# Product News Published articles for Product News. This is one page of public article previews, not the complete archive. Follow Next page to continue. Summaries are not the original full articles. ## sem-ai 0.4.0: smaller responses, safer access, and pre-flight checks DevFeed: [sem-ai 0.4.0: smaller responses, safer access, and pre-flight checks]() Original publisher: [Read original article]() Author: Pete Miloravac Published: 2026-09-16T12:01:04Z Content type: release Language: en Sources: [Semaphore Engineering]() Topics: [AI-assisted coding](), [Claude Code](), [Command-line interface](), [Authorization](), [API](), [configuration]() Tags: [ai-coding-agents](), [api](), [audio](), [claude-code](), [command-line](), [configuration](), [permissions](), [pipelines](), [product-news](), [release](), [video]() ### AI overview Semaphore's sem-ai 0.4.0 release adds more compact workflow and pipeline responses, context switching across organizations and credentials, and support for managing pre-flight checks. The update is aimed at reducing context usage and enabling more targeted permissions for AI coding agents. ### Source excerpt AI coding agents work best when they receive the right information without unnecessary noise. They also need clearly defined permissions and reliable safeguards for the changes they make. sem-ai 0.4.0 improves all three areas. The release introduces more compact pipeline responses, flexible context switching, and support for Semaphore pre-flight checks. Watch Nick demonstrate the new [...] The post sem-ai 0.4.0: smaller responses, safer access, and pre-flight checks appeared first on Semaphore. ## Cloudflare adds controls to allow search indexing while disallowing AI training DevFeed: [Cloudflare adds controls to allow search indexing while disallowing AI training]() Original publisher: [Read original article]() Author: Bryan Becker Published: 2026-09-15T13:00:00Z Content type: release Language: en Sources: [Cloudflare Blog]() Topics: [Cloudflare](), [Artificial Intelligence](), [Crawler](), [Google](), [Microsoft]() Tags: [ai](), [ai-bots](), [blocking](), [bot-management](), [bots](), [cloudflare](), [content](), [google](), [internet](), [microsoft](), [network-services](), [product-news](), [search](), [security]() ### AI overview Cloudflare announces a Disallow AI Training setting that lets website owners remain indexed in search while refusing AI training by mixed-use crawlers. Apple, Google, and Microsoft honor or have committed to honor the setting. ### Source excerpt Cloudflare is giving site owners a way to stay discoverable while disallowing AI training. New controls and an Accountable designation establish a shared model with Apple, Google, and Microsoft. ## Give every teammate and agent the right level of access to your Workers DevFeed: [Give every teammate and agent the right level of access to your Workers]() Original publisher: [Read original article]() Author: Visal In Published: 2026-09-15T13:00:00Z Content type: release Language: en Sources: [Cloudflare Blog]() Topics: [Workers](), [Authorization](), [Developer Platform](), [debug]() Tags: [agent](), [api](), [cloudflare](), [debug](), [developer](), [developer-platform](), [developers](), [identity](), [least-privilege](), [logs](), [metrics](), [monitor](), [product-news](), [scope](), [security](), [traces](), [workers](), [workflows]() ### AI overview Cloudflare now lets teams scope access to individual Workers and assign narrower Developer Platform roles. Teammates, CI tokens, and agents can receive only the permissions needed to debug, deploy, or monitor safely. ### Source excerpt You can now scope access to individual Workers and assign narrower Developer Platform roles, so teammates, CI tokens, and agents get only the access they need to debug, deploy, or monitor safely. ## Making testing work better for AI driven development DevFeed: [Making testing work better for AI driven development]() Original publisher: [Read original article]() Author: Pete Miloravac Published: 2026-09-10T09:28:14Z Content type: release Language: en Sources: [Semaphore Engineering]() Topics: [Testing](), [Development](), [Artificial Intelligence](), [Test coverage](), [RSpec]() Tags: [ai](), [flaky](), [framework](), [product-news](), [test-coverage](), [testing](), [xunit]() ### AI overview Semaphore describes product work to make testing more useful for developers and AI agents. The update covers richer test reports from testing frameworks, signal-based flaky-test detection, and