# Latest reads > The engineering internet, summarised so you can actually read it. ## Articles ### [Building Reliable Production AI with Durable Workflows](https://yomu.fyi/post/building-reliable-production-ai-with-durable-workflows.md) - Company: [Salesforce](https://yomu.fyi/company/salesforce.md) - Author: Scott Nyberg - Published: Jul 27, 2026 AI prototypes rely on simple prompt-response interactions, but production AI systems handling thousands of records must manage distributed execution issues like worker crashes, rate limits, and transient failures. Rather than treating long-running operations as single large jobs or rebuilding state from logs, systems require durable workflows that preserve execution history across failures. In Agentforce Grid, execution is organized into a hierarchy where column runs divide into recoverable batches and rows composed of discrete activities. Each batch checkpoints after every successful row, retrying up to ten times with exponential backoff and resuming strictly at incomplete work to prevent duplicated model calls. Exposing progress across these hierarchical boundaries ensures that both users and engineers can distinguish completed, failing, and retryable units. ### [Pinner Progression: Better Use-Case Representation Driving Weekly Active User Growth at Pinterest](https://yomu.fyi/post/pinner-progression-better-use-case-representation-driving-weekly-activ.md) - Company: [Pinterest](https://yomu.fyi/company/pinterest.md) - Author: Pinterest Engineering - Published: Jul 27, 2026 Pinterest designed the Pinner Progression initiative to shift its home feed recommendation pipeline from short-term engagement optimization toward long-term user retention. Standard ranking systems model user actions as immediate sequential features, failing to capture the evolving lifecycles of distinct user habits. To address this gap, the platform introduced User Interest Clusters (UICs), which cluster a user's engaged Pins in OmniSage embedding space using dynamic cluster counts and stateful lifecycle metadata. Pinterest integrated a UIC-aware penalty directly into Sliding Spectrum Diversity (SSD) scoring by matching Pin embeddings to cluster medoids via cosine similarity. Online experiments demonstrated that balancing use-case representation increased interaction diversity, extended session lengths, and delivered meaningful engagement gains across the platform. ### [No Dumb Questions: What is the AI bottleneck? How does context engineering fix it?](https://yomu.fyi/post/no-dumb-questions-what-is-the-ai-bottleneck-how-does-context-engineeri.md) - Company: [Stack Overflow](https://yomu.fyi/company/stack-overflow.md) - Author: Phoebe Sajor - Published: Jul 24, 2026 An adoption bottleneck slows artificial intelligence integration because standalone tools lack connectivity with everyday enterprise workflows. While models can draft responses or process text, they fail to access siloed background information from emails, chat channels, and shared documents. Consequently, human users must expend disproportionate effort gathering context, granting tool permissions, and editing preliminary outputs. Michael Foree explains that overcoming this hurdle requires context engineering, where practitioners deliberately observe their own thought processes to identify relevant information sources and filter out distracting data. Testing mock prompts and iteratively refining context architectures allows practitioners to bridge the gap between standalone model capabilities and autonomous task execution. ### [Agent platform (Part 1): How we help Grab build and run AI agents at scale](https://yomu.fyi/post/agent-platform-part-1-how-we-help-grab-build-and-run-ai-agents-at-scal.md) - Company: [Grab](https://yomu.fyi/company/grab.md) - Author: Kendrick Tan - Published: Jul 24, 2026 Grab scaled its internal AI tooling by transforming the infrastructure behind a single technical support bot into a standardized agent framework named LLM-Kit. The original Go-based bot revealed critical bottlenecks, including the lack of automated evaluation, painful provider migrations, fragmented observability, and excessive production scaffolding overhead. To address these frictions, engineers developed a FastAPI template pre-wired with LangGraph ReAct agents, remote Model Context Protocol servers, and built-in ROUGE, BLEU, and LLM-as-judge evaluation suites. The framework centralizes model access through an OpenAI-compatible GrabGPT Gateway and unifies observability across services, outbound calls, and agent steps using OpenTelemetry. This extracted scaffolding reduced day-one production setup time from two weeks to roughly an hour while supporting hundreds of production agents. ### [How AI Rebuilt Salesforce’s Decades-Old Localization Pipeline](https://yomu.fyi/post/how-ai-rebuilt-salesforce-s-decades-old-localization-pipeline.md) - Company: [Salesforce](https://yomu.fyi/company/salesforce.md) - Author: Scott Nyberg - Published: Jul 23, 2026 Salesforce needed to deliver major releases across 34 languages as product localization volume surged by more than 35% under fixed budgets and unchanged delivery windows. To address these scaling constraints, the engineering team replaced their legacy translation workflows with an LLM-powered orchestration pipeline integrating prompt engineering, context