactions on sensitive topics. The term “sensitive content” includes within its scope a wide range of categories of content such as offensive content (e.g., hate speech, racist speech), profanity, content that is suitable only for certain age groups, politically polarizing content, and religiously polarizing content. The term “content” refers to any material that is exposed to customers by Alexa (including both 1P and 3P experiences) and includes text, speech, audio, and video.
IN, KA, Bengaluru
Alexa+ is Amazon’s next-generation, AI-powered virtual assistant. Building on the original Alexa, it uses generative AI to deliver a more conversational, personalized, and effective experience. As an Applied Scientist II on the Alexa Sensitive Content Intelligence (ASCI) team, you'll be part of an elite group developing industry-leading technologies in attribute extraction and sensitive content detection that work seamlessly across all languages and countries. In this role, you'll join a team of exceptional scientists pushing the boundaries of Natural Language Processing. Working in our dynamic, fast-paced environment, you'll develop novel algorithms and modeling techniques that advance the state of the art in NLP. Your innovations will directly shape how millions of customers interact with Amazon Echo, Echo Dot, Echo Show, and Fire TV devices every day. What makes this role exciting is the unique blend of scientific innovation and real-world impact. You'll be at the intersection of theoretical research and practical application, working alongside talented engineers and product managers to transform breakthrough ideas into customer-facing experiences. Your work will be crucial in ensuring Alexa remains at the forefront of AI technology while maintaining the highest standards of trust and safety. We're looking for a passionate innovator who combines strong technical expertise with creative problem-solving skills. Your deep understanding of NLP models (including LSTM and transformer-based architectures) will be essential in tackling complex challenges and identifying novel solutions. You'll leverage your exceptional technical knowledge, strong Computer Science fundamentals, and experience with large-scale distributed systems to create reliable, scalable, and high-performance products that delight our customers. Key job responsibilities In this dynamic role, you'll design and implement GenAI solutions that define the future of AI interaction. You'll pioneer novel algorithms, conduct ground breaking experiments, and optimize user experiences through innovative approaches to sensitive content detection and mitigation. Working alongside exceptional engineers and scientists, you'll transform theoretical breakthroughs into practical, scalable solutions that strengthen user trust in Alexa globally. You'll also have the opportunity to mentor rising talent, contributing to Amazon's culture of scientific excellence while helping build high-performing teams that deliver swift, impactful results. A day in the life Imagine starting your day collaborating with brilliant minds on advancing state-of-the-art NLP algorithms, then moving on to analyze experiment results that could reshape how Alexa understands and responds to users. You'll partner with cross-functional teams - from engineers to product managers - to ensure data quality, refine policies, and enhance model performance. Your expertise will guide technical discussions, shape roadmaps, and influence key platform features that require cross-team leadership. About the team The mission of the Alexa Sensitive Content Intelligence (ASCI) team is to (1) minimize negative surprises to customers caused by sensitive content, (2) detect and prevent potential brand-damaging interactions, and (3) build customer trust through appropriate interactions on sensitive topics. The term “sensitive content” includes within its scope a wide range of categories of content such as offensive content (e.g., hate speech, racist speech), profanity, content that is suitable only for certain age groups, politically polarizing content, and religiously polarizing content. The term “content” refers to any material that is exposed to customers by Alexa (including both 1P and 3P experiences) and includes text, speech, audio, and video.