Quality Sense Conf 2026: Global Debates on Software Quality and AI

Quality Sense Conf 2026 made one thing very clear. The paradigm shift AI is bringing to industries and society is still underway, and we’re right in the middle of that transition.

This is a time for debate, definition, and direction. Just as many technologies that are now an intrinsic part of our lives met resistance and serious skepticism when they first appeared, it’s now artificial intelligence’s turn.

The big dilemmas AI raises today were the common thread running through Quality Sense Conf 2026, and they lie at the heart of the technological transformation we’re experiencing across every field of knowledge.

If AI lets us produce software faster and faster, how can we understand its risks and make confident decisions about its quality?

This question shaped the conversations throughout the conference, from software development and testing to leadership, business models, and our human accountability for the decisions we make with AI.

Organized by Abstracta under the theme “Building Trust in the Age of AI,” the fifth edition took place on October 13, 2026, at the Radisson Hotel in Montevideo, Uruguay. It drew nearly 450 in-person attendees and more than 30 speakers from around the world, along with a livestream featuring simultaneous interpretation in English, Portuguese, and Spanish. The sense of community was felt everywhere, from social media to every corner of the venue.

▶Play

Announcement: Quality Intelligence, the Manifesto¶

We Produce Software Faster Than We Can Understand It. It’s Time to Change That.¶

One of the most meaningful moments at Quality Sense Conf 2026 was the presentation of the first version of the Quality Intelligence Manifesto, an initiative led by Abstracta that rethinks how we understand, evaluate, and manage software quality in the age of artificial intelligence.

During the opening keynote, Sofía Palamarchuk and Matías Reina, Co-CEOs of Abstracta, shared a vision rooted in an increasingly clear challenge. AI is speeding up how fast we generate code, tests, and changes, but our ability to understand their implications and assess their risks isn’t keeping pace.

In response, Quality Intelligence introduces a new framework that expands Quality Engineering across the SDLC and connects systems, context, and human judgment to understand the risk of every change and make decisions with greater confidence.

The proposal is built on six principles:

1. Understanding the risk of each change over expanding coverage.
2. Deciding with evidence over trusting green indicators.
3. Sharing context with people and agents over concentrating knowledge in a few.
4. Learning from causes over treating symptoms.
5. Using AI to understand over using AI to produce more.
6. Being accountable for outcomes over being accountable for activity.

The announcement also reached an international audience through PR Newswire, with a release that takes a deeper look at the challenges of applying Quality Intelligence to critical systems.

A Manifesto Open to the Global Community¶

The presentation marked the start of a collective effort. The manifesto launched as version 0.9, with an open invitation to professionals, teams, and organizations around the world to question, enrich, and expand its principles.

The seventh statement is intentionally left open for new perspectives. Anyone can sign the manifesto, join the conversations on GitHub, and contribute to version 1.0, scheduled for November 2026.

Testimonials in Their Own Words¶

Quality Sense Conf 2026 left behind lessons, reflections, and conversations that continued well beyond the talks. Speakers, industry leaders, and attendees shared their experiences and the ideas they’re taking away from this edition. In this section, we share some of their voices.

Brijesh Deb, Principal Consultant at Infosys and Chief Enablement Officer & Co-founder of The Test Chat

“What a fantastic experience at Quality Sense Conference in Montevideo, Uruguay!

I have just finished delivering my keynote, and what an experience it has been!

There is so much about this conference that deserves appreciation, starting with the organization. What particularly impressed me was the effort to make the conference accessible to a wider audience.

The speaker lineup has been fantastic, bringing together different experiences, ideas, and perspectives on testing and quality. But what I have enjoyed just as much are the conversations outside the sessions.

I have met some wonderful people here. It was also incredibly encouraging to see how much my keynote resonated with the audience.

My keynote may have brought me to Montevideo, but the people and conversations have made this visit memorable.

I am taking home some great memories, new connections, and plenty to think about!”

José Antonio Guerrero, Software Engineering Manager at BBVA

“My heart is full after today at #QualitySenseConf. Sharing time face to face with colleagues and industry leaders who are committed to strengthening and caring for our community is an absolute privilege. Here are a few ideas I’m taking away from the management track:

• With implementations moving this fast, let’s put our focus and energy on the sources of truth (they’re scarce).
• Let’s not look at technological change through the rearview mirror (or without emotional intelligence).
• Leading is still effective when it’s about asking better questions, not about knowing everything.
• Watch out for “Forward Deployment Engineering.”