engineering, and multi-stage validation. The architecture transforms existing style guides, glossaries, and terminology databases into structured context, routing interface strings through specialized prompt stages—up to 85 stages for some languages—to enforce product context, grammar, and branding rules. Combined with an automated validation loop spanning AI editing, AI validation, and human review, this system reduced localization costs by 50 to 90% while accelerating turnaround times across enterprise releases. ### [Treating Pricing Changes Like Code Deploys](https://yomu.fyi/post/treating-pricing-changes-like-code-deploys.md) - Company: [Thumbtack](https://yomu.fyi/company/thumbtack.md) - Author: Ananda Kanagaraj Sankar - Published: Jul 22, 2026 Thumbtack manages marketplace pricing by updating hundreds of thousands of bid settings stored in DynamoDB across service offerings. Previously executed through individual custom Go scripts, these pricing rollouts lacked automated runtime state tracking, dynamic database throughput pacing, and durable records for reliable rollbacks. To eliminate manual operational risk, engineering introduced a shared deployment-like engine that accepts declarative target states and executes pure Go transformation functions without direct I/O. The engine enforces idempotency, conducts dry runs with validation reports to S3, coordinates atomic DynamoDB updates with audit logging, and dynamically manages write capacity. This platform standardizes pricing updates into reviewable, resumable, and reversible operations that safely skip already written rows and check for production drift during rollbacks. ### [Building a serverless AI assistant at Pelago: concept to care in two weeks](https://yomu.fyi/post/building-a-serverless-ai-assistant-at-pelago-concept-to-care-in-two-we.md) - Company: [AWS](https://yomu.fyi/company/aws.md) - Author: Anton Aleksandrov - Published: Jul 22, 2026 Pelago engineered a serverless, event-driven AI assistant on AWS within two weeks to provide substance use recovery coaches with contextual response suggestions. Operating under strict Protected Health Information constraints, the system maintains clinical safety through human-in-the-loop review and keeps data confined to an Amazon VPC. Incoming messages flow via AWS AppSync and Amazon DynamoDB to an Amazon SNS topic, which fans out to independent AWS Lambda functions. The asynchronous Chat Assistant Lambda queries history, invokes Amazon Bedrock, and persists suggestions into Amazon RDS MySQL in under 10 seconds. When coaches access a conversation via Amazon API Gateway, pre-generated suggestions load in under 100 milliseconds. ### [Building multi-Region resiliency for AWS CloudFormation custom resource deployment](https://yomu.fyi/post/building-multi-region-resiliency-for-aws-cloudformation-custom-resourc.md) - Company: [AWS](https://yomu.fyi/company/aws.md) - Author: Raman Pujani - Published: Jul 22, 2026 AWS CloudFormation custom resources extend template provisioning capabilities but lack built-in multi-Region coordination, risking duplicate executions and unhandled failures during regional outages. To solve this limitation, an active-active architecture leverages Amazon Simple Notification Service topics to fan out lifecycle events across primary and secondary infrastructure Regions. The primary Region processes events immediately, whereas the secondary Region processes incoming messages after a deliberate delay implemented via Amazon Simple Queue Service. Coordination relies on Amazon DynamoDB Global Tables with conditional writes to manage distributed locking and enforce idempotency. When failures occur in the primary Region, Amazon CloudWatch alarms signal Amazon Application Recovery Controller to automate failover without manual intervention. ### [Architecting offline-first generative AI applications for edge deployments using AWS services](https://yomu.fyi/post/architecting-offline-first-generative-ai-applications-for-edge-deploym.md) - Company: [AWS](https://yomu.fyi/company/aws.md) - Author: Ahmed Ewis - Published: Jul 22, 2026 Industrial edge environments often face significant unplanned downtime yet lack reliable cloud connectivity to run large-scale artificial intelligence models. To address this limitation, an offline-first reference architecture shifts generative inference to edge devices while leveraging cloud services for preparation and lifecycle management. The workflow uses Amazon Bedrock with Amazon Nova Pro to create labeled dataset pairs, Amazon SageMaker AI Pipelines to fine-tune a compact model, and AWS IoT Greengrass to orchestrate edge deployments. Local execution relies on Ollama, Strands Agents, and a CPU-based ChromaDB retrieval pipeline that consumes zero GPU VRAM. In evaluations across three foundation model judges, the fine-tuned gpt-oss-20b model combined with retrieval-augmented generation consistently outperformed the base model configuration across accuracy, completeness, and relevance metrics. ### [Automate custom PII detection at scale with Amazon Macie and Step Functions](https://yomu.fyi/post/automate-custom-pii-detection-at-scale-with-amazon-macie-and-step-func.md) - Company: [AWS](https://yomu.fyi/company/aws.md) - Author: Aishwariya Khiani - Published: Jul 22, 2026 Regulated organizations ingesting large data volumes must