# AirBnB

Published articles for AirBnB.

This is one page of public article previews, not the complete archive. Follow Next page to continue. Summaries are not the original full articles.

## How Airbnb uses cost per task to operate coding agents on Amazon Bedrock

DevFeed: [How Airbnb uses cost per task to operate coding agents on Amazon Bedrock](<https://devfeed.tech/articles/how-airbnb-uses-cost-per-task-to-operate-coding-agents-on-amazon-bedrock-141280.md>)

Original publisher: [Read original article](<https://aws.amazon.com/blogs/machine-learning/how-airbnb-uses-cost-per-task-to-operate-coding-agents-on-amazon-bedrock/>)

Author: Alan Yao

Published: 2026-11-18T21:48:19Z

Content type: article

Language: en

Sources: [Artificial Intelligence](<https://devfeed.tech/sources/artificial-intelligence.md>)

Topics: [Amazon Bedrock](<https://devfeed.tech/topics/amazon-bedrock.md>), [LLM observability](<https://devfeed.tech/topics/llm-observability.md>), [cloud cost management](<https://devfeed.tech/topics/cloud-cost-management.md>), [Amazon CloudWatch](<https://devfeed.tech/topics/amazon-cloudwatch.md>), [agentic-coding](<https://devfeed.tech/topics/agentic-coding.md>), [AI-assisted coding](<https://devfeed.tech/topics/ai-assisted-coding.md>), [rate-limiting](<https://devfeed.tech/topics/rate-limiting.md>)

Tags: [advanced-300](<https://devfeed.tech/tags/advanced-300.md>), [airbnb](<https://devfeed.tech/tags/airbnb.md>), [amazon-bedrock](<https://devfeed.tech/tags/amazon-bedrock.md>), [coding-agents](<https://devfeed.tech/tags/coding-agents.md>), [cost](<https://devfeed.tech/tags/cost.md>), [customer-solutions](<https://devfeed.tech/tags/customer-solutions.md>), [evals](<https://devfeed.tech/tags/evals.md>), [how-to](<https://devfeed.tech/tags/how-to.md>), [latency](<https://devfeed.tech/tags/latency.md>), [model-selection](<https://devfeed.tech/tags/model-selection.md>), [observability](<https://devfeed.tech/tags/observability.md>), [production](<https://devfeed.tech/tags/production.md>), [quotas](<https://devfeed.tech/tags/quotas.md>), [spending](<https://devfeed.tech/tags/spending.md>), [tasks](<https://devfeed.tech/tags/tasks.md>)

### AI overview

Airbnb combines task-based evaluations with Amazon Bedrock production metrics to select and revisit coding-agent models. It scores models and reasoning-effort settings on representative engineering tasks, pricing all uncached input, cache reads, cache writes, and output tokens across a task; these results guide defaults and effort ceilings. Production can diverge: one model scored better at similar eval cost, but its users later spent several times more because requests cost about three times as much and users sent about three times as many requests. A newer model later scored higher at roughly one sixth the task cost, and heavy users' spend fell to about a seventh with similar request volume. For operations, Airbnb tracks latency, token counts, derived output speed, throttles, and estimated quota usage. Quota admission reserves uncached input, cache writes, and max_tokens, so lowering an oversized max_tokens can improve admission headroom without changing final quota consumption for unchanged output. Gateway records, IAM tags, inference profiles, and invocation logs support aggregate spend attribution; logs require access controls and retention settings.

### Source excerpt

Airbnb runs evals on real engineering tasks and uses Amazon Bedrock observability to choose models for its coding agents and control production costs. This post shows how cost per task guides model selection, why production spending can differ from eval results, and how to monitor latency, manage quotas, and attribute spend.

## De-identifying text at scale: How Airbnb protects personal data in AI training

DevFeed: [De-identifying text at scale: How Airbnb protects personal data in AI training](<https://devfeed.tech/articles/de-identifying-text-at-scale-how-airbnb-protects-personal-data-in-ai-training-141090.md>)

Original publisher: [Read original article](<https://airbnb.tech/infrastructure/de-identifying-text-at-scale-how-airbnb-protects-personal-data-in-ai-training/>)

Author: natalijafijacko

Published: 2026-11-18T16:33:01Z

Content type: article

Language: en

Sources: [Airbnb Engineering & Data Science](<https://devfeed.tech/sources/airbnb-engineering-data-science.md>)

Topics: [managing large-scale text data in AI](<https://devfeed.tech/topics/managing-large-scale-text-data-in-ai.md>), [data loss prevention](<https://devfeed.tech/topics/data-loss-prevention.md>), [Data Quality](<https://devfeed.tech/topics/data-quality.md>), [ner](<https://devfeed.tech/topics/ner.md>), [ML model versioning](<https://devfeed.tech/topics/ml-model-versioning.md>)

Tags: [ai](<https://devfeed.tech/tags/ai.md>), [ai-training](<https://devfeed.tech/tags/ai-training.md>), [airbnb](<https://devfeed.tech/tags/airbnb.md>), [data](<https://devfeed.tech/tags/data.md>), [engineering](<https://devfeed.tech/tags/engineering.md>), [infrastructure](<https://devfeed.tech/tags/infrastructure.md>), [machine-learning](<https://devfeed.tech/tags/machine-learning.md>), [personal](<https://devfeed.tech/tags/personal.md>), [personal-data](<https://devfeed.tech/tags/personal-data.md>), [scale](<https://devfeed.tech/tags/scale.md>), [technology](<https://devfeed.tech/tags/technology.md>), [text](<https://devfeed.tech/tags/text.md>), [training](<https://devfeed.tech/tags/training.md>)

### AI overview

Airbnb describes an in-process text de-identification library built on Presidio to remove personal data before ML training. Teams provide data schemas; Airbnb supplies recognizers, operators, language handling and runtime configuration, while dataset tags and recorded versions/configurations support production gating and traceability. Detection and replacement are separate stages: Airbnb adds phrase-aware context for identifiers such as listing IDs and gift cards, and uses GLiNER for person and street-address detection where spaCy's broad location tags were insufficient. Replacement usually uses realistic Faker values; run-specific secrets make outputs consistent within a run but different across runs, without storing a real-to-fake mapping. Other data receives tailored handling, including salted hashes, coordinate truncation and format-preserving encryption for internal IDs. Detection thresholds and replacement methods vary by use case. Quality is measured by entity and language for recall, precision and throughput, with recall favored for privacy; benchmark comparisons gate model and library changes against regressions. The account covers text deployment and says work on other-媒体

### Source excerpt

Here's how Airbnb detects and replaces personal data in messages, reviews, and support chats before it reaches a model.

## De-identifying text at scale: How Airbnb protects personal data in AI training

DevFeed: [De-identifying text at scale: How Airbnb protects personal data in AI training](<https://devfeed.tech/articles/de-identifying-text-at-scale-how-airbnb-protects-personal-data-in-ai-training-138584.md>)

Original publisher: [Read original article](<https://medium.com/airbnb-engineering/de-identifying-text-at-scale-how-airbnb-protects-personal-data-in-ai-training-32f3ff8ff7d0?source=rss----53c7c27702d5---4>)

Author: Alexandr Climov

Published: 2026-11-17T18:01:03Z

Content type: article

Language: en

Sources: [Airbnb](<https://devfeed.tech/sources/the-airbnb-tech-blog-medium.md>)

Topics: [pii](<https://devfeed.tech/topics/pii.md>), [privacy-filter](<https://devfeed.tech/topics/privacy-filter.md>), [managing large-scale text data in AI](<https://devfeed.tech/topics/managing-large-scale-text-data-in-ai.md>), [Data Quality](<https://devfeed.tech/topics/data-quality.md>), [Machine learning](<https://devfeed.tech/topics/machine-learning.md>), [AI Integration Strategies](<https://devfeed.tech/topics/ai-integration-strategies.md>), [AI Infrastructure](<https://devfeed.tech/topics/ai-infrastructure.md>)

Tags: [ai](<https://devfeed.tech/tags/ai.md>), [ai-training](<https://devfeed.tech/tags/ai-training.md>), [airbnb](<https://devfeed.tech/tags/airbnb.md>), [data](<https://devfeed.tech/tags/data.md>), [de-identification](<https://devfeed.tech/tags/de-identification.md>), [engineering](<https://devfeed.tech/tags/engineering.md>), [extensibility](<https://devfeed.tech/tags/extensibility.md>), [hosting](<https://devfeed.tech/tags/hosting.md>), [infrastructure](<https://devfeed.tech/tags/infrastructure.md>), [machine-learning](<https://devfeed.tech/tags/machine-learning.md>), [messages](<https://devfeed.tech/tags/messages.md>), [modularity](<https://devfeed.tech/tags/modularity.md>), [open-source](<https://devfeed.tech/tags/open-source.md>), [personal-data](<https://devfeed.tech/tags/personal-data.md>), [pii](<https://devfeed.tech/tags/pii.md>), [presidio](<https://devfeed.tech/tags/presidio.md>), [privacy](<https://devfeed.tech/tags/privacy.md>), [reviews](<https://devfeed.tech/tags/reviews.md>), [support](<https://devfeed.tech/tags/support.md>), [technology](<https://devfeed.tech/tags/technology.md>), [text](<https://devfeed.tech/tags/text.md>), [training](<https://devfeed.tech/tags/training.md>)

### AI overview

Airbnb de-identifies text used for model training with an on-premises Presidio library integrated into its shared ML workflow. The Analyzer detects and labels PII; the Anonymizer resolves overlapping spans and replaces them. Airbnb added phrase-based context matching for company-specific identifiers and uses GLiNER for PERSON and LOCATION because spaCy's broad location tags did not reliably capture full street addresses in its benchmark. Detection thresholds and entity scope vary by consumer. Most text PII receives plausible Faker-generated replacements; per-run secret seeding keeps repeated values consistent within a run while changing fakes across runs, without storing a real-to-fake map. Structured data uses salted hashes for identifiers, truncated coordinates, and format-preserving encryption for internal IDs. Benchmarks report recall, precision, and throughput by entity type and language; releases must avoid regressions. The library's protection depends on pipelines using a current version and compliant configuration, and new languages require labeled data for evaluation.