Thank you for so much, and happy 18th anniversary, Abstracta!”

Aníbal Gonda, VP of Talent at CUTI and Head of Partnerships at GeneXus

“Today I had a déjà vu. I walked into Quality Sense Conf 2026 and, for a moment, I was back at the GeneXus events. High-caliber talks, the kind of networking that leaves conversations open, and a team that makes something hard look easy. And on top of that, in the very same room.

This year’s theme was “Building Trust in the Age of AI,” and that’s no small topic. Trust is what separates an organization that experiments with AI from one that’s ready to put it into production.

Organizing something like this isn’t logistics, it’s judgment. You have to choose content that’s worth people’s time, make sure the conversation happens in the hallways as much as on stage, and uphold a standard the community recognizes the moment it walks through the door.

Some standards outlive the people who created them. Seeing them thrive in another house, with an identity of their own, is one of the best things that can happen to an ecosystem.”

Shane Evans, Director of Products at Perforce

“My main takeaway from #QualitySenseConf so far is this: AI is a tool, but we, the people working in QA, are the ones who manage the work it does.

We’re the ones who bring the context, define the intent, and understand the risks of not delivering the expected outcomes. That’s why we’re the ones who need to decide how to use that tool.

Testing isn’t dead. Today, it’s more important than ever.”

These perspectives reflect part of what we aim to foster with every edition of Quality Sense Conf: a community that shares knowledge, questions its own practices, and builds new perspectives on the future of software quality.

A Recap of Every Talk at the Event¶

Quality Sense Conf 2026 brought together 29 sessions throughout October 13. The day kicked off in the main room with two opening keynotes. After that, the program split into parallel spaces: the General Track and the Testing Track, with five talks each, and the Management Track, with four talks and a panel for Executive Pass holders. There was also the Demo Corner, with ten 20-minute demos.

Thanks to this variety, each attendee could build their own path based on their interests and role. Toward the end of the afternoon, the whole audience came back together in the main room for the two closing keynotes, followed by the event’s closing and the giveaways celebrating Abstracta’s 18th anniversary.

General Talks - General Track¶

From QA to Quality Intelligence: The Future of Quality, With People at the Center¶

Speakers: Sofía Palamarchuk, Co-CEO of Abstracta, and Matías Reina, Co-CEO and Co-founder of Abstracta.

The opening keynote presented Abstracta’s vision for Quality Intelligence, an approach that brings together artificial intelligence, knowledge, technology, and human judgment to understand software risks and make informed decisions about quality. The talk explored how to evolve from traditional QA approaches toward quality management grounded in intelligence and evidence.

Narratives, Not Needs: How Testing Got Hijacked¶

Speaker: Brijesh Deb, Principal Consultant at Infosys and Chief Enablement Officer & Co-founder of The Test Chat.

A critical look at the narratives that have shaped the testing industry, and at how certain trends, tools, and approaches can pull attention away from what teams and products really need. The talk invited the audience to reclaim critical thinking and the purpose behind quality practices.

Tero Doesn’t Go It Alone: Adoption Stories With Abstracta Intelligence¶

Speakers: Roger Abelenda, CTO of Abstracta, and Anyeelen Cuayatto, QA Engineer at Abstracta.

A talk on real experiences adopting AI agents for software testing and quality, and on the role of Abstracta Intelligence in supporting their implementation. It covered the challenges of integrating these capabilities into existing processes and tools, with a focus on how teams adopt them and how they shape day-to-day work.

The Future of Testing With AI¶

Speaker: Shane Evans, Director of Products at Perforce.

A look at how testing is evolving as artificial intelligence advances. The talk covered how tools, practices, and responsibilities are shifting for quality teams, and which capabilities will matter most for validating software as development keeps speeding up.

Caring for the Present, Shaping the Future: The Role of Junior Talent in High-Performing Teams¶

Speaker: Katia Peña, Development Director at Electronic Arts (EA).

A reflection on the role junior talent plays in building high-performing teams. The talk focused on mentoring, learning, and professional growth opportunities as part of how technology teams evolve.