detect and classify standard and domain-specific personally identifiable information to satisfy compliance mandates like GDPR, HIPAA, CCPA, and PCI DSS. To eliminate manual inspection, an event-driven architecture orchestrates Amazon Macie scans for files landing in Amazon S3. Amazon EventBridge captures upload events and invokes AWS Step Functions, which manages Lambda functions to stage objects, trigger Macie classification jobs with custom regex identifiers, and poll for results. The pipeline separates data across a three-bucket pattern representing raw, staged, and scanned states to prevent mixing unprocessed data with validated assets. Finally, the workflow exports timestamped compliance reports in CSV and JSON formats while alerting security teams via Amazon SNS on high-severity findings. ### [Session revocations at scale](https://yomu.fyi/post/session-revocations-at-scale.md) - Company: [Canva](https://yomu.fyi/company/canva.md) - Author: Llew Vallis - Published: Jul 22, 2026 Canva gateways check in-memory session revocations on every request, but pulling over a million revocations from MySQL during deployments created severe database stampedes. To eliminate this bottleneck, the team transitioned to storing a twelve-hour sliding window of revocations in Amazon S3 partitioned into 30-minute chunks. Each revocation is packed into a 16-byte binary structure within a sorted flat array, allowing gateways to query records via direct binary search without object deserialization. Asynchronous workers batch updates into S3 using ZooKeeper leader election and conditional PUT requests for optimistic concurrency control. This architecture reduced the in-memory cache footprint by 87.5% and allowed the team to reduce their MySQL database to just two read replicas. ### [Personalizing Airbnb search by learning from the guest journey](https://yomu.fyi/post/personalizing-airbnb-search-by-learning-from-the-guest-journey.md) - Company: [Airbnb](https://yomu.fyi/company/airbnb.md) - Author: Daochen Zha - Published: Jul 21, 2026 Airbnb replaced hundreds of hand-crafted ranking features with a Transformer-based sequence model that captures both long-term booking history and short-term browsing behavior. To keep latency low and throughput high, sequence representations are generated via daily batch jobs and combined with real-time queries using a co-trained setwise ranker. ### [Building a Transformer-Based Category Recommender at Thumbtack](https://yomu.fyi/post/building-a-transformer-based-category-recommender-at-thumbtack.md) - Company: [Thumbtack](https://yomu.fyi/company/thumbtack.md) - Author: Andrew Morss - Published: Jul 20, 2026 Thumbtack developed a transformer-based category recommender to personalize email and push notification suggestions across roughly 500 home service categories. Because user activity is sparse while contextual signals like location and climate are rich, the architecture represents search history and context features as sequences of tokens evaluated against candidate category tokens using cross-attention. Initial training with naive cross-entropy suffered from severe popularity bias, skewing recommendations toward head categories and yielding a low tail hit rate. To resolve this issue, the team implemented adaptive mixed sampling, combining in-batch and random negative candidates and keeping only top-scoring hard negatives for cross-entropy loss computation. This method raised tail hit rate from 2.1% to 28.4%, improved overall HR@10 to 54.6%, and yielded a statistically significant 5% lift in requests per user in production A/B testing. ### [How our universal content processing platform Riviera evolved for AI and beyond](https://yomu.fyi/post/how-our-universal-content-processing-platform-riviera-evolved-for-ai-a.md) - Company: [Dropbox](https://yomu.fyi/company/dropbox.md) - Author: Ilya Yakovlev,Andrew Cheung,Binoy Dash - Published: Jul 20, 2026 Dropbox developed Riviera, a centralized content processing platform that evolved from an internal file preview generator into a shared infrastructure supporting over 300 file formats. By decomposing complex conversion tasks into modular, reusable transformations, the system now powers search indexing, media transcoding, and AI context extraction across Dropbox products. ### [Coding Agent Horror Stories: The Agent That Deleted Production](https://yomu.fyi/post/coding-agent-horror-stories-the-agent-that-deleted-production.md) - Company: [Docker](https://yomu.fyi/company/docker.md) - Author: Jennifer Kohl - Published: Jul 20, 2026 Recent industry updates focus on AI agent security, container maintenance, and developer workflows within Docker ecosystems. The OpenAI and Hugging Face incident involved 17,600 attacker actions, demonstrating that AI agent security requires automated system controls to constrain, observe, and govern agents rather than relying on human review. In software maintenance, Docker Extended Lifecycle Support (ELS) addresses escalating supply-chain risks and MinIO end of life by maintaining patches, building software from source, and enforcing local developer policies. For continuous integration, Docker Sandboxes enable isolated AI agents to run Testcontainers tests, implement code fixes, and submit draft pull requests within GitHub Actions. Additionally, Docker Verified Publisher applications have