Increase personal AI coverage

We testers love coverage. In this talk, the two kinds of coverage we focus on are experiences and interactions, because those are the foundational skills in addition to 'asking for it'.

Transcript

1. Increase personal AI coverage AI Native journey Maaret Pyhäjärvi November 2026 © 2026 CGI Inc. 1
2. LESSON 1 ON COVERAGE 100% is not the goal © 2026 CGI Inc. 2
3. FULLY AUTO MATED, DEEPLY HUMAN People can now do things by asking for it. © 2026 CGI Inc. 3
4. ASKING FOR IT Use playwright-cli to operate website https://www.workroomproductions.com/raster-reveal/ and create a script that systematically reveals the image that gets more accurate by mouse movement. Take regular screenshots and figure out for each if you know what is in the picture. Keep the browser open so that I can watch it unfold. © 2026 CGI Inc. 4
5. ABOUT TESTING Stopping criteria when automation is more accessible Test design Test cases 0:00 Test execution 0:46 animal-like shape ManualAis dark emerging on a light Confirmed: it's a quadtree that reveals finer detail in blocks my cursor actually crosses. Let me sweep the remaining bands top-tobottom. background, with Managing orange/gold accents. 3:12 Exploratory 13:26 That's unmistakably a black rubber duck with an orange beak and a gold Batman bat-symbol on its side/wing — a "Batman rubber duck" bath toy. Final identification Automated stands: a black rubber duck with an orange Doing beak and a gold Batman logo on its side. Avoid co nfidentl y incorr ect judg ement © 2026 CGI Inc. 5
6. LESSON 1 ON COVERAGE 100% is not the goal © 2026 CGI Inc. 6
7. LESSON 2 ON COVERAGE Experiences coverage is foundation for innovation © 2026 CGI Inc. 7
8. AI-native journey: individual experiences by role 30 experiences people grow into. Knowledge workers track 12; developers track those plus 18 more. Knowledge worker role 01 02 12 experiences External imagination Developer role 01 Code autocomplete 10 Team/Product context 02 Reactive agentic 11 Team/Product context advanced 03 Selecting and configuring 3rd party MCPs 12 Building own MCPs 04 Integrating 3rd party AI system components 13 Delivering AI native project 05 Skills and AI-friendly git-first templates 14 Product AI feature delivery for proof of concept Local summarizing 03 Online summarizing 04 Integrated AI features in domain tools 05 AI-enabled practices 18 experiences you start it e.g. .md files e.g. MCPs, memory, skills, orchestration e.g. Rovo for Confluence & Jira e.g. AI notetaking memory, context compression 06 Task expansion 07 Personal applications 08 2nd brain 06 Using local models 15 Added business value in domain AI proof of concept 09 Token awareness 07 Proactive agentic 16 Product AI feature delivery to run in production 08 Dark factory 17 Product feature AI feedback 09 Spec-driven development 18 Sandboxing 10 Generating artifacts 11 Pitch to project for AI usecase 12 Mentioned in CV it starts automatically unattended An experience counts when you can tell its story: “…when AI makes it possible for you to do things you used to think as someone else’s work.” Task expansion © 2026 CGI Inc. Source: AI-Native Journey Tracker, qe-at-cgi-fi.github.io/ai-journey 8
9. DARK FACTORY VALIDATION DESIGN AI for testers journey SMART ARTIFACT TRANSFORMATIONS AGENTIC TESTING ARTIFACT TRANSFORMATIONS Test data and application not for AI No client artifacts to use AI on EXTERNAL IMAGINATION No AI tools access © 2026 CGI Inc. 9
10. A SUCCESS MINDSET: QUALITY ENGINEERING From doubtful intent to learning at the center Doubtful intent REQUIREMENTS END Living common ground Intent Lead sets the bar Conversations become specifications and acceptance materials. Converse with the people who hold the intent Ingest conversations into the OKF-LLMwiki Facilitate deepening the aspects that matter TESTIN G END Quality feedback slices Layered signals on whether the slice is good, and what we learned. IN THE MIDDLE Build a slice of value Learning Agents build, people validate, we decide what ships. Properties that must hold across every input Core examples, built up from the acceptance factory Model reconciliation: our model vs. the system Core examples grow from the living common ground into every feedback slice © 2026 CGI Inc. 10
11. NEW FRAMING FOR TEST PROCESS Automation is documentation 1 · FIR ST 2 · RIG HT AFTER 3 · TH EN 4 · LA ST Collaborate Automate — the documentation Explore Test cases 8 Spend time using the application; report bugs by fixing them 9 Publish the list of test cases for review and conversation — generated primarily from the automation 1 Start with enablers: budget, test environment, people — the things that move slowly 2 Risk-based sampling of reviews; follow the change 3 Build up a risk register and core examples in living common ground 4 When you test, first ask for bugs: quality slices 5 Pair to fix bugs, leaving behind architectureaware test automation: red → green → pull request 6 Model the APIs and UIs to increase automation coverage 7 Ensure core examples are included and reported green ↻ ALL ALONG © 2026 CGI Inc. 10 Collect product risks and drive risk-based quality slices 11 Improve bug fix decision-making rules 11
12. LESSON 2 ON COVERAGE Experiences coverage is foundation for innovation © 2026 CGI Inc. 12
13. LESSON 3 ON COVERAGE People coverage matters © 2026 CGI Inc. 13
14. DEEPLY HUMAN COVERAGE What social at work looks like to you? © 2026 CGI Inc. 14
15. BREAKING ILLUSIONS WITH TESTING From knowledge workers to builders, specializing in… © 2026 CGI Inc. 15
16. MIX UP THE TRADITIONAL ROLES IS AN OPPORTUNITY TO GROW Redistribution of work Traditional ↓ New → Intent Lead Lead Defines good. Analyst Developer Tester © 2026 CGI Inc. Context Engineer Value Engineer Alignment Engineer Decides what to ship. Sets the bar. Curates inputs. Translates outcomes. Maintains freshness. Builds assets. Experience Engineer Centers judgment. Bridges gaps. Designs interaction. Directs agents. Validates output. Tests behavior. Catches drift. Anticipates misuse. 16
17. LESSON 3 ON COVERAGE People coverage matters © 2026 CGI Inc. 17
18. FULLY AUTO MATED, DEEPLY HUMAN People can now do things by asking for it. © 2026 CGI Inc. 18
19. Insights you can act on Founded in 1976, CGI is among the largest IT and business consulting services firms in the world. We are insights-driven and outcomes-focused to help accelerate returns on your investments. Across hundreds of locations worldwide, we provide comprehensive, scalable and sustainable IT and business consulting services that are informed globally and delivered locally. cgi.com © 2026 CGI Inc. 19