techlist.io
KREN

Generative AI

125 posts

line4 min readCurated summary

ODW #8: A Hands-On Internal Workshop on Accelerating Incident Response and FAQ Generation with Slack MCP

LY Corporation’s Orchestration Development Workshop demonstrated how Slack MCP can turn scattered Slack conversations into structured operational knowledge. Using AI, employees can summarize incidents, generate reports, create FAQs, and publish results to Confluence with minimal setup. The workshop’s central conclusion was that hands-on practice, reusable skills, and human review are essential for turning new AI capabilities into practical workplace tools. ## The Information and Adoption Challenge - Slack contains valuable real-time information from incident response, customer inquiries, and project discussions. - Much of this information remains unstructured because employees lack time to document it. - Documentation quality varies by author, causing useful knowledge to become difficult to find. - Although Slack MCP became available internally in March 2026, adoption barriers remained: - Limited time to explore new tools - Concerns about complex configuration - Slow internal distribution of technical knowledge ## Introducing Slack MCP Through Hands-On Practice - Slack MCP is an internally developed MCP server connected to company authentication. - Employees can access internal Slack data without issuing personal tokens or configuring OAuth. - The workshop began with a simple exercise: - Launch a coding tool such as Claude Code - Ask the AI to post “Hello” in a designated Slack channel - Confirm that the message was actually posted - This immediate success helped participants understand MCP’s practical capabilities. ## Combining Slack MCP with Other MCP Servers Slack MCP supports several core operations: - Reading messages and threads - Posting messages and performing actions - Looking up channels and members - Searching Slack content Combined with other MCP servers, it can support broader workflows: - Slack plus Confluence MCP: Generate and publish project reports or FAQs - Slack plus Jira MCP: Create work tickets from discussions - Slack conversations can be transformed into structured documents rather than remaining isolated in chat history. ## Automatically Creating FAQs from Slack Inquiries The first major exercise converted repeated support discussions into reusable knowledge. - Slack inquiry threads were collected and converted into FAQ-formatted Markdown. - Existing Confluence content was checked to identify duplicates. - New FAQs were published as child pages under an existing Confluence knowledge base. - The output was formatted as a table containing: - Symptoms - Causes - Solutions The workflow was packaged into reusable skills such as: - `slack-to-faq`: Searches recent inquiry threads and generates new FAQ files - `faq-to-confluence`: Converts and publishes the FAQs to Confluence This demonstrated how MCP can automate the entire path from conversation search to knowledge-base publication. ## Supporting Incident Response The second exercise focused on reducing the time needed to understand and document incidents. ### Rapid Situation Summaries Participants could ask the AI to summarize an outage in natural language. MCP searched relevant Slack threads and organized the information into: - Current resolution status - Customer impact - Actions being taken by team members - A chronological timeline This helps managers or newly joining responders understand the situation quickly without reading every thread. ### Automated Incident Reports After resolution, the AI generated reports in a specified format, including: - Incident and detection times - Duration - Root cause - Affected users and features - Whether data was lost - Remediation steps The `slack-incident-status` and `slack-incident-report` skills separated real-time status checking from post-incident documentation. ## Practical Guidelines and Safeguards - Clean and constrain source data before processing it: - Compare results with existing Confluence FAQs - Filter messages using reactions or other markers - Limit searches to relevant channels and threads - Do not publish AI-generated documents without review. - Check for personal information and confirm that the output accurately reflects the source conversations. - Include links or references to the original Slack threads. - Specify the desired output structure, such as a three-column table for symptoms, causes, and solutions. - Convert successful prompts into reusable skills so teams can avoid rewriting complex instructions and maintain consistent output quality. ## Lessons from the Workshop - **Timing matters:** Holding the workshop soon after Slack MCP became available captured user interest and accelerated experimentation. - **Practice is more effective than explanation:** Starting with a simple Slack post and progressing to FAQs and incident reports made the benefits immediately tangible. - **Real work makes training relevant:** Inquiry handling and incident response were chosen because they are common, time-consuming tasks. - **Reusable skills improve adoption:** Prompt patterns were tested manually, refined, saved as skills, and shared with participants for continued workplace use. The recommended approach is to introduce new AI tools through timely, task-focused workshops, then refine successful workflows into shared skills. MCP can greatly reduce the effort of operational documentation, but human validation remains necessary before generated knowledge is published.

Read original(opens in new tab)
Generative AIModel Context ProtocolSlackClaude Code+4
aws3 min readCurated summary

Introducing the next generation of AWS Resilience Hub for generative AI-based SRE resilience journey | Amazon Web Services