### Source excerpt

Here's how Airbnb detects and replaces personal data in messages, reviews, and support chats before it reaches a model. By: Emelin Flores, Alex Klimov, Lee Formyduval, Bahador Nooraei Introduction Airbnb is built on trust. Every night that a guest books a stay, or a host welcomes someone into their home, that trust is backed by information they've shared with us, which includes personally identifiable information (PII) such as names, home location, current location, and payment details. We now use transaction information to train machine learning models. Before we do so, we remove PII to minimize the number of copies of this information and prevent leakage into and through our models. As we've written before, Airbnb maintains a shared taxonomy as to what constitutes PII, from commonly used fields such as names and card numbers to less frequently used fields such as precise location coordinates. We use de-identification to remove PII and replace it with simulated data that's as realistic as possible to maximize its usefulness for ML model training. Decisions relating to user privacy start as policy. These policies are set and maintained by Airbnb's Privacy Architecture team, with engagement from Legal, Policy, and Engineering. Engineering then implements policy decisions as code. This post focuses on text de-identification. We'll describe the OSS library we chose to start with, the changes we made to create a functional system for Airbnb, and how we confirm that the system is working. 1. Choosing Presidio as the foundation Many organizations are concerned with protecting PII, so there's a lot of existing best practice and tested code out there that we can use. We chose Presidio, an open-source library originally developed by Microsoft and recently transitioned to community governance. We needed to meet demanding requirements: On-premises hosting, to keep data on our infrastructure General-purpose functionality and high degree of modularity, for maximum extensibility

## Airbnb Introduces CASTLE for Training Natural Language Search Models with Synthetic Data

DevFeed: [Airbnb Introduces CASTLE for Training Natural Language Search Models with Synthetic Data](<https://devfeed.tech/articles/airbnb-introduces-castle-for-training-natural-language-search-models-with-synthetic-data-135326.md>)

Original publisher: [Read original article](<https://www.infoq.com/news/2026/11/airbnb-castle/>)

Author: Robert Krzaczyński

Published: 2026-11-16T12:25:00Z

Content type: news

Language: en

Sources: [InfoQ](<https://devfeed.tech/sources/infoq.md>)

Topics: [Large Language Model](<https://devfeed.tech/topics/llm.md>), [distilabel](<https://devfeed.tech/topics/distilabel.md>), [search-engines](<https://devfeed.tech/topics/search-engines.md>), [Advanced AI workflows](<https://devfeed.tech/topics/advanced-ai-workflows.md>), [Artificial Intelligence](<https://devfeed.tech/topics/ai.md>)

Tags: [ai](<https://devfeed.tech/tags/ai.md>), [ai-ml-data-engineering](<https://devfeed.tech/tags/ai-ml-data-engineering.md>), [airbnb](<https://devfeed.tech/tags/airbnb.md>), [airbnb-castle](<https://devfeed.tech/tags/airbnb-castle.md>), [cold-start](<https://devfeed.tech/tags/cold-start.md>), [data](<https://devfeed.tech/tags/data.md>), [framework](<https://devfeed.tech/tags/framework.md>), [large-language-models](<https://devfeed.tech/tags/large-language-models.md>), [large-language-models-llms](<https://devfeed.tech/tags/large-language-models-llms.md>), [ml-data-engineering](<https://devfeed.tech/tags/ml-data-engineering.md>), [natural-language](<https://devfeed.tech/tags/natural-language.md>), [natural-language-processing](<https://devfeed.tech/tags/natural-language-processing.md>), [news](<https://devfeed.tech/tags/news.md>), [queries](<https://devfeed.tech/tags/queries.md>), [relevance](<https://devfeed.tech/tags/relevance.md>), [search](<https://devfeed.tech/tags/search.md>), [search-traffic](<https://devfeed.tech/tags/search-traffic.md>), [synthetic-data](<https://devfeed.tech/tags/synthetic-data.md>), [training](<https://devfeed.tech/tags/training.md>)

### AI overview

CASTLE trains natural language search models by turning de-identified booking sessions into contrastive listing pairs: the booked property is positive, a viewed but unbooked property is negative, and an LLM generates a query that distinguishes them. This embeds relevance labels in query construction, unlike InPars and Promptagator's separate query-generation and labeling steps. CASTLE combines template prompts, few-shot prompts based on about 500 research seed queries, attribute-grounded prompts, and query variation. For pairs lacking booking history, its Virtual Judge labels additional query-listing pairs; CASTLE-R is intended for production settings with emerging search traffic. In the reported evaluation, query-distribution KL divergence was 1.01 versus 9.33 for Promptagator, and attribute-level divergence was 0.08 versus 0.09 for manually curated survey queries. Three experts agreed with relevance assignments 91-93% of the time across 200 triplets. The team says it evaluated on untouched real queries and used leakage guardrails, but did not report a controlled comparison of random splits against stricter splits disjoint in seed templates and listing IDs.

### Source excerpt

Airbnb researchers have introduced CASTLE, a framework designed to address the cold-start problem in natural language search. The approach uses de-identified booking sessions and large language models (LLMs) to jointly generate synthetic search queries and relevance labels, enabling model training before sufficient real search traffic is available. By Robert Krzaczyński

## LinkedIn Replaces Argo CD with a Custom GitOps Engine for Kubernetes Deployments

DevFeed: [LinkedIn Replaces Argo CD with a Custom GitOps Engine for Kubernetes Deployments](<https://devfeed.tech/articles/linkedin-replaces-argo-cd-with-a-custom-gitops-engine-for-kubernetes-deployments-130046.md>)

Original publisher: [Read original article](<https://www.infoq.com/news/2026/11/kubernetes-argocd-linkedin/>)

Author: Claudio Masolo

Published: 2026-11-12T09:00:00Z

Content type: news

Language: en

Sources: [InfoQ](<https://devfeed.tech/sources/infoq.md>)

Topics: [GitOps](<https://devfeed.tech/topics/gitops.md>), [Argo CD](<https://devfeed.tech/topics/argo-cd.md>), [Deployment Strategies](<https://devfeed.tech/topics/deployment-strategies.md>), [flux](<https://devfeed.tech/topics/flux.md>)

Tags: [ai](<https://devfeed.tech/tags/ai.md>), [ai-workloads](<https://devfeed.tech/tags/ai-workloads.md>), [airbnb](<https://devfeed.tech/tags/airbnb.md>), [api](<https://devfeed.tech/tags/api.md>), [api-server](<https://devfeed.tech/tags/api-server.md>), [argo-cd](<https://devfeed.tech/tags/argo-cd.md>), [cache](<https://devfeed.tech/tags/cache.md>), [churn](<https://devfeed.tech/tags/churn.md>), [cluster](<https://devfeed.tech/tags/cluster.md>), [clusters](<https://devfeed.tech/tags/clusters.md>), [continuous-deployment](<https://devfeed.tech/tags/continuous-deployment.md>), [controller](<https://devfeed.tech/tags/controller.md>), [convergence](<https://devfeed.tech/tags/convergence.md>), [crd](<https://devfeed.tech/tags/crd.md>), [deployments](<https://devfeed.tech/tags/deployments.md>), [devops](<https://devfeed.tech/tags/devops.md>), [diversity](<https://devfeed.tech/tags/diversity.md>), [engine](<https://devfeed.tech/tags/engine.md>), [gitops](<https://devfeed.tech/tags/gitops.md>), [kubernetes](<https://devfeed.tech/tags/kubernetes.md>), [kubernetes-argocd-linkedin](<https://devfeed.tech/tags/kubernetes-argocd-linkedin.md>), [kubernetes-clusters](<https://devfeed.tech/tags/kubernetes-clusters.md>), [linkedin](<https://devfeed.tech/tags/linkedin.md>), [news](<https://devfeed.tech/tags/news.md>)

### AI overview

LinkedIn replaced Argo CD for application deployments with an internal GitOps engine that runs each deployment in an isolated, ephemeral pod, uses full-object PUTs, retries resource-version conflicts, and checks drift with a three-way diff. The system supports 4,000+ services across 250+ Kubernetes clusters and handles over 100,000 deployments weekly. In a year-over-year comparison, deployment-system failures fell from 925 to 63 as deployment volume rose 3.7x, and median detection and resolution time fell from 16.1 to 2.45 minutes. LinkedIn cautions that improvements also reflect better orchestrator reliability and error classification; successful-deployment median duration stayed similar, while mean and tail improved. Argo CD remains in use for add-ons and system services, and the internal engine has no stated open-source release. Unlike LinkedIn's per-deployment pods, Uber uses a long-running controller per deployment; Airbnb's kube-gen tooling applies or replaces objects and treats a rollout container restarting for 30 seconds as failure. The comparison excludes drift errors and uses May 2026 as the first clean post-migration month.

### Source excerpt

In a recent post, LinkedIn revealed it has replaced Argo CD with its own GitOps engine. This new system deploys applications across over 250 Kubernetes clusters. It supports more than 4,000 services and manages over 100,000 deployments each week. By Claudio Masolo

## Uber, DoorDash, and Airbnb reveal how few people are actually using AI agents

DevFeed: [Uber, DoorDash, and Airbnb reveal how few people are actually using AI agents](<https://devfeed.tech/articles/uber-doordash-and-airbnb-reveal-how-few-people-are-actually-using-ai-agents-128985.md>)

Original publisher: [Read original article](<https://www.techspot.com/news/114516-uber-doordash-airbnb-reveal-how-few-people-actually.html>)

Author: Rob Thubron

Published: 2026-11-11T10:20:00Z

Content type: news

Language: en

Sources: [TechSpot](<https://devfeed.tech/sources/techspot.md>)

Topics: [AI Bots](<https://devfeed.tech/topics/ai-bots.md>), [Artificial Intelligence](<https://devfeed.tech/topics/ai.md>)

Tags: [ai](<https://devfeed.tech/tags/ai.md>), [ai-agent](<https://devfeed.tech/tags/ai-agent.md>), [ai-agents](<https://devfeed.tech/tags/ai-agents.md>), [airbnb](<https://devfeed.tech/tags/airbnb.md>), [doordash](<https://devfeed.tech/tags/doordash.md>), [meta](<https://devfeed.tech/tags/meta.md>), [muse](<https://devfeed.tech/tags/muse.md>), [openai](<https://devfeed.tech/tags/openai.md>), [the-web](<https://devfeed.tech/tags/the-web.md>), [uber](<https://devfeed.tech/tags/uber.md>)

### AI overview

AI agents account for very few transactions on Uber, DoorDash, and Airbnb, according to figures cited by their executives. During Halloween week, Uber recorded four agent-placed rides and 500 Uber Eats orders, against about 320 million total trips and orders. DoorDash reported several hundred agent-generated orders since agents became available, compared with billions of orders globally each year; Airbnb said agent bookings were negligible against nearly half a million daily bookings. The executives suggested that quick existing booking flows and travelers' preference to research and choose for themselves limit demand. The excerpt also cites concerns about agents acting improperly, including one that exploited a booking platform's API to move a user ahead of someone on a gym class waitlist.