From the Workshop to the Playing Field: How We Adopted AI in QA Through Leadership and Execution¶

Speakers: Sabitha Nair, Quality Assurance Manager at Alpine, an ITW company, and Isaac Rodríguez, Functional Tester at Abstracta.

A hands-on story of AI adoption in QA that connected leadership decisions with how teams put them into practice. The talk shared challenges, lessons learned, and the organizational side of bringing AI into real quality processes.

Agentic Performance Automation and Verification¶

Speaker: Mark Tomlinson, Chief Performacologist at Performacology and performance and observability specialist.

A talk on using artificial intelligence and agentic approaches to automate and validate performance tests. It explored how new AI capabilities can be applied to performance analysis and to evaluating how systems behave.

Becoming “Builders”¶

Speaker: Andrew Knight, Director of Product & Engineering at Cycle Labs.

This keynote explored how artificial intelligence is transforming the way software gets built and the role of the people involved in building it. It invited the audience to reflect on new ways of creating digital products and on how technical roles are evolving now that generating code is more accessible than ever.

Engineering Trust: Testing’s New Deliverable¶

Speaker: Federico Toledo, Co-founder and Chief Quality Officer of Abstracta.

The closing keynote explored how the purpose of testing is evolving in the age of artificial intelligence. With software being generated faster than ever, it made the case for building trust through evidence, a clear understanding of risk, and human judgment, as part of the value quality teams bring.

Specialized Talks - Testing Track¶

Agent Assurance: When AI Speaks for Your Brand, Who Tests the Agent?¶

Speaker: Javier Bastante, Senior Director, Partnerships & Alliances at TestMu AI.

A talk on the challenges of validating AI agents that interact with users and represent organizations. It addressed the need to evaluate their behavior, reliability, and responses, given the risks that come up when AI takes a direct part in customer experiences and business processes.

Govern Before You Automate¶

Speakers: Gonzalo Botero Sierra, AI Technical Specialist at Devco, and Karen Cogollo Segura, Operations and Services Lead at Devco.

A talk on why it matters to set governance criteria before scaling AI-driven automation. It focused on the control, accountability, and decisions needed to bring AI into technology processes.

The QA Method for Teams Building With AI¶

Speaker: Henrique Manieri Claro, Co-founder of Lumestack and QA Engineer Specialist Consultant at Limestone Digital.

A proposal for adapting Quality Assurance practices to teams that use artificial intelligence to build software. The talk explored how to structure validation activities and keep a critical eye on AI-generated output.

AI Harness for Testing: From Generating BDD Specifications to Maintainable E2E Test Automation¶

Speaker: Beatriz Pérez, QA Manager at LKS NEXT.

A technical talk on using an AI harness to connect the generation of behavior-driven development (BDD) specifications with end-to-end test automation. It covered how AI can support test creation and the challenges of maintaining those tests over time.

Accessible Frontends in the Age of AI¶

Speaker: Eva Ferreira, Lead Software Engineer at mabl.

A talk on web accessibility and frontend development in the context of artificial intelligence. It covered the challenges of building inclusive digital experiences and the role of technology and human validation in identifying and preventing accessibility barriers.

Leadership and Business - Management Track¶

How Tech Companies’ Business Models Are Evolving in the Age of AI¶

Speaker: Marcel Mordezki, Professor of Technology Management and Innovation at Universidad ORT Uruguay, Executive Board Member at Synapsis | Tech BPO, Executive Board Member at Hinweiss, and Managing Director at Mordezki & Asociados.

A talk on the changes artificial intelligence is bringing to the business models of technology companies. It covered new ways of creating, delivering, and capturing value, the economic dilemmas across the industry, and the strategic decisions organizations need to make in response.

Moving From Problems to Solutions (With AI!)¶

Speakers: Fabián Baptista, CIO and Co-founder of Abstracta, and Matías Reina, Co-CEO and Co-founder of Abstracta.

A session focused on connecting real business problems with opportunities to apply artificial intelligence. It covered how to identify needs, think through viable solutions, and use new technology capabilities to respond to organizational challenges.

Minds That Lead Change: The Real ROI in the Age of AI¶

Speaker: Chiara Toscani, Founder of Magha Studio.