AWS introduces the next generation of AWS Resilience Hub to help organizations manage application resilience consistently across large portfolios. The update adds a new business-oriented application model, modular resilience policies, dependency discovery, generative AI failure-mode analysis, and organization-wide reporting. Its goal is to help SREs and development teams define expectations, identify weaknesses, implement fixes, and demonstrate resilience through testing. ## Modular Resilience Policies - Policies are built from composable requirements rather than a single fixed policy type. - Requirements can include: - Availability service-level objectives (SLOs) - Multi-AZ and multi-Region disaster recovery - Recovery time objectives (RTOs) - Recovery point objectives (RPOs) - Backup data recovery requirements - Example policies can define 99.95% availability, a 15-minute RTO, and a 5-minute RPO for financial applications. ## Business-Oriented Application Modeling - A **system** represents a business application. - **User journeys** describe critical end-user paths and business outcomes. - **Services** represent deployable units such as microservices, AWS resources, code, and observability components. - Resilience Hub automatically maps resource relationships into a topology showing data flow, containment, and permissions. ## Dependency Discovery - Resilience Hub analyzes VPC DNS query logs to identify dependencies that may not be documented. - It can discover: - AWS services - Internal endpoints - Third-party endpoints - Unexpected cross-Region calls - Critical external dependencies - Dependency discovery can be enabled or disabled for individual services. ## Generative AI Failure-Mode Assessments - Assessments analyze services against: - Configured resilience policies - AWS Well-Architected best practices - The AWS Resilience Analysis Framework - Findings explain the failure mode, its architectural impact, recommended remediation, and related policy requirement. - Users can add or modify assertions to guide the AI agents and improve assessment accuracy. - Findings can be marked as resolved after remediation or irrelevant when they do not apply. ## Getting Started and Enterprise Management - Users must configure an invoker IAM role granting read-only access to AWS resources. - Cross-account roles or AWS Organizations service-linked roles can support multi-account environments. - AWS Organizations integration allows a delegated administrator to assess resilience across the enterprise without signing into individual accounts. - A typical workflow is: - Create a resilience policy. - Create a system and service. - Associate resources through tags, CloudFormation, Terraform, or Amazon EKS. - Enable dependency discovery. - Run a failure-mode assessment. - Review and implement recommendations. ## Migration, Availability, and Pricing - Migration APIs convert older Resilience Hub policies and applications into the new model, including mapping multiple related applications into one system with multiple services. - The new version is generally available in supported AWS commercial Regions. - Pricing uses a service-based model and includes two failure-mode assessments per service per month, with automated dependency assessment available optionally. - AWS offers a free trial. The updated Resilience Hub is most useful for organizations that need consistent resilience standards and evidence across many AWS accounts and applications. Teams should begin by defining reusable policies, modeling critical services and dependencies, and using the AI assessments to prioritize remediation.

Read original(opens in new tab)
Generative AITerraformInfrastructure As CodeAmazon Eks+4
google3 min readCurated summary

A New Era of Innovation: Google Research at I/O 2026

Google’s I/O 2026 research announcements present AI as an “agentic” amplifier of human ingenuity, particularly in science and healthcare. New systems such as Gemini for Science, ERA, Co-Scientist, and Gemini Deep Think are designed to generate hypotheses, write and optimize code, evaluate evidence, and solve difficult research problems. Google also highlighted health-focused AI that supports users before, during, and after medical visits, while emphasizing collaboration, validation, and responsible deployment. ## AI-Driven Scientific Discovery - **Gemini for Science** is a suite of experimental tools built from Google Research and developed with Google Cloud, Google DeepMind, and Google Labs. - **Empirical Research Assistance (ERA)** acts as a code-optimizing research engine: - Proposes concepts and writes software. - Evaluates results against a defined scoring system. - Uses tree search to test thousands of code variants. - Has supported work in neuroscience, cosmology, respiratory-illness forecasting, and California runoff prediction. - **Co-Scientist** is a Gemini-based multi-agent collaborator that generates, evaluates, and refines hypotheses. - Researchers have applied it to antimicrobial resistance, plant immunity, and liver fibrosis. - **Computational Discovery**, combining ERA and AlphaEvolve, runs thousands of code variations in parallel to test scientific models and hypotheses more quickly. - **Hypothesis Generation** uses a multi-agent “idea tournament” to debate and rank research ideas, with clickable citations supporting claims. - **Literature Insights**, powered by NotebookLM, helps researchers synthesize large bodies of scientific literature. - **Science Skills** can automate specialist workflows such as structural bioinformatics and genomic analysis on agentic coding platforms. ## AI for Peer Review and Advanced Reasoning - Google is piloting the **Paper Assistant Tool (PAT)** for scientific peer review. - PAT has experimentally reviewed more than 10,000 papers for conferences including ICML, STOC, and NeurIPS. - Its feedback has helped authors identify theoretical gaps and design additional experiments. - **Gemini Deep Think** has been used with mathematicians, physicists, and computer scientists to address open problems involving network deadlocks, optimization, machine-learning behavior, auction theory, and cosmic-string singularities. ## Advancing Health with AI - Google’s health research focuses on supporting people throughout the full healthcare journey, from understanding symptoms and preparing for appointments to interpreting medical records. - Research contributions underpin the **Google Health app** and **Google Health Coach**, with the app beginning rollout to existing Fitbit users. - **Symptom AI** investigates how conversational AI can reason about information relevant to a person’s symptoms. - A Fitbit-based study included 13,917 participants. - In blind comparisons, clinicians preferred Symptom AI’s differential diagnoses roughly twice as often as those produced by other clinicians. - The **Plan for Care** pilot involved 1,779 participants preparing for doctor visits. - Compared with baseline systems, 15% more users felt prepared. - 13% more users felt confident they could make effective use of their appointment. - Google is also studying personal health large language models and the use of personal health record data to improve health guidance. Google’s announcements point toward research systems that actively experiment, collaborate, and reason rather than merely retrieve information. Their practical value will depend on continued scientific validation, clinician involvement, privacy protections, and careful expansion from experimental tools into real-world use.