code-graph-based selection of tests affected by code changes. ### Source excerpt AI agents can generate and modify code quickly. But when a test fails, speed is no longer enough. The agent needs enough context to understand what happened, why it happened, and whether the code or the test itself needs to change. In our latest product update, Marko Gaćeša is joined by Semaphore engineers Nick and [...] The post Making testing work better for AI driven development appeared first on Semaphore. ## Introducing IP Allowlisting DevFeed: [Introducing IP Allowlisting]() Original publisher: [Read original article]() Author: Postmark team (fdossetto+postmark@activecampaign.com) Published: 2026-09-08T17:37:00Z Content type: release Language: en Sources: [Postmark (en-US)]() Topics: [Security](), [API](), [Network](), [Cloud]() Tags: [api](), [infrastructure](), [ip](), [nat](), [network](), [product-news](), [protection](), [range](), [request](), [security](), [token]() ### AI overview Postmark introduces IP Allowlisting, a security feature that restricts email sending through the Postmark API to up to 10 configured IP ranges in CIDR format. Requests from outside the allowed ranges are rejected with a 403 response. The ranges can be configured at the Server or account level, with Server settings overriding account settings. ### Source excerpt Good security is layered and each layer does a job the others can't. Scoping a token to a Server limits what it reaches. Rotating a token limits how long it lasts. Neither can say anything about where a request came from. We've been hard at work to ship a new layer of protection that can. IP Allowlisting is a new Postmark security feature that lets you name the infrastructure your email should come from. It's available now on all Postmark plans at no extra cost. It's off until you turn it on. How IP Allowlisting works You add up to 10 IP ranges, in CIDR format, that are allowed to send email using the Postmark API. Send requests from outside those ranges are rejected with a 403 status code that includes the IP the request came from. You can set your ranges in two places: On a Server. The ranges apply to that Server, covering every Message Stream on it. This is where we'd suggest starting. On your account. The ranges apply to every Server you have. When a Server has ranges of its own they will override account level settings. That's it! A straightforward security control to protect your API sending. Protect individual Servers or across your account. Set your Allowlist ranges on the account or Server. If you don't write CIDR blocks often, it's a quick 30 seconds to get familiar with them and the correct notation. CIDR blocks allow you to enable a grouped collection of IP addresses (aka ranges.) A CIDR block is an IP address followed by a suffix that says how many addresses it covers. The smaller the suffix, the wider the range: 198.51.100.24/32 one address, and only that address 203.0.113.0/24 256 addresses: 203.0.113.0 through 203.0.113.255 203.0.0.0/16 65,536 addresses: 203.0.0.0 through 203.0.255.255 So a /32 pins the allowlist to a single machine, and a /24 covers a subnet. Most teams end up somewhere in that span. Where you find your own ranges depends on how you send. A single VM has a static public IP you can read off your provider's dashboard. Cloud workloads ## Introducing context-aware vulnerability discovery and remediation with Cloudflare Managed Defense and OpenAI Daybreak models DevFeed: [Introducing context-aware vulnerability discovery and remediation with Cloudflare Managed Defense and OpenAI Daybreak models]() Original publisher: [Read original article]() Author: Blake Darché Published: 2026-09-03T21:03:02Z Content type: release Language: en Sources: [Cloudflare Blog]() Topics: [Vulnerabilities](), [Language models](), [AI-assisted coding]() Tags: [artificial-intelligence](), [cloudflare](), [code](), [developers](), [edge](), [firewall](), [gpt](), [large-language-models](), [openai](), [product-news](), [production](), [security](), [vulnerability](), [workers]() ### AI overview Cloudflare announces early access to an invitation-only service that prioritizes code vulnerabilities using production traffic, security signals, WAF context, and OpenAI Daybreak models. It proposes and validates patches or mitigations for customer review, while customers decide whether to implement them. ### Source excerpt Use production traffic and security signals to prioritize findings, prepare edge mitigations when safe, and propose