### Source excerpt

Uber, DoorDash, and Airbnb have all said that AI agents are responsible for only hundreds of transactions on their platforms, a tiny fraction compared to the millions completed by real people daily. Read Entire Article

## The Codebase Rewrite is Back

DevFeed: [The Codebase Rewrite is Back](<https://devfeed.tech/articles/the-codebase-rewrite-is-back-129056.md>)

Original publisher: [Read original article](<https://read.engineerscodex.com/p/the-codebase-rewrite-is-back>)

Author: Engineer's Codex

Published: 2026-11-10T19:00:17Z

Content type: opinion

Language: en

Sources: [Engineer's Codex](<https://devfeed.tech/sources/engineer-s-codex.md>)

Topics: [Software Engineering](<https://devfeed.tech/topics/software-engineering.md>), [Legacy Modernization](<https://devfeed.tech/topics/legacy-modernization.md>), [Test automation](<https://devfeed.tech/topics/test-automation.md>), [performance-engineering](<https://devfeed.tech/topics/performance-engineering.md>), [human review](<https://devfeed.tech/topics/human-review.md>), [Developer experience](<https://devfeed.tech/topics/developer-experience.md>), [progressive delivery](<https://devfeed.tech/topics/progressive-delivery.md>), [bugfixes](<https://devfeed.tech/topics/bugfixes.md>), [CI/CD](<https://devfeed.tech/topics/cicd.md>), [Tech Debt](<https://devfeed.tech/topics/tech-debt.md>), [engineering-culture](<https://devfeed.tech/topics/engineering-culture.md>), [Claude Code](<https://devfeed.tech/topics/claude-code.md>)

Tags: [acceptance](<https://devfeed.tech/tags/acceptance.md>), [agent](<https://devfeed.tech/tags/agent.md>), [agents](<https://devfeed.tech/tags/agents.md>), [ai](<https://devfeed.tech/tags/ai.md>), [ai-assisted](<https://devfeed.tech/tags/ai-assisted.md>), [ai-assisted-workflows](<https://devfeed.tech/tags/ai-assisted-workflows.md>), [airbnb](<https://devfeed.tech/tags/airbnb.md>), [api](<https://devfeed.tech/tags/api.md>), [app](<https://devfeed.tech/tags/app.md>), [application](<https://devfeed.tech/tags/application.md>), [apps](<https://devfeed.tech/tags/apps.md>), [architectures](<https://devfeed.tech/tags/architectures.md>), [asana](<https://devfeed.tech/tags/asana.md>), [automated](<https://devfeed.tech/tags/automated.md>), [autonomous](<https://devfeed.tech/tags/autonomous.md>), [economics](<https://devfeed.tech/tags/economics.md>), [engineering](<https://devfeed.tech/tags/engineering.md>), [rewrite](<https://devfeed.tech/tags/rewrite.md>), [software](<https://devfeed.tech/tags/software.md>), [software-engineering](<https://devfeed.tech/tags/software-engineering.md>)

### AI overview

AI coding agents have made some rewrites and long-deferred engineering work cheaper, shifting the cost-benefit calculation. The excerpt cites GitHub's TypeScript-to-Rust runtime port, Shopify's React Native-to-Swift/Kotlin rebuild, Bun's Zig-to-Rust rewrite, and X's web rewrite, with reported speed, memory, stability, or performance gains. These projects used different approaches: GitHub migrated component by component through pull requests and frequent releases, while Bun used dozens of parallel agents. The evidence also shows limits: agents miss hidden behavior, Bun reported 19 regressions, and a benchmark found only 5.4% of whole-repository migration runs passed all stages. Uber's JUnit migration succeeded with deterministic codemods where generative AI did not. The article recommends revisiting backlogs, batching small fixes, prototyping migration slices, and investing in behavioral tests, evals, benchmarks, observability, canaries, and rollback. Rewrites remain risky when specifications and verification are weak.

### Source excerpt

The economics of software engineering have fundamentally changed.

## Skipper, Airbnb's embedded workflow engine, is now open source

DevFeed: [Skipper, Airbnb's embedded workflow engine, is now open source](<https://devfeed.tech/articles/skipper-airbnb-s-embedded-workflow-engine-is-now-open-source-129354.md>)

Original publisher: [Read original article](<https://airbnb.tech/open-source/skipper-airbnbs-embedded-workflow-engine-is-now-open-source/>)

Author: natalijafijacko

Published: 2026-11-10T18:08:34Z

Content type: article

Language: en

Sources: [Airbnb Engineering & Data Science](<https://devfeed.tech/sources/airbnb-engineering-data-science.md>)

Topics: [Orchestration](<https://devfeed.tech/topics/orchestration.md>), [workflow automation](<https://devfeed.tech/topics/workflow-automation.md>), [Open Source](<https://devfeed.tech/topics/open-source.md>)

Tags: [actions](<https://devfeed.tech/tags/actions.md>), [adapters](<https://devfeed.tech/tags/adapters.md>), [airbnb](<https://devfeed.tech/tags/airbnb.md>), [durable-workflows](<https://devfeed.tech/tags/durable-workflows.md>), [embedded](<https://devfeed.tech/tags/embedded.md>), [engine](<https://devfeed.tech/tags/engine.md>), [engineering](<https://devfeed.tech/tags/engineering.md>), [open](<https://devfeed.tech/tags/open.md>), [open-source](<https://devfeed.tech/tags/open-source.md>), [orchestration](<https://devfeed.tech/tags/orchestration.md>), [service](<https://devfeed.tech/tags/service.md>), [skipper](<https://devfeed.tech/tags/skipper.md>), [software-architecture](<https://devfeed.tech/tags/software-architecture.md>), [source](<https://devfeed.tech/tags/source.md>), [technology](<https://devfeed.tech/tags/technology.md>), [workflow](<https://devfeed.tech/tags/workflow.md>), [workflow-engine](<https://devfeed.tech/tags/workflow-engine.md>), [workflows](<https://devfeed.tech/tags/workflows.md>)

### AI overview

Skipper is an Apache 2.0 Java/Kotlin workflow engine that runs inside a service, persisting workflow state and scheduled work in a shared database rather than requiring a separate orchestration cluster. Replicas run its runtime and scheduler, which coordinate through leases and can recover work after a replica fails; the service team owns execution, database capacity, and recovery operations. Workflows are replayed from the top using saved action checkpoints, so orchestration must be deterministic and actions must make side effects idempotent. Batched checkpoints reduce database writes but can cause completed actions to run again after a crash; even immediate checkpoints cannot make downstream effects atomic. Retries, signals, waits, compensation, and workflow tests are supported, while permanent failures or exhausted recovery attempts may need handling or manual intervention. The release includes MySQL and SQLite adapters, an admin UI, test utilities, and a Kotlin state-machine DSL; additional storage plugins are described as future work.

### Source excerpt

Durable workflows, running inside your service with no separate orchestration cluster.

## Skipper, Airbnb's embedded workflow engine, is now open source

DevFeed: [Skipper, Airbnb's embedded workflow engine, is now open source](<https://devfeed.tech/articles/skipper-airbnb-s-embedded-workflow-engine-is-now-open-source-127298.md>)

Original publisher: [Read original article](<https://medium.com/airbnb-engineering/skipper-airbnbs-embedded-workflow-engine-is-now-open-source-78dd354f472b?source=rss----53c7c27702d5---4>)

Author: Andriy Sergiyenko

Published: 2026-11-10T18:01:02Z

Content type: article

Language: en

Sources: [Airbnb](<https://devfeed.tech/sources/the-airbnb-tech-blog-medium.md>)

Topics: [workflow automation](<https://devfeed.tech/topics/workflow-automation.md>), [Open Source](<https://devfeed.tech/topics/open-source.md>), [Flowable](<https://devfeed.tech/topics/flowable.md>)

Tags: [airbnb](<https://devfeed.tech/tags/airbnb.md>), [apache](<https://devfeed.tech/tags/apache.md>), [apache-2-0](<https://devfeed.tech/tags/apache-2-0.md>), [architecture](<https://devfeed.tech/tags/architecture.md>), [asynchronous](<https://devfeed.tech/tags/asynchronous.md>), [business-processes](<https://devfeed.tech/tags/business-processes.md>), [classes](<https://devfeed.tech/tags/classes.md>), [crashes](<https://devfeed.tech/tags/crashes.md>), [database](<https://devfeed.tech/tags/database.md>), [debugging](<https://devfeed.tech/tags/debugging.md>), [dependencies](<https://devfeed.tech/tags/dependencies.md>), [dependency](<https://devfeed.tech/tags/dependency.md>), [deployment](<https://devfeed.tech/tags/deployment.md>), [documentation](<https://devfeed.tech/tags/documentation.md>), [embedded](<https://devfeed.tech/tags/embedded.md>), [engine](<https://devfeed.tech/tags/engine.md>), [engineering](<https://devfeed.tech/tags/engineering.md>), [open-source](<https://devfeed.tech/tags/open-source.md>), [skipper](<https://devfeed.tech/tags/skipper.md>), [software-architecture](<https://devfeed.tech/tags/software-architecture.md>), [technology](<https://devfeed.tech/tags/technology.md>), [workflow](<https://devfeed.tech/tags/workflow.md>), [workflow-engine](<https://devfeed.tech/tags/workflow-engine.md>)

### AI overview

Skipper is an open-source Java/Kotlin workflow engine that runs in a service's own replicas and uses its existing database, avoiding a separate orchestration tier between workflow steps. A shared database stores state and scheduled work; replicas poll for tasks and use leases so another replica can recover work after a failure. This suits teams that want durable workflows inside their existing deployment, but they take responsibility for execution, database capacity, and recovery. Workflows replay from the beginning, reusing persisted action results, so orchestration code must be deterministic; actions should make side effects idempotent because effects and checkpoints are not atomic and may run at least once. Checkpoints are normally batched, reducing database writes but allowing completed actions to run again after a crash before persistence. The Apache 2.0 release includes MySQL and SQLite adapters, test utilities, an admin UI, and a Kotlin state machine DSL.