Read original(opens in new tab)
Generative AIMachine LearningGeminiMulti Agent Systems+2
figma3 min readCurated summary

The Figma Design Agent is Here | Figma Blog

Figma introduces a design agent built directly into its canvas and left rail. Unlike external tools, it understands a team’s components, tokens, libraries, standards, and best practices, while preserving designers’ ability to manipulate files directly. The agent is intended to support exploration, iteration, collaboration, and repetitive production work without forcing a choice between AI speed and design precision. ## A Figma-native design agent - Works inside the same Figma file as the team, acting as a collaborative partner. - Can start from any design layer and generate or edit Figma layers. - Supports parallel prompting to explore multiple ideas simultaneously. - Lets designers continue making manual edits while the agent works. - Uses context from frequently and recently used components, with additional control through selected libraries and `@` mentions for tokens, variables, and components. - Is designed for direct manipulation and editing of Figma files, rather than simply producing external suggestions. ## How the agent works with MCP and Figma Make - The Figma agent is intended for canvas-based work and has deeper design-system context. - Figma’s MCP server and `use_figma` support movement between code and the canvas: - Pull code into Figma for iteration or design-system application. - Push designs back to code while maintaining fidelity. - Teams can begin in Figma Design, use the agent to clarify flows, states, copy, and structure, then send work to Figma Make to generate code layers. - Alternatively, teams can start in Figma Make, copy frames into Figma Design, refine them with the agent, and return them to Make. ## Exploring more design directions - The agent helps designers generate several approaches instead of settling for the first plausible result. - It can: - Produce distinct stylistic directions for the same design. - Compare checkout flows optimized for different business goals. - Generate alternative information architectures. - Create multiple screen or layout variations. - Example prompts include generating organic, modern, and retro style options, or producing image carousels with different title treatments. - Once a direction is selected, hands-on editing remains an efficient way to refine the design and reduce unnecessary prompting. ## Automating repetitive design work - The agent handles bulk operations that require both scale and design context. - Potential tasks include: - Renaming variables consistently. - Replacing components across many screens. - Applying padding changes throughout a flow. - Populating frames with realistic content. - Updating typography across a file. - Replacing placeholder text and imagery. - Setting chip components to active states. - Converting screens to dark mode with appropriate fill and contrast changes. - For design-system teams, it can help update library descriptions, tags, use cases, naming conventions, and component documentation. - This automation is designed to preserve momentum between AI-generated changes and precise manual adjustments. The practical recommendation is to use the Figma agent for broad exploration and context-heavy repetitive work, while retaining direct canvas manipulation for judgment, refinement, and final design decisions.

Read original(opens in new tab)
Generative AIAIDesign SystemsModel Context Protocol+2
line4 min readCurated summary

AI Didn’t Replace QA; It Expanded It

Generative AI has not replaced QA at LINE Album; it has expanded QA’s scope and influence. The team found that QA productivity depends less on executing tests quickly than on organizing and interpreting large amounts of scattered information. By embedding AI into event-driven quality workflows, QA engineers now focus more on risk assessment, test strategy, and final decisions. ## QA as a Quality Architect - QA operates across the entire product lifecycle: planning, development, testing, release, and post-release feedback. - Its responsibilities include: - Identifying design risks during planning - Assessing the impact of code changes - Designing test strategies - Validating releases - Connecting user feedback and operational data to product improvements - QA information comes from many sources: - Planning and technical documents - Slack discussions and decisions - Jira tickets and pull requests - Automated test scripts and logs - App Store and Google Play reviews - The central challenge is therefore managing information volume and complexity, not merely increasing testing speed. ## From AI Assistant to AI-Driven Workflow - Initially, AI was used interactively to: - Summarize documents - Draft test cases - Organize bug reports - Document reproduction steps - This improved individual productivity but required QA engineers to manually collect and prepare information. - LINE Album QA instead built an automated quality platform with more than 30 workflows. - AI now reacts automatically to events such as: - Jira issue creation - Code changes and pull requests - Test execution - User feedback collection - AI gathers, analyzes, and structures quality information, while QA engineers interpret risks and make decisions. ## Scheduling and Webhook Automation ### Scheduled Analysis - Scheduled workflows periodically collect and summarize quality data. - Examples include: - Daily App Store review classification - API test result summaries sent to Slack - UI automation reports - Weekly QA activity and issue reports - QA engineers spend less time gathering data and more time evaluating risks and verifying important findings. ### Webhook-Based Analysis - Webhook workflows run immediately when quality-related events occur. - Examples include: - Summarizing the potential impact of merged code changes - Creating meeting notes when Slack discussions end - Analyzing and visualizing automated test results - This allows the team to recognize important quality signals much earlier. ## The AI-Supported QA Workday - UI tests run through MagicPod for Android and iOS, with results updated in Jira and shared in Slack. - Failed tests trigger analysis to determine whether they are flaky tests and identify possible causes. - Pytest-based API tests are similarly reported to Jira and Slack. - Daily Scrum workflows automatically provide: - Current test progress - Scrum board and issue dashboard links - Unresolved issues - Jira mentions requiring QA attention - App reviews are analyzed daily, classified as positive or negative, translated into Japanese and Korean, and summarized for the team. - During focused work periods, QA engineers use AI-generated information to plan quality activities, execute tests, monitor workflows, and summarize relevant discussions or documents. - End-of-day workflows summarize completed work and remaining issues. ## AI as a Test Design Partner - By 2026, AI generated approximately 90% of LINE Album QA’s test-case drafts. - Simple prompting produced many generic scenarios but failed to capture: - The reason a feature was introduced - Historical defect patterns - Effects on existing user flows - The team improved results by supplying broader context, including: - Specifications and development tickets - Change rationale - Previous Jira issues - Test history - Recurring bug patterns ### Multi-Agent Test Generation - An orchestrator coordinates five specialized sub-agents: - **Plan-Analyzer:** Examines requirements, feature descriptions, and images. - **Dev-Analyzer:** Adds implementation and development-ticket context. - **TestCase-Generator:** Produces normal, exceptional, boundary-value, platform-specific, and prioritized scenarios. - **TestCase-Validator:** Checks coverage, traceability, completeness, Given/When/Then structure, priorities, and platform coverage. - **Quality-Inspector:** Uses prior feedback and quality evaluations to improve future generations. - The workflow expands testing beyond stated requirements by incorporating defects that have historically occurred. - Validation feedback creates an iterative loop, making the output more executable and useful over time. AI is most valuable when it is connected to the organization’s accumulated context and quality signals—not when it is used merely as a chat-based drafting tool. The recommended approach is to automate information collection and analysis while keeping QA responsible for interpretation, prioritization, and final quality decisions.