code patches. By combining WAF data with OpenAI Daybreak models, Vulnerability Discovery and Remediation helps teams identify and patch the most critical threats first. ## Introducing Adaptive Intelligence: Undermining the economics of every bot attack DevFeed: [Introducing Adaptive Intelligence: Undermining the economics of every bot attack]() Original publisher: [Read original article]() Author: Chris Pope Published: 2026-08-31T12:59:00Z Content type: release Language: en Sources: [Cloudflare Blog]() Topics: [Bot](), [Artificial Intelligence](), [Cloudflare](), [Network](), [releases]() Tags: [ai](), [application-security](), [attacks](), [bot-management](), [cloudflare](), [machine-learning](), [network](), [product-news](), [releases]() ### AI overview Cloudflare introduces Adaptive Intelligence, a bot detection engine designed to undermine the economics of automated attacks. It responds to attackers' changing tactics by learning from live traffic and making attacks slower and more costly to sustain. ### Source excerpt Bot operators have historically had the economic advantage, bypassing static, deterministic detection rules with cheap proxies and retooling. Cloudflare's new Adaptive Intelligence engine flips this dynamic by autonomously learning from the meta-signals of live traffic and deploying disposable rules, making automated attacks too expensive to sustain. ## Say it once: Introducing Bot Preference Sync DevFeed: [Say it once: Introducing Bot Preference Sync]() Original publisher: [Read original article]() Author: Jin-Hee Lee Published: 2026-08-21T23:19:57Z Content type: article Language: en Sources: [Cloudflare Blog]() Topics: [AI Bots]() Tags: [ai](), [ai-bots](), [ai-models](), [ai-training](), [bot-management](), [bots](), [cloudflare](), [network-services](), [product-news](), [robots](), [search](), [sync](), [training]() ### AI overview Cloudflare introduces Bot Preference Sync, which updates robots.txt preferences to match configured AI bot policies for Search, Agent, and Training traffic. ### Source excerpt Cloudflare's new Bot Preference Sync automatically aligns your robots.txt file with your AI bot policies for Search, Agent, and Training. Easily manage which bots access your content without maintaining static files. ## From all-or-nothing to task-based OAuth consent DevFeed: [From all-or-nothing to task-based OAuth consent]() Original publisher: [Read original article]() Author: José Enrique Rodríguez Published: 2026-08-20T17:03:03Z Content type: article Language: en Sources: [Cloudflare Blog]() Topics: [Authorization](), [Security](), [Cloudflare](), [MCP Server](), [App](), [Low-Code / Internal Tools](), [Software as a service]() Tags: [agent](), [agents](), [api](), [applications](), [cloudflare](), [developer-platform](), [developers](), [identity](), [integrations](), [internal-tools](), [mcp](), [mcp-server](), [oauth](), [product-news](), [security](), [workflows]() ### AI overview Cloudflare OAuth now supports customizable consent scopes, allowing users to grant only the optional permissions needed for a specific task while developers retain required scopes. ### Source excerpt Cloudflare OAuth now supports optional scopes, giving users more control over what an app can access and helping developers build secure consent flows around the task at hand. ## How Cloudflare detects MCP traffic and helps secure it DevFeed: [How Cloudflare detects MCP traffic and helps secure it]() Original publisher: [Read original article]() Author: Kenny Johnson Published: 2026-08-14T13:12:12Z Content type: release Language: en Sources: [Cloudflare Blog]() Topics: [MSP MCP](), [AI Chat]() Tags: [agentic-ai](), [agents](), [ai](), [api](), [cloudflare-one](), [mcp](), [product-news](), [sase](), [security](), [zero-trust]() ### AI overview Cloudflare announces Cloudflare One controls for identifying MCP traffic, finding shadow connections, and enforcing Portal-only access to trusted MCP servers on managed network paths. ### Source excerpt Cloudflare Gateway identifies MCP requests using protocol-level heuristics. Security teams can use that signal to find shadow MCP traffic, enforce Portal-only access for approved servers, and block direct connections on managed network paths. ## Secure all your internal vibe-coded applications -- in one click DevFeed: [Secure all your internal vibe-coded applications -- in one click]() Original publisher: [Read original article]() Author: Matt Provost Published: 2026-08-14T13:00:00Z Content type: release