A reflection on leadership, organizational transformation, and return on investment in the age of artificial intelligence. The talk covered the role of people, capabilities, and organizational culture in creating value from new technologies.

Habits for Scaling Effectively in 2026¶

Speaker: Matías Salom, Co-founder and CEO of Superhábitos.

A talk on habits, productivity, and organizational growth. It covered how to build sustainable practices for work, prioritization, and leadership that support company growth amid technological transformation.

Leading Without Certainty: Philosophy for the Age of AI¶

Participants: Javier Mazza, Director of the Department of Humanities and Communication at Universidad Católica del Uruguay and philosopher, and Vera Babat, Chief Culture Officer of Abstracta and Co-founder of Tandem.

A conversation about the challenges of leadership in a landscape shaped by uncertainty and technological change. From a philosophical and organizational perspective, the panel invited the audience to reflect on judgment, accountability, and decision-making in the age of artificial intelligence.

Technical Demos - Demo Corner¶

The Demo Corner featured 20-minute demos showcasing tools, platforms, and practical applications of artificial intelligence in software testing and quality.

Neo: Portable QA Agents: Skills, Playbooks, and Assisted Orchestration (M1 + M3)¶

Speaker: Javier Re, CEO of Crowdar and Founder of Lippia.io.

A demo of Neo focused on portable QA agents, reusable skills, playbook definition, and assisted orchestration mechanisms for automating quality tasks.

Harness Engineering: From Context Drift to Determinism¶

Speaker: Carlos Gauto, Project Leader at Mercado Libre.

A demo on harness engineering and the challenges of controlling context in systems built on AI agents. It focused on techniques for reducing variability and encouraging more predictable behavior.

TestCraft: Community-Driven Evals, From Users to Contributors¶

Speaker: Damián Pereira, Head of Testing at Endava.

A demo centered on TestCraft and collaborative AI evaluations, focused on how community participation can help build and improve evaluation mechanisms.

JMeter DSL: Your JMeter Performance Tests From Your Favorite IDE¶

Speakers: Faustino Delpoggio, Performance Engineer at Abstracta, and Sebastián Lorenzo, Lead Quality Engineer at Abstracta.

A technical demo of JMeter DSL, which lets teams define and run performance tests as code from a development environment, making them easier to integrate into software engineering workflows.

AI in QA: Fast, Yes. Without Control? No.¶

Speakers: Gonzalo Botero Sierra, AI Technical Specialist at Devco, and Karen Cogollo Segura, Operations and Services Lead at Devco.

A demo on using artificial intelligence for QA tasks, with an emphasis on combining speed with governance, validation, and control over results.

Dale IA: An Agent to Support AI Adoption in Your Team¶

Speaker: Mercedes Remedi, Co-founder of Tandem and Learninc.

A presentation of Dale IA, an agent designed to support AI adoption across teams, with a focus on making it easier to bring AI into everyday work.

Tero 101: Open-Source Platform for Managing AI Testing Agents¶

Speakers: Lucas del Reguero, Software Tester at Abstracta, and Santiago Duarte, Software Engineer at Abstracta.

A hands-on introduction to Tero, the open-source agent harness for managing AI agents applied to testing. The demo covered its main capabilities and potential uses.

Tero: Agents That Help Testers Analyze Requirements¶

Speaker: Matías Fornara, Quality Manager at Abstracta.

A demo of Tero agents used to support requirements analysis, making requirements easier to understand and surfacing information relevant to testing activities.

Tero: How to Integrate Tero Agents From Cursor or Claude¶

Speaker: Matías Fornara, Quality Manager at Abstracta.

A demo on integrating Tero agents with AI-assisted development tools such as Cursor and Claude, to bring testing capabilities into existing workflows.

Neo: From Playbooks to Plans: Deterministic Orchestration of QA Agents in CI/CD (M2 + M4)¶

Speaker: Javier Re, CEO of Crowdar and Founder of Lippia.io.

A demo on deterministic orchestration of QA agents with Neo, focused on how to turn playbooks into executable plans and integrate these capabilities into continuous integration and delivery pipelines.

Thank You to Our Sponsors¶

Quality Sense Conf 2026 was made possible by the organizations that chose to support this edition and champion an open conversation about software quality and artificial intelligence in Latin America.