Read original(opens in new tab)
Generative AIAutomationSlackJira+4
figma3 min readCurated summary

What the Design-to-Code Loop Unlocks | Figma Blog

AI is bringing design and engineering into a more continuous, bidirectional workflow. Instead of treating code as an expensive final step, teams can use functional prototypes, editable designs, and AI assistance to explore behavior and visuals together. The result is broader participation, faster learning, and a shift from mechanical translation between design and code toward more semantic collaboration. ## AI Makes Code Part of Design Exploration - Code was traditionally costly and difficult to revise, while design allowed cheap, broad exploration. - AI reverses that relationship by making functional wireframes easier to create and iterate. - Designers can explore interaction and behavior—not just static layouts—then move work between code and canvas. - AI can translate between the two mediums in a way that preserves intent and structure rather than simply converting files or syntax. ## A More Bidirectional Collaboration Model - Code-based workflows tend to move in one direction and are often constrained by the patterns already present in a codebase. - Figma’s canvas gives teams space to reconsider assumptions and explore radically different directions. - Designers and developers can work from the same evolving artifact instead of repeatedly handing work off. - AI lowers participation barriers: people without access to an internal design system can import a live product into Figma as editable frames and begin contributing. ## Lower Learning Curves for Designers and Developers - AI turns steep technical learning curves into gradual ramps by providing a capable starting point. - People can learn frameworks, routes, React, and other concepts in the context of real work rather than abstract exercises. - Designers can extend beyond previous technical limits into areas such as shaders, 3D, and custom tools. - Deeper specialization remains possible, but the initial investment is much smaller and learning becomes more contextual. ## Curiosity as the New Differentiator - When AI tools become broadly available, access to technology alone is less likely to distinguish practitioners. - Curiosity and taste become more important: people who actively experiment can discover new possibilities. - AI functions as a patient tutor, reducing the friction of learning tools, frameworks, syntax, and development environments. - Staying effective requires continually exploring what can be built rather than relying only on existing technical expertise. The design-to-code loop is therefore less about replacing designers or developers and more about making experimentation and collaboration accessible across disciplines. Teams should treat AI as both a creative medium and a learning partner, moving freely between canvas and code while preserving room to question the initial direction.

Read original(opens in new tab)
Generative AIFigmaDesign SystemsReact+2
aws3 min readCurated summary

AWS Weekly Roundup: Anthropic & Meta partnership, AWS Lambda S3 Files, Amazon Bedrock AgentCore CLI, and more (April 27, 2026) | Amazon Web Services