Language: en Sources: [Cloudflare Blog]() Topics: [Cloudflare Access](), [Workers](), [Authentication](), [Cloudflare](), [Deployment](), [App]() Tags: [ai](), [authentication](), [cloudflare](), [cloudflare-access](), [cloudflare-workers](), [deployment](), [developer](), [developer-platform](), [developers](), [policy](), [product-news](), [sase](), [workers](), [zero-trust]() ### AI overview Cloudflare introduces Cloudflare Access for Workers, allowing account-level or application-level policies to require company authentication for preview and production deployments. Policies can protect Workers across custom domains, routes, workers.dev subdomains, and preview URLs, while authenticated user details can be accessed directly in application code. ### Source excerpt Introducing Cloudflare Access for Workers. Attach an Access policy directly to a Worker and it applies everywhere that Worker runs -- routes, custom domains, workers.dev, and previews -- automatically. ## Rerun Only the Jobs That Failed DevFeed: [Rerun Only the Jobs That Failed]() Original publisher: [Read original article]() Author: Pete Miloravac Published: 2026-08-12T10:31:39Z Content type: release Language: en Sources: [Semaphore Engineering]() Topics: [ci](), [jobs](), [Development]() Tags: [2026](), [ci](), [cost](), [flag](), [jobs](), [pipeline](), [product-news](), [rebuilds](), [run](), [workflow]() ### AI overview Semaphore now reruns only failed jobs in a pipeline, carrying over successful jobs and preserving the workflow topology. This reduces rerun time and billable usage, while a YAML flag preserves the previous full-block rebuild behavior. ### Source excerpt Your pipeline fails on one job, and until now you had to rebuild the entire block to recover. Not anymore. Semaphore now reruns only the jobs that actually failed, so you get feedback faster and pay less to get it. What Shipped: Job Rerun When a pipeline failed, the old behavior rebuilt every job inside [...] The post Rerun Only the Jobs That Failed appeared first on Semaphore. ## Announcement: Xcode16 Deprecation in Semaphore DevFeed: [Announcement: Xcode16 Deprecation in Semaphore]() Original publisher: [Read original article]() Author: Pete Miloravac Published: 2026-08-04T13:47:48Z Content type: release Language: en Sources: [Semaphore Engineering]() Topics: [Xcode](), [macOS](), [ci]() Tags: [announcement](), [ci](), [deprecated](), [end-of-life](), [lifecycle](), [macos](), [operating-systems](), [product-news](), [yaml]() ### AI overview Semaphore is deprecating and retiring its macOS Xcode16 build environments. Brownout periods will run from September 7 through October 4, 2026, before the environments are removed on October 5, 2026. Users are instructed to migrate pipelines to macos-xcode26 and validate them. ### Source excerpt MacOS Xcode16 reached the end of its supported lifecycle on Semaphore. To ensure the security, reliability, and maintainability of our platform, we are announcing the deprecation and end of life of MacOS Xcode16 build environments. Semaphore users should switch to Xcode26. Why We're Deprecating Xcode16 As operating systems age, they cease to receive timely security [...] The post Announcement: Xcode16 Deprecation in Semaphore appeared first on Semaphore. ## Announcing Serverless Workers for Google Cloud Run DevFeed: [Announcing Serverless Workers for Google Cloud Run]() Original publisher: [Read original article]() Author: Brandon Chavis Published: 2026-07-30T00:00:00Z Content type: release Language: en Sources: [Temporal Blog]() Topics: [Cloud Run](), [autoscaling](), [Serverless](), [Google Cloud Platform (GCP)](), [Deployment](), [container](), [IAM]() Tags: [autoscaling](), [cloud-run](), [deployment](), [docker](), [google-cloud-run](), [iam](), [product-news](), [serverless]() ### AI overview Temporal announces Serverless Workers support for Google Cloud Run. The service integrates with Cloud Run Worker Pools and dynamically adjusts capacity, including scaling to zero when appropriate, reducing the infrastructure planning and autoscaling work required from users. ### Source excerpt Temporal now supports Serverless Workers on Google Cloud Run, autoscaling Worker Pools for you so you never manage infrastructure or pay for idle compute. ## The Postmark MCP server, one year later: from 4 tools to 24 DevFeed: [The Postmark MCP server, one year later: from 4 tools to 24]() Original publisher: [Read original article]() Author: Jabal Torres (jtorres@activecampaign.com) Published: 2026-07-21T16:05:00Z