transitioned to a self-serve process accessible directly through Docker Hub. ### [In-House LLM Serving at Netflix](https://yomu.fyi/post/in-house-llm-serving-at-netflix.md) - Company: [Netflix](https://yomu.fyi/company/netflix.md) - Author: Netflix Technology Blog - Published: Jul 17, 2026 Netflix established an in-house serving platform to run large language model inference directly inside existing production environments alongside traditional machine learning models. Built upon NVIDIA Triton Inference Server and vLLM, the unified architecture handles member-scale routing, candidate generation, feature fetching, and model execution over gRPC and OpenAI-compatible HTTP endpoints. The team shifted their primary engine from TensorRT-LLM to vLLM to support custom architectures, simpler debugging, and non-trivial constraint logic. Addressing production obstacles required patching Triton's frontend for guided decoding, pinning dependent library versions, rewriting logits processors in C++ for vLLM V1, and handling state machine resets during engine preemptions. The resulting platform unifies deployment flows while preserving operational stability across evolving model schemas. ### [The cost of saying yes has changed](https://yomu.fyi/post/the-cost-of-saying-yes-has-changed.md) - Company: [Github](https://yomu.fyi/company/github.md) - Author: Dalia Abuadas - Published: Jul 17, 2026 Generating initial code patches has become significantly cheaper with AI agents, shifting the primary expense of small feature requests from writing code to debating scope in meetings. Teams can use agent-generated patches as diagnostic probes rather than final deliverables, turning abstract scope debates into concrete artifacts that reveal true system touchpoints and risks. However, low generation costs do not translate to low ownership costs, as changes touching areas like authorization, compliance, or public contracts still demand significant human review. Constrained attempts allow engineers to price uncertainty quickly and shift scope discipline from pre-implementation speculation to evidence-based code review. ### [Eclipse Dataspace Components on AWS: Cost optimization strategies](https://yomu.fyi/post/eclipse-dataspace-components-on-aws-cost-optimization-strategies.md) - Company: [AWS](https://yomu.fyi/company/aws.md) - Author: Jorge Hernández Suárez - Published: Jul 17, 2026 Deploying Eclipse Dataspace Components (EDC) connectors on AWS presents challenges in forecasting infrastructure expenses without clear benchmarks. Estimated costs differ substantially between business-critical setups and non-critical environments based on compute and database sizing. A business-critical configuration relying on Amazon Aurora PostgreSQL db.r6g.large and standard Amazon ECS with AWS Fargate totals an estimated 387.00 USD monthly in the eu-south-2 region. Sizing down to db.t4g.medium and switching to AWS Fargate Spot lowers the non-critical monthly expense to 164.00 USD, representing a 58% reduction. Core cost drivers remain baseline infrastructure components, while storage, API calls, and data transfers contribute marginally under baseline assumptions. ### [Enable Your SAML Requesting App for Cross App Access](https://yomu.fyi/post/enable-your-saml-requesting-app-for-cross-app-access.md) - Company: [Okta](https://yomu.fyi/company/okta.md) - Author: Alisa Duncan - Published: Jul 17, 2026 Cross App Access allows enterprise applications federated with Security Assertion Markup Language to interact with third-party resource APIs without migrating to OpenID Connect. The flow adapts the Identity Assertion Authorization Grant specification to SAML by adding three token exchange steps following the standard single sign-on handshake. First, the application exchanges the validated SAML assertion for an OAuth refresh token using Okta's token endpoint and a private key JSON Web Token. The application then uses the refresh token to request a short-lived Identity Assertion Authorization Grant token from Okta. Finally, the application presents the Identity Assertion Authorization Grant token to the third-party authorization server to obtain an OAuth access token. ### [Your agent should understand what you see](https://yomu.fyi/post/your-agent-should-understand-what-you-see.md) - Company: [Sentry](https://yomu.fyi/company/sentry.md) - Author: Mihir Mavalankar - Published: Jul 16, 2026 Sentry's Seer Agent initially parsed user screens using DOM-scraped character-by-character ASCII grids, leading to severe token consumption, model context rot, and an inability to support interactive actions. To resolve these bottlenecks, Sentry replaced visual text scraping with a composable semantic context system where React UI components directly declare their state, metadata, and interactive affordances. A root React context provider maintains a registry of component nodes organized hierarchically through higher-order wrappers, serializing the resulting structure to JSON and backend-generated Markdown within the system prompt. Across twenty-four live pages, this approach reduced dashboard context tokens from roughly 5,500 to 1,300 while maintaining identical satisfaction rates and tool-call volumes across more than 14,000 evaluated conversations. [Newer posts](https://yomu.fyi/page/6.md) · [Older posts](https://yomu.fyi/page/8.md)