This week’s AWS news centers on deeper AI infrastructure partnerships and tools for building production-ready agents. AWS and Anthropic are expanding Claude’s integration with AWS hardware and Amazon Bedrock, while Meta is adopting Graviton for large-scale agentic AI workloads. New services for Lambda, EKS, Aurora, and Bedrock also emphasize simpler data access, hybrid networking, serverless scaling, and faster agent development. ## Anthropic and Meta Expand AWS AI Partnerships - Anthropic is training advanced foundation models on AWS Trainium and Graviton processors. - Anthropic and AWS’s Annapurna Labs are co-engineering at the silicon level to improve efficiency across the stack. - Claude Cowork is now available through Amazon Bedrock, allowing enterprise teams to collaborate with Claude while keeping data within AWS. - A unified Claude Platform on AWS is planned, offering a single experience for building, deploying, and scaling Claude applications. - Meta signed an agreement to deploy tens of millions of AWS Graviton cores for CPU-intensive agentic AI tasks, including reasoning, code generation, search, and orchestration. ## New Lambda and Kubernetes Infrastructure - AWS Lambda can mount Amazon S3 buckets as file systems using S3 Files. - Functions can perform standard file operations without downloading data first. - Built on Amazon EFS, S3 Files combines file-system access with S3’s scalability, durability, and cost model. - Multiple Lambda functions can share the same workspace, supporting AI agents that need persistent memory or shared state. - The Amazon EKS Hybrid Nodes gateway simplifies networking between cloud-based EKS resources and on-premises Kubernetes Pods. - It enables pod-to-pod traffic, control-plane webhook communication, and access to AWS services without making on-premises pod networks routable. - The gateway is available at no additional charge. ## Aurora Serverless and Bedrock Agent Development - Aurora Serverless now offers up to 30% better performance on platform version 4. - Its scaling algorithm better handles competing workloads, including busy APIs and bursty agentic AI applications. - The service continues to scale to zero during idle periods, with no additional charge for the improvements. - Amazon Bedrock AgentCore adds a managed harness in preview, allowing developers to define a model, system prompt, and tools without writing orchestration code. - Harnesses can later be exported as Strands-based code for greater control. - The AgentCore CLI supports governed, auditable deployments through AWS CDK, with Terraform support planned. - The CLI is available in 14 AWS Regions at no additional charge, and AgentCore skills support coding assistants. ## Cost Management, Operations, and Machine Learning - Granular cost attribution for Amazon Bedrock enables teams to track usage by project or organization and support detailed chargeback. - AWS DevOps Agent can work with the Salesforce MCP Server to investigate incidents, diagnose causes, and notify customers through Salesforce Service Cloud. - AWS microcredentials are now free through AWS Skill Builder in supported countries. - These hands-on assessments use simulated business scenarios and live AWS environments rather than traditional multiple-choice testing. - Amazon SageMaker AI can recommend optimized generative AI inference configurations, including instance types, containers, and inference parameters, helping reduce latency and deployment costs. ## Upcoming AWS Events - “What’s Next with AWS” is scheduled as a virtual event on April 28. - AWS Summits continue in May across cities including Singapore, Tel Aviv, Warsaw, Stockholm, Sydney, Hamburg, Seoul, Amsterdam, Bangkok, and Milan. AWS’s latest releases point toward a more integrated AI platform: specialized hardware for model execution, managed agent tooling, shared state through serverless storage, and stronger cost and operational controls. Builders should evaluate S3 Files and AgentCore for AI workflows, while teams running production inference can benefit from SageMaker recommendations and Bedrock’s improved cost attribution.

Read original(opens in new tab)
Generative AIKubernetesPostgreSQLAWS+4
google2 min readCurated summary

It's all about the angle: Your photos, re-composed

Google’s new Auto frame feature in Google Photos re-composes photos by changing the apparent camera viewpoint after capture. It combines 3D scene reconstruction with generative AI to adjust framing, reduce wide-angle distortion, and generate background areas that were outside the original frame. The result is a more natural perspective while preserving the visible content and subjects’ identities. ## Why Traditional Editing Falls Short - Cropping and zooming cannot change the original camera perspective or parallax. - They also cannot reveal areas hidden outside the captured frame. - This is especially limiting for portraits, selfies, and “almost perfect” photos with poor framing or lens distortion. ## Two-Stage 3D-Aware Editing - **3D scene and camera estimation** - A machine-learning model creates a 3D point map from the 2D image using monocular depth estimation. - Each pixel is associated with an estimated 3D surface point. - The system estimates the original focal length and reconstructs human faces and bodies carefully to reduce identity-distorting artifacts. - Semantic analysis detects subjects’ face positions and 3D orientations to determine better camera parameters. - **Generative completion and retouching** - Classical 3D rendering produces an image from the modified camera position, orientation, and focal length. - Moving the virtual camera exposes “holes” where the original image contained no information. - A latent diffusion model fills these missing regions and corrects the rendered result. - Classifier guidance with regional scaling helps preserve original content while allowing generation in newly revealed areas. ## Automatic Framing and Distortion Correction - The system automatically selects camera parameters for improved portrait composition. - It can adjust both camera pose and intrinsic properties such as focal length. - For wide-angle selfies, it detects perspective distortion that enlarges features close to the lens. - By effectively moving the virtual camera backward and adjusting the optics, it produces more natural facial proportions. ## Availability in Google Photos - The technology is now integrated into the Auto frame feature. - It applies to eligible photos containing people. - Users receive the re-composed image as a second Auto frame candidate. - The enhancement requires only a single action and automatically changes the viewpoint while retaining the original scene. The feature demonstrates how combining geometric 3D reconstruction with controlled generative inpainting can perform edits that conventional cropping and retouching cannot. For portraits and selfies, Auto frame offers a practical way to improve composition and perspective after the moment has passed.

Read original(opens in new tab)
Generative AIMachine Learning3d RenderingImage Editing+4
google3 min readCurated summary