Content type: opinion Language: en Sources: [Postmark (en-US)]() Topics: [MCP](), [MCP Server](), [API](), [AI Agent]() Tags: [ai-agent](), [api](), [diagnostics](), [mcp](), [mcp-server](), [product-news](), [tool]() ### AI overview Postmark reflects on a year of developing and operating its MCP server, which grew from four tools to 24 in the official @activecampaign/postmark-mcp package. The article explains why designing tools around user outcomes, such as the diagnoseDelivery workflow, is different from mechanically wrapping API endpoints. ### Source excerpt About a year ago, we introduced something experimental from Postmark Labs: an MCP server that let an AI assistant send email through Postmark. It shipped with exactly one useful tool, sendEmail, plus three supporting ones (four total). You gave it a recipient, a subject, and a body, and it sent. We said at the time we'd started with a single Postmark server "because we had to start somewhere." A lot has happened since. The project graduated from Labs and became the official @activecampaign/postmark-mcp package, and along the way, we learned a lot about what it actually takes to put an AI assistant in front of a production email API responsibly. The latest release, v2.1.1, ships 24 tools across eight categories: sending, templates, message search, delivery diagnostics, bounces, suppressions, stats, and webhooks. But the tool count isn't really the story. The story is what a year of running this thing taught us: designing tools for an AI agent is a different discipline than wrapping an API, and once your server has an official name, everything downstream of that name needs to earn it. From one endpoint to a whole surface The original four tools mirrored individual Postmark endpoints directly. Getting from there to 24 the naive way -- one tool per endpoint, mechanically -- is where we started. But somewhere around tool ten, we realized that users interacting with an AI assistant don't conceptualize their needs as API calls. They approach it with human inquiries. That reframing shaped everything that mattered about the v2.0 release. Designing for outcomes, not endpoints The best example of that shift doesn't map to a single Postmark endpoint at all. It's called diagnoseDelivery, and it exists to answer one very human question: did my email actually reach this person, and if not, why? Before, answering that meant a five-step investigation across the dashboard: search outbound messages, pull the message details, read the event timeline, check the suppression list, check the ## LangGraph in production: Temporal's LangGraph Plugin adds Durable Execution DevFeed: [LangGraph in production: Temporal's LangGraph Plugin adds Durable Execution]() Original publisher: [Read original article]() Author: Brian Strauch Published: 2026-07-16T00:00:00Z Content type: release Language: en Sources: [Temporal Blog]() Topics: [Langgraph](), [Orchestration](), [Agent Framework](), [human review](), [Python](), [telemetry]() Tags: [agent-framework](), [crash-recovery](), [human-review](), [langgraph](), [orchestration](), [product-news](), [python]() ### AI overview Temporal announces a public-preview LangGraph integration for Python, allowing LangGraph agents to run on Temporal with automatic failure recovery, durable execution, human-in-the-loop waits, and support for long-running work. The announcement also covers LangSmith integrations for Python and TypeScript. ### Source excerpt LangGraph agents now run on Temporal: automatic crash recovery, free human-in-the-loop waits, and full observability via new LangSmith integration. ## DASH 2026 recap: Product news, sessions, and highlights DevFeed: [DASH 2026 recap: Product news, sessions, and highlights]() Original publisher: [Read original article]() Author: Claire Laurence Published: 2026-07-07T00:00:00Z Content type: news Language: en Sources: [Datadog | The Monitor blog]() Topics: [observability](), [agent observability](), [Artificial Intelligence](), [AI Agent](), [Automation](), [Security](), [Monitoring](), [AI-assisted coding]() Tags: [agent-observability](), [ai](), [announcements](), [automation](), [dash](), [news](), [observability](), [product](), [product-news](), [security](), [updates]() ### AI overview DASH 2026 recap covering Datadog product announcements, technical sessions, customer talks, and community activities. The article highlights more than 170 new products and features across observability, security, AI-assisted operations, infrastructure, networking, code, data, and