### Source excerpt

Durable workflows, running inside your service with no separate orchestration cluster. By: Ricardo Gamba, Andriy Sergiyenko Skipper, an embedded workflow engine used in production by teams all across Airbnb, is now available to the open source community. Skipper lets you express multi-step business processes as Java or Kotlin classes, persist their progress, and recover from crashes and transient failures. It runs inside your service and reuses its existing dependencies. Skipper is available under the Apache 2.0 license. The code is on GitHub, alongside documentation and runnable examples. Our earlier engineering deep dive explains how we built it. Here, we'll focus on the architecture of Skipper and where it fits in the ecosystem of options for development around workflows. Why we developed Skipper A process that spans multiple services, waits for human input, or involves a mix of synchronous and asynchronous steps, needs persistent storage for recording its progress. When a server restarts, it must know what has already happened, what (if anything) should be retried, and what is still awaiting processing. Implementing this separately for each process would mean repeatedly solving the same problems around partial failure, timers, and recovery, with associated testing and debugging; using a proven library is likely to improve quality and reduce toil. Existing workflow engines meet these challenges. A common approach relies on a central orchestration service, whether self-hosted or fully managed, to handle durable execution. This setup provides a unified platform for multiple teams, streamlining central operations and monitoring. For Airbnb, we wanted a new approach, one in which each service owned its workflows within its existing deployment and database. For critical services, that meant avoiding an additional shared orchestration dependency. It also let workflow execution stay in-process, without a separate coordinator between steps. That requirement shaped Skippe

## Customer support is the gnarliest AI problem

DevFeed: [Customer support is the gnarliest AI problem](<https://devfeed.tech/articles/customer-support-is-the-gnarliest-ai-problem-127396.md>)

Original publisher: [Read original article](<https://stackoverflow.blog/2026/11/10/customer-support-is-the-gnarliest-ai-problem/>)

Author: Phoebe Sajor

Published: 2026-11-10T08:40:00Z

Content type: article

Language: en

Sources: [Stack Overflow](<https://devfeed.tech/sources/stack-overflow-blog.md>)

Topics: [AI for customer service automation](<https://devfeed.tech/topics/ai-for-customer-service-automation.md>), [AI tools for developers](<https://devfeed.tech/topics/ai-tools-for-developers.md>), [Software Engineering](<https://devfeed.tech/topics/software-engineering.md>), [engineering-leadership](<https://devfeed.tech/topics/engineering-leadership.md>)

Tags: [agentic-ai](<https://devfeed.tech/tags/agentic-ai.md>), [agents](<https://devfeed.tech/tags/agents.md>), [ahmad-al-dahle](<https://devfeed.tech/tags/ahmad-al-dahle.md>), [ai](<https://devfeed.tech/tags/ai.md>), [ai-coding-tools](<https://devfeed.tech/tags/ai-coding-tools.md>), [airbnb](<https://devfeed.tech/tags/airbnb.md>), [balance](<https://devfeed.tech/tags/balance.md>), [blog](<https://devfeed.tech/tags/blog.md>), [cto](<https://devfeed.tech/tags/cto.md>), [customer-support](<https://devfeed.tech/tags/customer-support.md>), [engineering](<https://devfeed.tech/tags/engineering.md>), [engineers](<https://devfeed.tech/tags/engineers.md>), [evaluations](<https://devfeed.tech/tags/evaluations.md>), [generative](<https://devfeed.tech/tags/generative.md>), [generative-ai](<https://devfeed.tech/tags/generative-ai.md>), [implement](<https://devfeed.tech/tags/implement.md>), [latency](<https://devfeed.tech/tags/latency.md>), [podcast](<https://devfeed.tech/tags/podcast.md>), [se-stackoverflow](<https://devfeed.tech/tags/se-stackoverflow.md>), [se-tech](<https://devfeed.tech/tags/se-tech.md>), [software](<https://devfeed.tech/tags/software.md>), [software-engineering](<https://devfeed.tech/tags/software-engineering.md>), [teams](<https://devfeed.tech/tags/teams.md>), [tools](<https://devfeed.tech/tags/tools.md>)

### AI overview

Airbnb CTO Ahmad Al-Dahle describes customer support as a particularly difficult AI problem and discusses deploying multi-party AI agents to address it. He explains how evolving, rigorous evaluations help engineers balance response latency with accuracy, and argues that AI coding tools require software teams to exercise greater judgment. The supplied text gives no further details about the agents, evaluations, or engineering practices.

### Source excerpt

Ryan chats with Ahmad Al-Dahle, CTO at Airbnb, about deploying multi-party AI agents to tackle the uniquely gnarly problem of customer support, how a moving target of rigorous evaluations helps engineers balance latency against accuracy, and the ways in which AI coding tools demand an even higher level of judgment from software engineering teams.

## Airbnb says it's launching an AI travel agent in the first half of 2027

DevFeed: [Airbnb says it's launching an AI travel agent in the first half of 2027](<https://devfeed.tech/articles/airbnb-says-it-s-launching-an-ai-travel-agent-in-the-first-half-of-2027-119635.md>)

Original publisher: [Read original article](<https://techcrunch.com/2026/11/05/airbnb-says-its-launching-an-ai-travel-agent-in-the-first-half-of-2027/>)

Author: Sarah Perez

Published: 2026-11-05T22:40:55Z

Content type: news

Language: en

Sources: [TechCrunch | AI News & Artificial Intelligence](<https://devfeed.tech/sources/techcrunch-ai-news-artificial-intelligence.md>)

Topics: [AI Agent](<https://devfeed.tech/topics/ai-agent.md>), [a2ui](<https://devfeed.tech/topics/a2ui.md>)

Tags: [2026](<https://devfeed.tech/tags/2026.md>), [2027](<https://devfeed.tech/tags/2027.md>), [about](<https://devfeed.tech/tags/about.md>), [added](<https://devfeed.tech/tags/added.md>), [agent](<https://devfeed.tech/tags/agent.md>), [agents](<https://devfeed.tech/tags/agents.md>), [ai](<https://devfeed.tech/tags/ai.md>), [ai-agent](<https://devfeed.tech/tags/ai-agent.md>), [ai-agents](<https://devfeed.tech/tags/ai-agents.md>), [ai-chatbot](<https://devfeed.tech/tags/ai-chatbot.md>), [ai-native](<https://devfeed.tech/tags/ai-native.md>), [airbnb](<https://devfeed.tech/tags/airbnb.md>), [also](<https://devfeed.tech/tags/also.md>), [commerce](<https://devfeed.tech/tags/commerce.md>), [compare](<https://devfeed.tech/tags/compare.md>), [first](<https://devfeed.tech/tags/first.md>), [half](<https://devfeed.tech/tags/half.md>), [help](<https://devfeed.tech/tags/help.md>), [it-s](<https://devfeed.tech/tags/it-s.md>), [plan](<https://devfeed.tech/tags/plan.md>), [travel](<https://devfeed.tech/tags/travel.md>)

### AI overview

Airbnb plans to launch its AI travel agent in the first half of 2027. Rather than relying on a text-only chatbot, it will assemble travel-specific interface elements such as maps, photos, comparisons, calendars, and itineraries to support browsing and trip planning. Airbnb says the agent will draw on its booking and hosting experience and help guests during trips with reservation changes, payment issues, refunds, rebooking, and 24-hour safety support--tasks outside agents cannot easily handle independently. The company expects to expand its help over time to services and experiences as well as homes and hotels.

### Source excerpt

Airbnb says its upcoming AI agent will help travelers plan trips, compare options, manage bookings, and get assistance throughout their stay.

## 5 stars for sale: Inside the underground fake review trade

DevFeed: [5 stars for sale: Inside the underground fake review trade](<https://devfeed.tech/articles/5-stars-for-sale-inside-the-underground-fake-review-trade-112882.md>)

Original publisher: [Read original article](<https://www.malwarebytes.com/blog/threat-intel/2026/11/5-stars-for-sale-inside-the-underground-fake-review-trade>)

Author: Malwarebytes Labs

Published: 2026-11-02T14:24:43Z

Content type: news

Language: en

Sources: [Malwarebytes](<https://devfeed.tech/sources/malwarebytes.md>)

Topics: [Threat monitoring](<https://devfeed.tech/topics/threat-monitoring.md>), [sensitive data](<https://devfeed.tech/topics/sensitive-data.md>), [AI Chat](<https://devfeed.tech/topics/ai-chat.md>)

Tags: [adoption](<https://devfeed.tech/tags/adoption.md>), [ai](<https://devfeed.tech/tags/ai.md>), [airbnb](<https://devfeed.tech/tags/airbnb.md>), [automate](<https://devfeed.tech/tags/automate.md>), [behind-the-scenes](<https://devfeed.tech/tags/behind-the-scenes.md>), [boosting](<https://devfeed.tech/tags/boosting.md>), [browser](<https://devfeed.tech/tags/browser.md>), [business](<https://devfeed.tech/tags/business.md>), [challenge](<https://devfeed.tech/tags/challenge.md>), [charges](<https://devfeed.tech/tags/charges.md>), [cybercrime](<https://devfeed.tech/tags/cybercrime.md>), [cybercriminals](<https://devfeed.tech/tags/cybercriminals.md>), [data](<https://devfeed.tech/tags/data.md>), [demand](<https://devfeed.tech/tags/demand.md>), [fake](<https://devfeed.tech/tags/fake.md>), [feedback](<https://devfeed.tech/tags/feedback.md>), [review](<https://devfeed.tech/tags/review.md>), [reviews](<https://devfeed.tech/tags/reviews.md>), [scams](<https://devfeed.tech/tags/scams.md>), [star](<https://devfeed.tech/tags/star.md>), [threat-intel](<https://devfeed.tech/tags/threat-intel.md>), [trade](<https://devfeed.tech/tags/trade.md>)

### AI overview

Underground sellers offer paid fake five-star reviews and removal of negative feedback across platforms including Google, Trustpilot, Yelp, app stores, and Airbnb. One seller claims to use real posters and a private method to keep reviews active; another offers removal for roughly $100-$200 per review, with Airbnb listings around $1,100. The excerpt also describes AI-generated reviews and residential or mobile proxies used to make campaigns appear more consumer-like. These services can hide legitimate complaints as well as fabricated ones. To assess reviews, read recent and middle-rated posts, look for repeated wording or sudden bursts of praise, and check for recurring details about issues such as durability, delivery, or refunds. These patterns are reasons to investigate, not proof a review is fake.