Towards developing future-ready skills with generative AI

Vantage is a Google Research experiment that uses generative AI to assess durable “future-ready” skills such as critical thinking, collaboration, conflict resolution, and creativity. It places students in realistic conversations with AI teammates, dynamically introduces challenges, and evaluates performance against educational rubrics. A study with New York University found that AI-generated scores agreed with human expert ratings at a comparable level to agreement between human raters. ## Why Future-Ready Skills Are Difficult to Measure - Skills such as collaboration, creative thinking, and conflict resolution are increasingly important as technology changes work and education. - Traditional tests are too rigid to capture how people think, communicate, and respond in realistic situations. - Human-based assessments can be resource-intensive, difficult to standardize, and dependent on whether challenging situations arise naturally. - Vantage aims to make these skills measurable, scalable, and useful for guiding instruction and student growth. ## AI-Simulated Team Assessments - Students participate in open-ended tasks, such as preparing a debate or pitching a creative idea, alongside AI avatars. - An “Executive LLM” uses an assessment rubric to manage the conversation and introduce targeted challenges, such as disagreement or conflict. - This adaptive process is designed to elicit enough evidence to assess a particular skill while keeping the interaction natural. - An “AI Evaluator” reviews the conversation transcript using the same rubric. - Students receive a visual skill map and qualitative feedback describing their demonstrated strengths and areas for improvement. ## Validation with New York University - Google Research partnered with NYU to align Vantage’s tasks and scoring criteria with established educational rubrics. - The joint study involved 188 U.S. participants aged 18–25 and focused on conflict resolution and project management. - Researchers tested whether the Executive LLM could steer conversations toward specific skills. - Steered conversations produced significantly more skill-relevant information than conversations involving independent, uncoordinated AI avatars. - The AI Evaluator’s scores showed agreement with human expert ratings comparable to the agreement between two human raters. - The results suggest that LLM-based assessment can provide a scalable alternative for evaluating complex interpersonal skills. ## Additional Research - Google also collaborated with OpenMic to study creativity and English language arts. - The collaboration analyzed work from 180 students completing creative multimedia assignments, including character interviews and literature-related media articles. - These studies tested whether the evaluation approach could extend beyond collaboration-focused tasks. Vantage is available in English through Google Labs as a research experiment. Its approach could help educators provide more consistent practice, evidence-based feedback, and scalable assessment for skills that conventional tests struggle to capture.

Read original(opens in new tab)
Generative AIProject ManagementConflict ResolutionExecutive Llm+4
figma2 min readCurated summary

Turning Prompts into Five Scalable Workflows with Figma Weave | Figma Blog

Figma Weave presents AI creation as a scalable, editable workflow rather than a one-off prompt. Its canvas connects AI models and processing nodes so creators can branch, refine, and reuse each step while maintaining control over imagery, video, audio, and 3D output. The article introduces five workflows, beginning with a method for deriving a reusable visual style from multiple reference images. ## Figma Weave as a Creative Workflow Canvas - Figma Weave evolved from Weavy, which Figma acquired to expand its capabilities in: - Image and video generation - Animation and motion design - Audio and 3D creation - VFX and professional editing - Users can chain prompts and AI nodes together, moving from references to finished assets without losing the ability to revise intermediate steps. - Figma has published more than 20 Community templates covering tasks such as: - Turning images into videos - Generating 3D models - Combining visual references - Comparing image-generation models ## Why Workflows Are More Scalable Than Single Prompts - A single prompt produces one interpretation of a style. - A workflow lets creators independently adjust how strongly each reference influences the result. - Individual stages can be reshaped, reused, and applied across multiple assets and channels. - The example brand, Epoch, demonstrates how the system can support a consistent visual identity based on distorted textures and 3D natural forms. ## Combining Two Images into a Reusable Style Guide - The first workflow combines a hibiscus flower and a rock face from Epoch’s existing visual references. - Each image is processed through an **Image Describer node**, which extracts attributes such as: - Texture - Color - Lighting - Composition - The resulting text descriptions can be edited and merged into a new style definition. - The balance between the two references can be adjusted until the desired blend is achieved. - The combined style can then be tested across different image-generation models, helping the team validate the look at scale. - The output is treated as a reusable style system rather than a single prompt for one image. The practical recommendation is to build visual direction as a modular workflow: analyze existing references, combine and tune their characteristics, and preserve the resulting style definition for reuse in future assets.

Read original(opens in new tab)
Generative AIPrompt EngineeringFigma WeaveImage Generation+2
figma3 min readCurated summary

How Figmates Used Figma AI to Take Delight to the Next Level | Figma Blog

Figma’s 2026 April Fun Day project, “FigCade,” used Figma Make, Figma Weave, and the Figma MCP server to create six playable mini-games in only a few days. The tools helped the team rapidly prototype ideas, explore visual styles, produce media, and translate designs into code. The project demonstrated how AI can make design and development more collaborative and iterative. ## Building a playful canvas experience - April Fun Day is Figma’s annual tradition of adding playful surprises and Easter eggs for its community. - This year, the team brought six mini-games directly into the Figma canvas for one week. - The project also gave employees an opportunity to experiment beyond their usual roles and push Figma’s tools in new ways. - The resulting FigCade included games such as: - **2Fast2Figma**, a timed quiz about Figma facts. - **FigPalette** and **Diabolical Magic Square**, featured in the game menu. ## Rapid prototyping with Figma Make - Figma Make helped the team turn ideas into working prototypes quickly. - An early concept for 2Fast2Figma was created on a Sunday morning and became functional that afternoon. - The team generated multiple prototypes, tested them with others, and iterated based on feedback. - This established a fast workflow: build something quickly, review it, align with the team, and refine it. ## Exploring visuals with Figma Weave - Figma Weave helped designers generate and explore visual assets more efficiently. - Designer Lesley Moon used it to create felt-style textures and assets, including the project’s textured cursor. - Generating many variations quickly expanded the range of visual themes the team could consider. - Weave was also used to develop the April Fun Day trailer: - Product Manager Tara Nadella explored the initial concept. - Motion Designer Fifi Law used those explorations and Lesley’s visuals to produce the final trailer in one day. ## Connecting design and code with MCP - The Figma MCP server helped developers turn design explorations into implementation. - Engineer Steven Noto used Claude and GitHub Copilot with MCP authentication. - By sharing links to specific Figma components, the coding agents could access design context and generate code matching the intended specifications. - The team moved back and forth between design and development, using AI to reduce the distance between visual concepts and working software. ## Practical takeaway FigCade illustrates how combining rapid prototyping, generative visual tools, and design-aware coding assistance can help small teams create polished interactive experiences quickly. The strongest results came from treating AI as part of an iterative design-and-development process rather than as a replacement for human direction.