Their commitment to the community allowed us to keep general admission free, bring in speakers from around the world, and offer an accessible experience, with a livestream and simultaneous interpretation.

Abstracta Academy¶

Abstracta Academy is Abstracta’s learning platform. It offers role-based learning paths in AI, testing, and software quality for technology teams, with hands-on practice in Tero and guidance from experienced specialists.

Tandem¶

Tandem helps companies adopt artificial intelligence with measurable impact. It combines change management, metrics from day one, and tailored solutions so AI becomes a real part of how teams work.

mabl¶

mabl is an agentic testing platform that independently verifies applications before every release. It helps development teams create, run, and maintain tests across web, mobile, and APIs, keeping pace with AI-driven development.

Seguro Americano¶

Seguro Americano is a private Uruguayan healthcare provider with 60 years of history. It provides medical care to its members across the country through the FEPREMI network and runs Sanatorio Americano, with a focus on high-quality care and a more human approach to medicine.

Crowdar¶

Crowdar is an Argentine company specializing in software testing, CloudOps, and AI solutions. It developed Lippia, a suite of tools for test automation and management, and Neo, its AI agents built into the testing lifecycle.

Electronic Arts (EA)¶

Electronic Arts is one of the largest video game and interactive entertainment companies in the world. It develops and publishes titles for consoles, PCs, and mobile devices that reach millions of people.

Devco¶

Devco is an AI-first company headquartered in Medellín, Colombia, that operates across Latin America. It designs AI solutions, intelligent agents, AI-powered QA, DevSecOps, and cloud architecture to transform how companies operate.

TestMu AI¶

TestMu AI (formerly LambdaTest) is a cloud-based agentic testing platform. It lets teams plan, create, run, and analyze tests across web, mobile, and AI applications, including chat and voice agents.

Learninc¶

Learninc is a company dedicated to corporate learning. It designs training experiences that fit into teams’ everyday work, with a focus on turning what people learn into action within their organizations.

PIA¶

PIA is a Uruguayan startup that applies artificial intelligence to hiring. Its platform conducts AI-powered interviews via video, voice, or WhatsApp and assesses technical, cognitive, and personality skills so HR teams can make decisions backed by more evidence.

Big Cheese¶

Big Cheese is a Uruguayan company specializing in cloud solutions and DevOps culture. It was Uruguay’s first AWS Premier Partner and supports companies across industries in optimizing their operations.

7FT¶

7FT is a boutique engineering and QA company with a presence in Argentina and Uruguay. It specializes in the quality of AI models and agents, and its team brings decades of experience in video games and other industries.

Thank you to each of these organizations for believing in the value of building community and for being part of an edition that put trust at the center of the conversation about AI and software quality. Their support helps this space keep growing year after year.

Thank You to Our Media Partners¶

We also want to thank our media partners for joining us for this edition of Quality Sense Conf and helping conversations about artificial intelligence, software quality, and technology innovation reach new audiences.

Their support helped us expand the conference’s reach, connect communities, and keep fostering the exchange of knowledge and experiences across the tech industry.

• Testing UY
• Abstracta Tech Talks
• Cuti
• IT Builders
• Crónicas
• Ágiles Uruguay
• Software Testing Conferences
• OWU
• Testing Channel
• Mujeres Testing Latam
• Ánima
• Builders Off the Record
• QA Makers

Looking Ahead: We Build the Future of Quality as a Community¶

Quality Sense Conf 2026 has come to a close, but the conversations it sparked are more relevant than ever. Throughout the day, industry leaders from around the world shared their experiences, challenged assumptions, and debated the challenges artificial intelligence poses for software development, organizations, and people.

This fifth edition reaffirmed the value of creating spaces where the industry can come together, exchange perspectives, and think collectively about where we want to go.

At Abstracta, we’ll keep driving these conversations through new initiatives, events, and spaces for collaboration. The launch of the Quality Intelligence Manifesto is also an invitation for the global community to take an active part in the evolution of our discipline.

Thank you to everyone who took part, shared their knowledge, and helped make this edition possible.

We’re leaving with new questions, lessons, and connections that will keep shaping what comes next. Because the future of software quality is built by everyone who is part of this community.

See you at Quality Sense Conf 2027!