### Source excerpt

Underground sellers offer five-star reviews and charge up to $1,100 to make negative feedback disappear.

## The Pulse: Time to rethink software security because of AI?

DevFeed: [The Pulse: Time to rethink software security because of AI?](<https://devfeed.tech/articles/the-pulse-time-to-rethink-software-security-because-of-ai-109769.md>)

Original publisher: [Read original article](<https://blog.pragmaticengineer.com/the-pulse-time-to-rethink-software-security-because-of-ai/>)

Author: Ivan Klaric

Published: 2026-10-30T16:49:15Z

Content type: news

Language: en

Sources: [The Pragmatic Engineer](<https://devfeed.tech/sources/the-pragmatic-engineer-2.md>)

Topics: [Security](<https://devfeed.tech/topics/security.md>), [Exploit](<https://devfeed.tech/topics/exploit.md>), [code security](<https://devfeed.tech/topics/code-security.md>), [Security research](<https://devfeed.tech/topics/security-research.md>), [Cloud & Application Security](<https://devfeed.tech/topics/cloud-application-security.md>), [Threat monitoring](<https://devfeed.tech/topics/threat-monitoring.md>), [trust](<https://devfeed.tech/topics/trust.md>), [Open Source](<https://devfeed.tech/topics/open-source.md>), [observability](<https://devfeed.tech/topics/observability.md>)

Tags: [2fa](<https://devfeed.tech/tags/2fa.md>), [adversarial](<https://devfeed.tech/tags/adversarial.md>), [adversary](<https://devfeed.tech/tags/adversary.md>), [agents](<https://devfeed.tech/tags/agents.md>), [ai](<https://devfeed.tech/tags/ai.md>), [ai-agents](<https://devfeed.tech/tags/ai-agents.md>), [ai-api](<https://devfeed.tech/tags/ai-api.md>), [ai-api-keys](<https://devfeed.tech/tags/ai-api-keys.md>), [ai-labs](<https://devfeed.tech/tags/ai-labs.md>), [ai-model](<https://devfeed.tech/tags/ai-model.md>), [ai-models](<https://devfeed.tech/tags/ai-models.md>), [ai-native](<https://devfeed.tech/tags/ai-native.md>), [airbnb](<https://devfeed.tech/tags/airbnb.md>), [alerting](<https://devfeed.tech/tags/alerting.md>), [amazon](<https://devfeed.tech/tags/amazon.md>), [breaches](<https://devfeed.tech/tags/breaches.md>), [pulse](<https://devfeed.tech/tags/pulse.md>), [security](<https://devfeed.tech/tags/security.md>), [software](<https://devfeed.tech/tags/software.md>), [software-security](<https://devfeed.tech/tags/software-security.md>)

### AI overview

The incidents point to security failures made more urgent by AI-assisted vulnerability discovery and exploitation. The excerpt details eMudhra's weak intermediate CA keys, PHP flaws exploited within hours of patch release, and Railway's exposed customer secrets; it also notes a TiDB provider breach that went undetected for a month. It argues that defenders should move toward automated patching, ongoing security monitoring, and greater use of AI, while recognizing patching can cause outages and continuous AI monitoring and security staffing raise costs. These recommendations are framed as urgent responses, with no established best practices for defensive AI yet.

### Source excerpt

A month's worth of security breaches in a single day - will things get worse before they improve?

## Leaving, Staying, or Living There? Duration Commonsense Reasoning with Human-LLM Co-annotations

DevFeed: [Leaving, Staying, or Living There? Duration Commonsense Reasoning with Human-LLM Co-annotations](<https://devfeed.tech/articles/leaving-staying-or-living-there-duration-commonsense-reasoning-with-human-llm-co-annotations-108117.md>)

Original publisher: [Read original article](<https://arxiv.org/abs/2610.38755>)

Author: Chenyang Yu, Zhaomin Xiao, Yan Huang, Eduardo Blanco

Published: 2026-10-30T04:00:00Z

Content type: article

Language: en

Sources: [arXiv: Artificial Intelligence](<https://devfeed.tech/sources/arxiv-artificial-intelligence.md>)

Topics: [Artificial Intelligence](<https://devfeed.tech/topics/ai.md>), [llm-reasoning](<https://devfeed.tech/topics/llm-reasoning.md>), [Chain-of-thought](<https://devfeed.tech/topics/chain-of-thought.md>), [human feedback](<https://devfeed.tech/topics/human-feedback.md>), [Large Language Model](<https://devfeed.tech/topics/llm.md>), [Image](<https://devfeed.tech/topics/image.md>), [Natural language processing](<https://devfeed.tech/topics/nlp.md>)

Tags: [abstract](<https://devfeed.tech/tags/abstract.md>), [airbnb](<https://devfeed.tech/tags/airbnb.md>), [annotations](<https://devfeed.tech/tags/annotations.md>), [arxiv](<https://devfeed.tech/tags/arxiv.md>), [backyard](<https://devfeed.tech/tags/backyard.md>), [behavior](<https://devfeed.tech/tags/behavior.md>), [chain-of-thought](<https://devfeed.tech/tags/chain-of-thought.md>), [challenges](<https://devfeed.tech/tags/challenges.md>), [context](<https://devfeed.tech/tags/context.md>), [critical](<https://devfeed.tech/tags/critical.md>), [cs-ai](<https://devfeed.tech/tags/cs-ai.md>), [cs-ir](<https://devfeed.tech/tags/cs-ir.md>), [days](<https://devfeed.tech/tags/days.md>), [details](<https://devfeed.tech/tags/details.md>), [error](<https://devfeed.tech/tags/error.md>), [fail](<https://devfeed.tech/tags/fail.md>), [gardening](<https://devfeed.tech/tags/gardening.md>), [leaving](<https://devfeed.tech/tags/leaving.md>), [llm](<https://devfeed.tech/tags/llm.md>), [reasoning](<https://devfeed.tech/tags/reasoning.md>), [staying](<https://devfeed.tech/tags/staying.md>), [with](<https://devfeed.tech/tags/with.md>)

### AI overview

The study tests whether vision-language models can infer whether someone is leaving, staying temporarily, or living in a place from geotagged tweets, where duration is rarely stated directly. The authors create a human- and LLM-co-annotated corpus for evaluation. They report that state-of-the-art models struggle even with multi-turn Chain-of-Thought prompting: models may miss important context or focus on prominent visual details while overlooking subtle hashtags and semantic nuances. The findings point to unresolved challenges in context-aware multimodal understanding.

### Source excerpt

arXiv:2610.38755v1 Announce Type: new Abstract: Gardening in the backyard implies living there, while checking into an Airbnb more likely means staying for a few days. Such duration judgments are important for understanding human mobility, travel behavior, and social context. However, duration is rarely stated explicitly in social media posts and must instead be inferred from noisy textual, visual, and contextual cues. In this paper, we investigate whether vision-language models possess such duration commonsense. We create a new corpus of geotagged tweets co-annotated by humans and LLMs to serve as a testbed for this task. We find that state-of-the-art models struggle with duration inference, even when guided by multi-turn Chain-of-Thought prompting. Error analyses further reveal that models often fail to integrate critical contextual information, or they overly rely on prominent visual details while overlooking subtle hashtags and semantic nuances. These findings underscore the significant challenges remaining in context-aware multimodal understanding.

## Airbnb Cuts Recommendation Staleness from 2 Days to Seconds with Chronon

DevFeed: [Airbnb Cuts Recommendation Staleness from 2 Days to Seconds with Chronon](<https://devfeed.tech/articles/airbnb-cuts-recommendation-staleness-from-2-days-to-seconds-with-chronon-104516.md>)

Original publisher: [Read original article](<https://www.infoq.com/news/2026/10/airbnb-chronon-recommendation/>)

Author: Leela Kumili

Published: 2026-10-28T13:53:00Z

Content type: news

Language: en

Sources: [InfoQ](<https://devfeed.tech/sources/infoq.md>)

Topics: [streaming data analytics](<https://devfeed.tech/topics/streaming-data-analytics.md>), [feature-store](<https://devfeed.tech/topics/feature-store.md>), [personalization](<https://devfeed.tech/topics/personalization.md>), [data-engineering](<https://devfeed.tech/topics/data-engineering.md>), [Open Source](<https://devfeed.tech/topics/open-source.md>)

Tags: [a-b-testing](<https://devfeed.tech/tags/a-b-testing.md>), [ai](<https://devfeed.tech/tags/ai.md>), [ai-ml-data-engineering](<https://devfeed.tech/tags/ai-ml-data-engineering.md>), [airbnb](<https://devfeed.tech/tags/airbnb.md>), [airbnb-chronon-recommendation](<https://devfeed.tech/tags/airbnb-chronon-recommendation.md>), [allows](<https://devfeed.tech/tags/allows.md>), [architecture](<https://devfeed.tech/tags/architecture.md>), [architecture-design](<https://devfeed.tech/tags/architecture-design.md>), [based](<https://devfeed.tech/tags/based.md>), [batch-processing](<https://devfeed.tech/tags/batch-processing.md>), [days](<https://devfeed.tech/tags/days.md>), [development](<https://devfeed.tech/tags/development.md>), [embedding](<https://devfeed.tech/tags/embedding.md>), [embeddings](<https://devfeed.tech/tags/embeddings.md>), [event-driven-architecture](<https://devfeed.tech/tags/event-driven-architecture.md>), [feature](<https://devfeed.tech/tags/feature.md>), [machine-learning](<https://devfeed.tech/tags/machine-learning.md>), [ml-data-engineering](<https://devfeed.tech/tags/ml-data-engineering.md>), [mlops](<https://devfeed.tech/tags/mlops.md>), [model](<https://devfeed.tech/tags/model.md>), [news](<https://devfeed.tech/tags/news.md>), [offline](<https://devfeed.tech/tags/offline.md>), [online](<https://devfeed.tech/tags/online.md>), [platform](<https://devfeed.tech/tags/platform.md>), [platforms](<https://devfeed.tech/tags/platforms.md>), [real-time](<https://devfeed.tech/tags/real-time.md>), [recommendation](<https://devfeed.tech/tags/recommendation.md>), [sequence](<https://devfeed.tech/tags/sequence.md>), [streaming](<https://devfeed.tech/tags/streaming.md>), [testing](<https://devfeed.tech/tags/testing.md>), [time](<https://devfeed.tech/tags/time.md>), [transformer-models](<https://devfeed.tech/tags/transformer-models.md>), [update](<https://devfeed.tech/tags/update.md>), [with](<https://devfeed.tech/tags/with.md>)

### AI overview

Airbnb added Push Mode and Near Real-Time Model Transform to Chronon so guest activity can trigger streaming inference with its existing JourneyFormer sequence encoder. The system combines updated events with guest history, writes refreshed embeddings to the existing low-latency store, and leaves the ranking path largely unchanged. Typical updates arrive in 10-30 seconds, reducing embedding staleness from nearly two days to under a minute. Airbnb reports a 1.67% offline NDCG improvement and about a 0.33% increase in uncancelled bookings in online A/B testing. The excerpt says this approach trades additional writes and pipeline complexity for fresher predictions; it contrasts Chronon's integrated streaming and model transformation with Feast's documented cached-prediction architecture. The features were contributed to Chronon's public repository.