Read original(opens in new tab)
Generative AIPrototypingGithub CopilotFigma Make+2
aws3 min readCurated summary

AWS Weekly Roundup: NVIDIA Nemotron 3 Super on Amazon Bedrock, Nova Forge SDK, Amazon Corretto 26, and more (March 23, 2026) | Amazon Web Services

This week’s AWS roundup highlights major updates across generative AI, data analytics, Java, serverless, logging, and Kubernetes. Notable announcements include NVIDIA Nemotron 3 Super on Amazon Bedrock, the Nova Forge SDK for customizing models, faster Redshift queries, and expanded EKS scaling and availability guarantees. The roundup also points readers to community initiatives, developer resources, and upcoming AWS events. ## Generative AI and Developer Tools - **NVIDIA Nemotron 3 Super** is now available through Amazon Bedrock. - Supports text generation, reasoning, summarization, and code generation. - Can be invoked through Bedrock’s unified API without managing infrastructure. - **Nova Forge SDK** simplifies fine-tuning and customizing Amazon Nova models. - Enables domain-specific adaptations for enterprise use cases. - Handles much of the underlying customization and deployment complexity. - **Kiro for students** provides free access to AI-powered development tools. - **Strands Steering Hooks** reportedly achieved 100% agent accuracy, outperforming prompt engineering and rigid workflows for controlling agent behavior. ## Data, Java, and Serverless Updates - **Amazon Redshift** now delivers up to 7x faster execution for new, uncached queries in dashboards and ETL workloads. - The improvement is especially useful for workloads with high query variability. - **Amazon Corretto 26** is generally available. - Includes current Java features, performance improvements, and security updates. - Supports Amazon Linux, Windows, macOS, and Docker environments. - **AWS Lambda** now exposes Availability Zone metadata for function invocations. - Helps with observability, troubleshooting, latency analysis, and multi-AZ architecture decisions. - **CloudWatch Logs** supports log ingestion through an HTTP-based protocol, reducing the need for custom agents or SDK integrations. ## Amazon EKS Enhancements - Provisioned Control Plane clusters now receive a **99.99% SLA**, compared with 99.95% for the standard control plane. - A new **8XL scaling tier** doubles Kubernetes API server request-processing capacity compared with the 4XL tier. - The larger tier targets demanding workloads such as AI/ML training, HPC, and large-scale data processing. ## AWS Community and Events - **AWS Builder Center badges** recognize contributions, challenges, and community participation. - AWS promotes community-driven learning through the “Keep Building Together” initiative. - Upcoming events include AWS Summits in cities such as Paris, London, Bengaluru, Singapore, Tel Aviv, and Stockholm; AWS Community Days in San Francisco and Romania; and the AWSome Women Summit LATAM in Mexico City. Overall, the announcements emphasize AWS’s continued investment in enterprise AI customization, higher-performance infrastructure, improved observability, and developer communities. Teams should evaluate the new Bedrock, Redshift, Lambda, and EKS capabilities according to their workload scale, reliability, and customization needs.

Read original(opens in new tab)
Generative AIDatabase DesignKubernetesAmazon Bedrock+4
stripe2 min readCurated summary

Three of the biggest fraud trends from MRC Vegas 2026

Fraud is becoming more automated, adaptive, and difficult to detect with traditional rules-based systems. At MRC Vegas 2026, leading fraud teams emphasized dynamic authentication, fraud controls embedded directly into agentic payments, and layered identity verification to address deepfakes and synthetic identities. The common goal is to reduce friction for trusted customers while applying stronger defenses where risk is highest. ## Dynamic Authentication Based on User Intent - Universal authentication creates unnecessary friction, increases false positives, and can cause businesses to lose legitimate customers and their long-term value. - Airbnb advocates building behavioral profiles over time to measure “high-trust velocity”—the likelihood that a user’s activity reflects legitimate intent. - Trusted users can proceed without additional challenges, while authentication is reserved for the small percentage of traffic proven to be risky. - Stripe Radar’s adaptive 3DS uses AI to trigger authentication only when transaction behavior appears unusual. - Stripe reports that eligible businesses have seen fraud reductions of more than 30% with this approach. ## Fraud Detection for Agentic Commerce - Ashley Furniture’s existing rules-based system handled different authorization needs for quick-ship products and custom orders. - That model became insufficient when AI agents began making purchases across channels. - Fraud detection must be part of the payment infrastructure and evaluate transactions in real time, rather than analyzing them only after purchase. - Stripe Shared Payment Tokens let agents use a customer’s saved payment method without exposing payment credentials. - Combined with Stripe Radar, these tokens transmit risk signals such as potential disputes, card testing, stolen-card usage, and issuer declines. - These signals help distinguish legitimate, high-intent agents from low-trust automated bots. ## Deepfakes and Synthetic Identity Fraud - Fake identities are easier to create because criminals can access document templates and generative AI impersonation tools. - Fraudsters may produce convincing fake IDs, images, voices, and videos with limited resources. - Effective verification depends on identifying inconsistencies that forgeries fail to reproduce, such as incorrect signatures, mirrored photos, or mismatched expiration dates. - No single verification check is reliable enough; multiple independent checks are necessary. - Stripe Identity uses AI to detect fake documents and spoofed photos, compare ID images with selfies, and validate Social Security numbers and addresses against databases. Businesses should replace blanket controls with risk-sensitive interventions: minimize friction for trusted users, integrate fraud detection into agent-driven payment flows, and use layered identity verification to catch increasingly convincing forgeries.