### Source excerpt

Airbnb extended its Chronon feature platform with Push Mode and Near Real-Time Model Transform to update sequence-based recommendation embeddings within seconds. The architecture reduced embedding staleness from nearly two days to under a minute and improved offline NDCG by 1.67%, while online testing increased uncancelled bookings by approximately one-third of a percent. By Leela Kumili

## Eight reasons human developers are better than coding agents

DevFeed: [Eight reasons human developers are better than coding agents](<https://devfeed.tech/articles/eight-reasons-human-developers-are-better-than-coding-agents-113145.md>)

Original publisher: [Read original article](<https://www.infoworld.com/article/4241333/eight-reasons-human-developers-are-better-than-coding-agents.html>)

Author: Nick Hodges

Published: 2026-10-28T09:00:00Z

Content type: opinion

Language: en

Sources: [InfoWorld](<https://devfeed.tech/sources/infoworld.md>)

Topics: [AI-assisted coding](<https://devfeed.tech/topics/ai-assisted-coding.md>), [agentic-coding](<https://devfeed.tech/topics/agentic-coding.md>), [human in the loop agent](<https://devfeed.tech/topics/human-in-the-loop-agent.md>), [Claude Code](<https://devfeed.tech/topics/claude-code.md>), [cursor](<https://devfeed.tech/topics/cursor.md>)

Tags: [agents](<https://devfeed.tech/tags/agents.md>), [airbnb](<https://devfeed.tech/tags/airbnb.md>), [artificial-intelligence](<https://devfeed.tech/tags/artificial-intelligence.md>), [artificial-intelligence-careers-developer-development-tools-generative-ai-roles-software-devel](<https://devfeed.tech/tags/artificial-intelligence-careers-developer-development-tools-generative-ai-roles-software-devel.md>), [careers](<https://devfeed.tech/tags/careers.md>), [claude-code](<https://devfeed.tech/tags/claude-code.md>), [coding-agents](<https://devfeed.tech/tags/coding-agents.md>), [context](<https://devfeed.tech/tags/context.md>), [cursor](<https://devfeed.tech/tags/cursor.md>), [customer](<https://devfeed.tech/tags/customer.md>), [developer](<https://devfeed.tech/tags/developer.md>), [developers](<https://devfeed.tech/tags/developers.md>), [development-tools](<https://devfeed.tech/tags/development-tools.md>), [generative-ai](<https://devfeed.tech/tags/generative-ai.md>), [human-in-the-loop](<https://devfeed.tech/tags/human-in-the-loop.md>), [language-en](<https://devfeed.tech/tags/language-en.md>), [marketplace](<https://devfeed.tech/tags/marketplace.md>), [pager](<https://devfeed.tech/tags/pager.md>), [process](<https://devfeed.tech/tags/process.md>), [software](<https://devfeed.tech/tags/software.md>), [software-development](<https://devfeed.tech/tags/software-development.md>), [storytype-opinion](<https://devfeed.tech/tags/storytype-opinion.md>), [uber](<https://devfeed.tech/tags/uber.md>)

### AI overview

The author argues that coding agents can produce code better and faster than people, but human judgment remains essential because software work extends beyond coding. Humans bring non-code context, such as leadership preferences and marketing requirements; remain accountable when software fails or projects slip; and can challenge requests, decide what customers need, and identify market opportunities. The excerpt also says agents may act confidently on assumptions without expressing uncertainty, depend on humans to initiate work, and tend toward generic design unless directed otherwise. Since agents follow their instructions, people must judge whether the request and resulting output are right. The author concludes that agents have shifted the development bottleneck rather than removed the need for human involvement.

### Source excerpt

Last week I wrote about how coding agents are better developers than humans. I'll stand by that -- the current agents can write code better, faster, longer, and with far less complaining than we humans can. But that doesn't make humans unnecessary -- quite the contrary. Humans still play a vital role in the process of building software. Here are eight reasons we can use to fend off the robots when they come for our jobs. Only humans can know non-code context Agents are great at keeping the work in mind and holding vastly more context than humans. But what about "This feature is a pet project of the CEO" or "The marketing team insists that the web page look like this"? Those are factors only a human can know and act on. You can try to explain complex human emotions to a coding agent, but it will never really understand the need to please the boss above a technical argument. Only humans can be accountable At the end of the day, there has to be a human in the loop. Customers can't complain to Claude Code about their software not being right. Someone has to be the on-duty developer who "carries the pager" when something goes wrong over the weekend. Your boss isn't going to have a stern conversation with Cursor if the project falls behind schedule. Only humans can say 'No' If you ask a coding agent to build an app where all the text is bright red and blinks at random intervals, it will cheerfully and diligently go off and do just that. It will not push back and say "Hmm. Is that really a good idea?" Only humans can say 'Yes' It takes a human being to decide what to do. You alone can talk to the customer and determine what exactly they need. Only humans can intuit what the marketplace wants and decide to build a crazy new thing like Uber or Airbnb. Only humans can say 'I don't know' Coding agents are skilled and energetic developers, but they can be too energetic, confidently charging off and doing things without stopping when they aren't sure about the destination. They mi

## Eight reasons you are better than coding agents

DevFeed: [Eight reasons you are better than coding agents](<https://devfeed.tech/articles/eight-reasons-you-are-better-than-coding-agents-104244.md>)

Original publisher: [Read original article](<https://www.infoworld.com/article/4241333/eight-reasons-you-are-better-than-coding-agents.html>)

Author: Nick Hodges

Published: 2026-10-28T09:00:00Z

Content type: opinion

Language: en

Sources: [InfoWorld](<https://devfeed.tech/sources/infoworld.md>)

Topics: [AI-assisted coding](<https://devfeed.tech/topics/ai-assisted-coding.md>), [human in the loop agent](<https://devfeed.tech/topics/human-in-the-loop-agent.md>), [Claude Code](<https://devfeed.tech/topics/claude-code.md>), [cursor](<https://devfeed.tech/topics/cursor.md>)

Tags: [agents](<https://devfeed.tech/tags/agents.md>), [airbnb](<https://devfeed.tech/tags/airbnb.md>), [app](<https://devfeed.tech/tags/app.md>), [artificial-intelligence](<https://devfeed.tech/tags/artificial-intelligence.md>), [artificial-intelligence-careers-developer-development-tools-generative-ai-roles-software-devel](<https://devfeed.tech/tags/artificial-intelligence-careers-developer-development-tools-generative-ai-roles-software-devel.md>), [building-software](<https://devfeed.tech/tags/building-software.md>), [careers](<https://devfeed.tech/tags/careers.md>), [ceo](<https://devfeed.tech/tags/ceo.md>), [charging](<https://devfeed.tech/tags/charging.md>), [claude-code](<https://devfeed.tech/tags/claude-code.md>), [coding](<https://devfeed.tech/tags/coding.md>), [coding-agents](<https://devfeed.tech/tags/coding-agents.md>), [context](<https://devfeed.tech/tags/context.md>), [cursor](<https://devfeed.tech/tags/cursor.md>), [customer](<https://devfeed.tech/tags/customer.md>), [developer](<https://devfeed.tech/tags/developer.md>), [development-tools](<https://devfeed.tech/tags/development-tools.md>), [generative-ai](<https://devfeed.tech/tags/generative-ai.md>), [human-in-the-loop](<https://devfeed.tech/tags/human-in-the-loop.md>), [intuit](<https://devfeed.tech/tags/intuit.md>), [language-en](<https://devfeed.tech/tags/language-en.md>), [marketing](<https://devfeed.tech/tags/marketing.md>), [marketplace](<https://devfeed.tech/tags/marketplace.md>), [pager](<https://devfeed.tech/tags/pager.md>), [random](<https://devfeed.tech/tags/random.md>), [red](<https://devfeed.tech/tags/red.md>), [roles](<https://devfeed.tech/tags/roles.md>), [software-development](<https://devfeed.tech/tags/software-development.md>), [storytype-opinion](<https://devfeed.tech/tags/storytype-opinion.md>), [uber](<https://devfeed.tech/tags/uber.md>)

### AI overview

The excerpt argues that coding agents can produce code quickly but still depend on humans to direct and judge software work. Humans contribute non-code context such as executive priorities and marketing requirements, remain accountable when software fails or schedules slip, and decide what to build by speaking with customers and judging market needs. Agents may follow poor requests without pushback, proceed on unstated assumptions instead of acknowledging uncertainty, and default to generic layouts unless given different direction. Because agents execute the request they receive, humans must also decide whether the result is appropriate. The excerpt's central takeaway is that agents shift the bottleneck from writing code to human judgment and direction.

### Source excerpt

Last week I wrote about how coding agents are better developers than humans. I'll stand by that -- the current agents can write code better, faster, longer, and with far less complaining than we humans can. But that doesn't make humans unnecessary -- quite the contrary. Humans still play a vital role in the process of building software. Here are eight reasons we can use to fend off the robots when they come for our jobs. Only humans can know non-code context Agents are great at keeping the work in mind and holding vastly more context than humans. But what about "This feature is a pet project of the CEO" or "The marketing team insists that the web page look like this"? Those are factors only a human can know and act on. You can try to explain complex human emotions to a coding agent, but it will never really understand the need to please the boss above a technical argument. Only humans can be accountable At the end of the day, there has to be a human in the loop. Customers can't complain to Claude Code about their software not being right. Someone has to be the on-duty developer who "carries the pager" when something goes wrong over the weekend. Your boss isn't going to have a stern conversation with Cursor if the project falls behind schedule. Only humans can say 'No' If you ask a coding agent to build an app where all the text is bright red and blinks at random intervals, it will cheerfully and diligently go off and do just that. It will not push back and say "Hmm. Is that really a good idea?" Only humans can say 'Yes' It takes a human being to decide what to do. You alone can talk to the customer and determine what exactly they need. Only humans can intuit what the marketplace wants and decide to build a crazy new thing like Uber or Airbnb. Only humans can say 'I don't know' Coding agents are skilled and energetic developers, but they can be too energetic, confidently charging off and doing things without stopping when they aren't sure about the destination. They mi

## 17 landing page examples to help you increase conversions

DevFeed: [17 landing page examples to help you increase conversions](<https://devfeed.tech/articles/17-landing-page-examples-to-help-you-increase-conversions-102445.md>)

Original publisher: [Read original article](<https://zapier.com/blog/landing-page-examples>)

Author: Katie Paterson

Published: 2026-10-26T05:00:00Z

Content type: article

Language: en

Sources: [Zapier](<https://devfeed.tech/sources/zapier.md>)

Topics: [A/B Testing](<https://devfeed.tech/topics/a-b-testing.md>), [User interface design](<https://devfeed.tech/topics/ui-design.md>)

Tags: [ai](<https://devfeed.tech/tags/ai.md>), [ai-tool](<https://devfeed.tech/tags/ai-tool.md>), [airbnb](<https://devfeed.tech/tags/airbnb.md>), [android](<https://devfeed.tech/tags/android.md>), [app](<https://devfeed.tech/tags/app.md>), [apple](<https://devfeed.tech/tags/apple.md>), [apple-pay](<https://devfeed.tech/tags/apple-pay.md>), [automate](<https://devfeed.tech/tags/automate.md>), [automation](<https://devfeed.tech/tags/automation.md>), [b2b-saas](<https://devfeed.tech/tags/b2b-saas.md>), [data](<https://devfeed.tech/tags/data.md>), [examples](<https://devfeed.tech/tags/examples.md>), [grow-your-business](<https://devfeed.tech/tags/grow-your-business.md>), [marketing](<https://devfeed.tech/tags/marketing.md>), [testing](<https://devfeed.tech/tags/testing.md>)

### AI overview

An effective landing page focuses visitors on one action, and the examples show varied ways to reduce friction or build interest: free tools and lead magnets, app QR codes, customer reviews, interactive demos and quizzes, personalized estimates, clear CTAs, and readable design. The article recommends matching tactics to the offer and audience; for example, multiple CTAs may suit a broad product range, while direct product access can work for easy-to-use software. It also stresses testing CTA options and adapting pages based on performance and audience response. Zapier is presented as automating follow-up after a form or button action, routing and updating leads across connected apps, with AI used for steps requiring judgment.

### Source excerpt

Any time I publish a landing page, I'm immediately thinking about what I could do next to make it better. How can I optimize the page to pull in more visitors? What new things can I add to see if we can improve conversions? Managing a successful landing page involves constantly testing new ideas, keeping an eye on the data, and adapting to whatever seems to resonate with your target audience. It's the beauty (or the drag, depending on how you look at it!) of online marketing. To inspire your nex

## GeoLEON-CLIP: Graph-Anchored Multimodal Contrastive Learning for Geographic Region Representation

DevFeed: [GeoLEON-CLIP: Graph-Anchored Multimodal Contrastive Learning for Geographic Region Representation](<https://devfeed.tech/articles/geoleon-clip-graph-anchored-multimodal-contrastive-learning-for-geographic-region-representation-99599.md>)

Original publisher: [Read original article](<https://arxiv.org/abs/2610.32311>)

Author: Radoslaw Malek, Szymon Soltysiak, Aleksandra Kawala-Sterniuk, Piotr Szymanski

Published: 2026-10-26T04:00:00Z

Content type: article

Language: en

Sources: [arXiv: Machine Learning](<https://devfeed.tech/sources/arxiv-machine-learning.md>)

Topics: [Representation learning](<https://devfeed.tech/topics/representation-learning.md>), [geospatial](<https://devfeed.tech/topics/geospatial.md>), [Embeddings](<https://devfeed.tech/topics/embeddings.md>), [metric learning](<https://devfeed.tech/topics/metric-learning.md>), [Graphs](<https://devfeed.tech/topics/graphs.md>)

Tags: [airbnb](<https://devfeed.tech/tags/airbnb.md>), [align](<https://devfeed.tech/tags/align.md>), [anchor](<https://devfeed.tech/tags/anchor.md>), [clip](<https://devfeed.tech/tags/clip.md>), [cs-cv](<https://devfeed.tech/tags/cs-cv.md>), [cs-lg](<https://devfeed.tech/tags/cs-lg.md>), [embedding](<https://devfeed.tech/tags/embedding.md>), [framework](<https://devfeed.tech/tags/framework.md>), [geospatial](<https://devfeed.tech/tags/geospatial.md>), [graph](<https://devfeed.tech/tags/graph.md>), [graph-embeddings](<https://devfeed.tech/tags/graph-embeddings.md>), [housing](<https://devfeed.tech/tags/housing.md>), [image](<https://devfeed.tech/tags/image.md>), [improvements](<https://devfeed.tech/tags/improvements.md>), [intermediate](<https://devfeed.tech/tags/intermediate.md>), [language](<https://devfeed.tech/tags/language.md>), [learning](<https://devfeed.tech/tags/learning.md>), [map](<https://devfeed.tech/tags/map.md>), [maps](<https://devfeed.tech/tags/maps.md>), [multimodal](<https://devfeed.tech/tags/multimodal.md>), [openstreetmap](<https://devfeed.tech/tags/openstreetmap.md>), [region](<https://devfeed.tech/tags/region.md>)

### AI overview

GeoLEON-CLIP aligns three views of each H3-indexed region: an OpenStreetMap-derived graph embedding, a satellite image crop, and a textual description. It uses frozen pretrained LEON graph embeddings as an anchor, with frozen graph, image, and text encoders linked by trainable residual projection heads and optimized using a symmetric tri-modal contrastive objective. The abstract reports strong graph-image and graph-text alignment, with graph-image retrieval performing best in a mixed-resolution pool. Chained retrieval through one graph cell improves R@1@1 over direct image-text retrieval by 4.8 points for image-to-text and 4.4 points for text-to-image. Downstream gains vary by task and are largest on Airbnb and Beijing housing.

### Source excerpt

arXiv:2610.32311v1 Announce Type: cross Abstract: Geographic regions are multimodal: satellite imagery captures visual morphology, text conveys human-interpretable semantics, and map structures describe urban context. Existing geospatial contrastive methods typically align image-text or image-location pairs, underusing structured map data. We introduce GeoLEON-CLIP, a graph-anchored contrastive framework that aligns three views of each H3-indexed region: an OpenStreetMap-derived graph embedding, a satellite image crop, and a textual description. Frozen pretrained LEON graph embeddings provide a semantic anchor between vision and language. Frozen graph, image, and text encoders are connected by trainable residual projection heads and trained with a symmetric tri-modal contrastive objective. Experiments show strong graph-image and graph-text alignment; graph-image retrieval achieves the best cross-modal performance in a mixed-resolution pool. To evaluate the anchoring hypothesis, we propose chained cross-modal recall $\mathrm{R}@A@B$, which routes retrieval through the graph modality and compares it with direct retrieval under a matched candidate budget. At $\mathrm{R}@1@1$, image$\rightarrow$graph$\rightarrow$text and text$\rightarrow$graph$\rightarrow$image outperform direct image-text retrieval by 4.8 and 4.4 points, respectively, despite using a single intermediate cell. Downstream probes show task-dependent gains, with the largest improvements on Airbnb and Beijing housing. These results indicate that OpenStreetMap graph structure can anchor multimodal representations combining maps, imagery, and language.

## Data Engineering Weekly #292

DevFeed: [Data Engineering Weekly #292](<https://devfeed.tech/articles/data-engineering-weekly-292-89969.md>)

Original publisher: [Read original article](<https://www.dataengineeringweekly.com/p/data-engineering-weekly-292>)

Author: Ananth Packkildurai

Published: 2026-10-19T03:58:54Z

Content type: article

Language: en

Sources: [Data Engineering Weekly](<https://devfeed.tech/sources/data-engineering-weekly.md>)

Topics: [data-engineering](<https://devfeed.tech/topics/data-engineering.md>), [AI Infrastructure](<https://devfeed.tech/topics/ai-infrastructure.md>), [data observability](<https://devfeed.tech/topics/data-observability.md>), [RDF (Resource Description Framework)](<https://devfeed.tech/topics/rdf.md>), [Apache Flink](<https://devfeed.tech/topics/apache-flink.md>), [elasticsearch](<https://devfeed.tech/topics/elasticsearch.md>), [Amazon Bedrock Knowledge Bases](<https://devfeed.tech/topics/amazon-bedrock-knowledge-bases.md>), [deltalake](<https://devfeed.tech/topics/deltalake.md>)

Tags: [ai](<https://devfeed.tech/tags/ai.md>), [airbnb](<https://devfeed.tech/tags/airbnb.md>), [apache](<https://devfeed.tech/tags/apache.md>), [apache-arrow](<https://devfeed.tech/tags/apache-arrow.md>), [aws](<https://devfeed.tech/tags/aws.md>), [aws-bedrock](<https://devfeed.tech/tags/aws-bedrock.md>), [clickhouse](<https://devfeed.tech/tags/clickhouse.md>), [data](<https://devfeed.tech/tags/data.md>), [data-engineering](<https://devfeed.tech/tags/data-engineering.md>), [data-infrastructure](<https://devfeed.tech/tags/data-infrastructure.md>)

### AI overview

This issue of Data Engineering Weekly collects reports and resources on data infrastructure. Topics include Zephon's deterministic online execution for AI training data, Apache Arrow's columnar computing ecosystem, observability ontology at Netflix, Spark and Flink shuffle scaling at LinkedIn, and data ingestion, search, and surveillance systems at other companies.