Read original(opens in new tab)
Generative AIMachine LearningStripeAgentic Commerce+4
discord3 min readCurated summary

How ROOST is Advancing Online Safety

Discord argues that online safety should be built through shared, open-source infrastructure rather than isolated corporate systems. Its donated rules engine, Osprey, lets platforms detect suspicious behavior and harmful activity in real time, while ROOST develops and maintains tools for broad industry adoption. Early adoption, including by Bluesky, suggests this model can raise baseline safety standards across the internet. ## The Need for Shared Safety Tools - Nearly 100 million people use Discord daily, generating hundreds of millions of events that must be evaluated for threats. - Generative AI has increased the scale and sophistication of phishing, deepfakes, and coordinated abuse. - Smaller platforms often lack the resources to build effective trust-and-safety systems from scratch. - ROOST aims to make proven safety technologies open, shared, and auditable. ## How Osprey Works - Osprey is a real-time rules engine for event processing and behavioral analysis. - It can evaluate logins, messages, account creation, content posts, and platform-specific actions. - Safety teams write rules in a simple language and deploy them without engineering dependencies. - The engine produces transparent decisions indicating whether activity is safe, suspicious, or malicious. - Discord runs thousands of rules across hundreds of action types. - Investigation findings feed new rules, while enforcement generates additional signals for future detection. - The open-source release is based on Discord’s production system rather than a reduced version; improvements from ROOST were later reintegrated into Discord. ## ROOST’s Collaborative Model - ROOST builds on earlier cross-industry efforts such as image hashing for child-safety work, the Tech Coalition’s Lantern program, GIFCT incident response, and shared ISO safety standards. - Unlike organizations that primarily steward open-source projects, ROOST also develops and maintains a suite of public-interest safety tools. - Its projects include Osprey and Coop, a comprehensive review tool. - Open-source tools can raise the minimum level of protection available to smaller platforms and reduce the spread of threats across services. - The model also enables companies to build managed services around free tools, similar to businesses built around Linux. ## Adoption and Industry Impact - Musubi announced a managed Coop offering, while Zentropi integrated its labeling engine with Coop. - Osprey v1 was introduced at FOSDEM, prompting collaboration among engineers from multiple organizations and protocols. - Platforms such as Bluesky are already using Osprey. - More than 360 million users across participating platforms are now covered by open-source safety tooling. - ROOST continues development through public contributor and adopter working-group meetings held every two weeks. ROOST’s approach suggests that open, production-grade safety infrastructure can help platforms respond faster to emerging threats while creating a shared foundation for industry-wide improvement.

Read original(opens in new tab)
Generative AIOpen SourceBehavioral AnalysisTrust And Safety+4
figma2 min readCurated summary

Design’s Influence Is Expanding, and Here’s Why That Feels Hard | Figma Blog

Design is expanding into more products, interactions, and strategic decisions, especially as AI introduces new software categories and interfaces. Although AI makes design work faster, it also increases output, expectations, and workload rather than reducing effort. This leaves designers divided: the field is growing, but many are unsure whether it is improving. ## Design’s Expanding Influence - Each technological shift—from graphical interfaces to the web and mobile apps—has increased design’s scope. - AI is creating new categories such as agent orchestration systems and answer engines. - Existing products are gaining generative, conversational, and predictive features. - Users now interact through prompts, speech, and image uploads, creating new design challenges: - Translating ambiguous input into clear intent - Making automated experiences understandable and human - Designing beyond traditional screen-by-screen navigation - Survey results show mixed sentiment: - 36% of designers think the profession has improved - 35% think it has worsened - 29% see no change - Meanwhile, 82% of hiring managers say demand for designers has increased or remained steady, though only 20% believe the industry itself is improving. ## AI Expands the Work - AI helps teams address new design problems more quickly, but it does not necessarily reduce the amount of work. - Product builders reported a 17.5% year-over-year increase in the number of tasks they perform. - Research from UC Berkeley found that AI users work faster while also taking on more tasks and working longer hours. - Workers often feel more productive without feeling less busy. ## The Jevons Paradox in Design - As AI makes creation cheaper and easier, teams produce more designs, explore more options, and iterate more deeply. - This follows the Jevons Paradox: efficiency increases can lead to greater overall consumption rather than reduced consumption. - Software development experienced a similar pattern when cloud infrastructure made releases easier, resulting in more frequent releases and redesigns. - AI has changed the rhythm and volume of design work rather than eliminating it. Designers should view AI as a force multiplier, not a shortcut to less work. Its benefits will depend on managing rising expectations and workload while developing clearer approaches to complex, automated interactions.

Read original(opens in new tab)
Generative AIAIUser Experience DesignCloud Infrastructure+3