### Source excerpt

The Weekly Data Engineering Newsletter

## CASTLE: training natural language search before the first real query

DevFeed: [CASTLE: training natural language search before the first real query](<https://devfeed.tech/articles/castle-training-natural-language-search-before-the-first-real-query-86238.md>)

Original publisher: [Read original article](<https://medium.com/airbnb-engineering/castle-training-natural-language-search-before-the-first-real-query-3818ef8b4828?source=rss----53c7c27702d5---4>)

Author: Wendy Ran Wei

Published: 2026-10-13T17:01:02Z

Content type: article

Language: en

Sources: [Airbnb](<https://devfeed.tech/sources/the-airbnb-tech-blog-medium.md>)

Topics: [search-engines](<https://devfeed.tech/topics/search-engines.md>), [Large Language Model](<https://devfeed.tech/topics/llm.md>), [Artificial Intelligence](<https://devfeed.tech/topics/ai.md>)

Tags: [ai](<https://devfeed.tech/tags/ai.md>), [airbnb](<https://devfeed.tech/tags/airbnb.md>), [cold-start-problem](<https://devfeed.tech/tags/cold-start-problem.md>), [data](<https://devfeed.tech/tags/data.md>), [distribution](<https://devfeed.tech/tags/distribution.md>), [engineering](<https://devfeed.tech/tags/engineering.md>), [few-shot](<https://devfeed.tech/tags/few-shot.md>), [generate](<https://devfeed.tech/tags/generate.md>), [generation](<https://devfeed.tech/tags/generation.md>), [language-model](<https://devfeed.tech/tags/language-model.md>), [large-language-model](<https://devfeed.tech/tags/large-language-model.md>), [llm](<https://devfeed.tech/tags/llm.md>), [machine-learning](<https://devfeed.tech/tags/machine-learning.md>), [model](<https://devfeed.tech/tags/model.md>), [natural-language](<https://devfeed.tech/tags/natural-language.md>), [relevance](<https://devfeed.tech/tags/relevance.md>), [search](<https://devfeed.tech/tags/search.md>), [synthetic](<https://devfeed.tech/tags/synthetic.md>), [technology](<https://devfeed.tech/tags/technology.md>), [traffic](<https://devfeed.tech/tags/traffic.md>), [train](<https://devfeed.tech/tags/train.md>), [training](<https://devfeed.tech/tags/training.md>), [training-data](<https://devfeed.tech/tags/training-data.md>)

### AI overview

CASTLE tackles cold-start natural language search by using de-identified booking sessions to form positive and negative listing pairs, then prompting an LLM to generate queries that fit the booked listing but not the alternatives. This makes relevance labels part of the construction, avoiding a separate LLM judging step for the core data. Template prompts, about 500 research seed queries, attribute-focused prompts, and a variety mechanism are used to improve query variety and match guest phrasing. For listings without booking history, a Virtual Judge assigns labels; CASTLE-R is intended for settings with some real search traffic. In the reported evaluation, CASTLE achieved 1.01 KL divergence against real query distributions, versus 9.33 for the best baseline, and experts agreed with its labels 91-93% of the time across 200 sampled triplets. These results are reported for the described evaluations.

### Source excerpt

How we addressed the cold-start problem for Airbnb's natural language search by jointly generating synthetic training data -- queries and relevance labels -- from de-identified booking and search signals. By: Wendy Ran Wei, Hao Li, Weiwei Guo, Xiaowei Liu, Xueyin Chen, Chun How Tan, Malay Haldar, Soumyadip Banerjee, Kedar Bellare, Huiji Gao, Sanjeev Katariya, and Stephanie Moyerman Introduction Natural language search lets guests express intent in their own words, such as "romantic cabin near skiing" or "pet-friendly beach house that sleeps eight," rather than navigating filters and categories. We needed to introduce this kind of search for Airbnb, and to have it work well from the start. However, this required training the model before we had actual user queries to train the model on, and a reasonable set of relevance labels (inferred from the queries) to map queries to matching listings. Without prior traffic, both must be synthesized from scratch. This is the cold-start problem for natural-language search. Other organizations have faced similar challenges and have created methods to address them. However, prior approaches address the need for a body of queries and the need for relevance labels separately. Passage-based methods such as InPars [1] prompt a large language model (LLM) to generate queries conditioned on a single document, then rely on additional LLM judgments to assign relevance labels, introducing a second source of error. Promptagator [2] improves query diversity using few-shot examples, but is still limited by the gap between its generation distribution and real user behavior. In this post, we describe Contrastive And Seed-guided Training for natural Language sEarch (CASTLE), our framework for jointly generating queries and producing relevance labels from Airbnb's own de-identified booking data. Our paper describing CASTLE was accepted as a full research paper at the 35th ACM International Conference on Information and Knowledge Management, more wide

## Police are using AI to locate homes from a single interior photo, and even a picture of a washing machine can be enough

DevFeed: [Police are using AI to locate homes from a single interior photo, and even a picture of a washing machine can be enough](<https://devfeed.tech/articles/police-are-using-ai-to-locate-homes-from-a-single-interior-photo-and-even-a-picture-of-a-washing-machine-can-be-enough-85342.md>)

Original publisher: [Read original article](<https://www.techspot.com/news/114174-police-using-ai-locate-homes-single-interior-photo.html>)

Author: Rob Thubron

Published: 2026-10-12T15:38:00Z

Content type: news

Language: en

Sources: [TechSpot](<https://devfeed.tech/sources/techspot.md>)

Topics: [Artificial Intelligence](<https://devfeed.tech/topics/ai.md>), [AI for customer service automation](<https://devfeed.tech/topics/ai-for-customer-service-automation.md>)

Tags: [ai](<https://devfeed.tech/tags/ai.md>), [airbnb](<https://devfeed.tech/tags/airbnb.md>), [flock](<https://devfeed.tech/tags/flock.md>), [law-enforcement](<https://devfeed.tech/tags/law-enforcement.md>), [police](<https://devfeed.tech/tags/police.md>), [raven](<https://devfeed.tech/tags/raven.md>), [surveillance](<https://devfeed.tech/tags/surveillance.md>), [tech-culture](<https://devfeed.tech/tags/tech-culture.md>)

### AI overview

Police departments in Los Angeles and Miami-Dade are using Raven, an AI tool from Graylark Technologies, to identify possible property locations from interior photos. The article says Raven matches distinctive details against short-term rental listings and may draw on real estate listings; its use raises privacy concerns, and its earlier public version was restricted after users sought help stalking women.

### Source excerpt

The tool, which is called Raven, is being used by the Los Angeles Police Department and Miami-Dade Sheriff's Office (MDSO), reports 404 Media. Made by a company called Graylark Technologies, Raven had been called GeoSpy before its new home-identification features were added. Read Entire Article

## 🍔🧠 Airbnb Tested DB Migrations With Real Production Traffic

DevFeed: [🍔🧠 Airbnb Tested DB Migrations With Real Production Traffic](<https://devfeed.tech/articles/airbnb-tested-db-migrations-with-real-production-traffic-85592.md>)

Original publisher: [Read original article](<https://hungrymindsdev.substack.com/p/airbnb-tested-db-migrations-with>)

Author: Alexandre Zajac

Published: 2026-10-12T15:31:08Z

Content type: article

Language: en

Sources: [Hungry Minds](<https://devfeed.tech/sources/hungry-minds.md>)

Topics: [Test-driven development](<https://devfeed.tech/topics/tdd.md>)

Tags: [airbnb](<https://devfeed.tech/tags/airbnb.md>), [capacity](<https://devfeed.tech/tags/capacity.md>), [concurrency](<https://devfeed.tech/tags/concurrency.md>), [migrations](<https://devfeed.tech/tags/migrations.md>), [production](<https://devfeed.tech/tags/production.md>)

### AI overview

Airbnb engineers built a system to capture production MySQL traffic and replay it against test databases before upgrades. The replay process reconstructs transactions, controls load, and compares results while protecting captured data. It exposed a query latency regression during a MySQL upgrade and a capacity limit under increased write traffic.

### Source excerpt

PLUS: Decisions API beta 🚀, JPEG XL reaches Chrome 🖼, Codemode composes MCP tools ⚙

## AI Company Lets Cops Pinpoint Specific Houses Based on a Single Interior Photo

DevFeed: [AI Company Lets Cops Pinpoint Specific Houses Based on a Single Interior Photo](<https://devfeed.tech/articles/ai-company-lets-cops-pinpoint-specific-houses-based-on-a-single-interior-photo-85314.md>)

Original publisher: [Read original article](<https://www.404media.co/ai-company-lets-cops-pinpoint-specific-houses-based-on-a-single-interior-photo/>)

Author: Joseph Cox

Published: 2026-10-12T13:00:05Z

Content type: news

Language: en

Sources: [404 Media](<https://devfeed.tech/sources/404-media.md>)

Topics: [infini-attention](<https://devfeed.tech/topics/infini-attention.md>), [ARKTunnel](<https://devfeed.tech/topics/arktunnel.md>)

Tags: [ai](<https://devfeed.tech/tags/ai.md>), [airbnb](<https://devfeed.tech/tags/airbnb.md>), [exploitation](<https://devfeed.tech/tags/exploitation.md>), [news](<https://devfeed.tech/tags/news.md>), [raven](<https://devfeed.tech/tags/raven.md>)

### AI overview

The article reports that Raven, an AI geolocation tool formerly called GeoSpy, can use interior photos to identify likely homes, rentals, or hotels by matching visual clues with property listings. It describes concerns about law enforcement use, data scraping, and privacy, and notes that a sheriff's office said the tool had not produced significant investigative breakthroughs or arrests.

### Source excerpt

Raven, previously called GeoSpy, lets cops figure out what specific Airbnb or Zillow property a photo was taken in.

[Next page](<https://devfeed.tech/tags/airbnb.md?cursor=WyIyMDI2LTEwLTEyVDEzOjAwOjA1KzAwOjAwIiwgImUxNzVlMmMwLTVlOTctNDIzYS1iZDMzLWUxMWYwNWIyMTE0YyJd>)