user experience. ### Source excerpt Catch up on the Datadog product and feature announcements, technical sessions, customer stories, and community activities from DASH 2026. ## Improved cost transparency with usage-based billing DevFeed: [Improved cost transparency with usage-based billing]() Original publisher: [Read original article]() Author: Markus Sample Published: 2026-06-25T00:00:00Z Content type: release Language: en Sources: [Temporal Blog]() Topics: [API](), [cloud cost management](), [Cloud](), [observability](), [Monitoring]() Tags: [api](), [cloud](), [cloud-cost-management](), [cost](), [datadog](), [metrics](), [observability](), [product-news](), [usage-based-billing]() ### AI overview Temporal announces general availability of the Temporal Cloud Billing API and Billable Action Count metric, providing more granular cost attribution, usage data, reporting, and optimization signals. ### Source excerpt Learn how the Temporal Cloud Billing API and Billable Action Count metric give teams clearer cost attribution, usage trends, and optimization signals. ## Flaky Test API Now GA, New Auto-Fix Skill, Skill Quality Improvements DevFeed: [Flaky Test API Now GA, New Auto-Fix Skill, Skill Quality Improvements]() Original publisher: [Read original article]() Author: Pete Miloravac Published: 2026-06-19T11:00:00Z Content type: release Language: en Sources: [Semaphore Engineering]() Topics: [API](), [AI Agent](), [LLM evaluation / benchmarking](), [Claude](), [data]() Tags: [agent](), [ai](), [api](), [audio](), [cost](), [data](), [flaky](), [improvements](), [product-news](), [quality](), [release](), [validation](), [verify](), [video]() ### AI overview Semaphore announces generally available flaky-test data through its sem-ai API, a skill that lets an AI agent investigate and fix flaky tests, and improvements to existing skills through added examples. The article also reports typical fix costs of $1 to $1.50 when benchmarking with Claude Opus 4.8 on high effort. ### Source excerpt You can now identify your flakiest tests through the API and have an AI agent fix them, at a cost of around $1 to $1.50 per fix. What Shipped Flaky Test Data in the API (Generally Available) Flaky test data is now accessible programmatically through the sem-ai API. The API surfaces tests ranked by disruption [...] The post Flaky Test API Now GA, New Auto-Fix Skill, Skill Quality Improvements appeared first on Semaphore. ## Workflow Streams: Live interactivity for agents and other applications DevFeed: [Workflow Streams: Live interactivity for agents and other applications]() Original publisher: [Read original article]() Author: Johann Schleier-Smith Published: 2026-06-17T00:00:00Z Content type: release Language: en Sources: [Temporal Blog]() Topics: [Streaming](), [User Interfaces](), [Library](), [clients](), [Artificial Intelligence]() Tags: [agents](), [product-news](), [sdk](), [streaming](), [streams](), [typescript](), [ui]() ### AI overview Temporal introduces Workflow Streams, a durable streams abstraction for building interactive UIs with incremental updates. The feature supports AI-agent status, reasoning, tool-call, and generated-text updates, and is in Public Preview for Python and TypeScript. ### Source excerpt Workflow Streams brings durable interactivity to Temporal. You get stream agent reasoning, tool calls, and status updates to any UI. ## Codex Support, Faster Task Creation, and Flaky Test Visibility DevFeed: [Codex Support, Faster Task Creation, and Flaky Test Visibility]() Original publisher: [Read original article]() Author: Pete Miloravac Published: 2026-06-04T14:43:11Z Content type: article Language: en Sources: [Semaphore Engineering]() Topics: [codex](), [ai-coding](), [Command-line interface](), [ci](), [Claude Code]() Tags: [ai-agents](), [ai-coding](), [audio](), [ci](), [cli](), [codex](), [flaky](), [product-news](), [video](), [visibility]() ### AI overview Semaphore's update covers fixes to sem-ai, faster and more reliable task creation, CLI-based task management, and a Semaphore Cloud workflow-editor option for showing skipped blocks. Planned work includes broader platform management through the CLI, flaky-test data through the API, and AI-assisted onboarding for tools including Claude Code and Codex. ### Source excerpt sem-ai keeps moving. Here's a quick rundown of what shipped last week and what's coming next. What Shipped on Sem-AI Glitches have been fixed.A few issues were blocking some users to get started with sem-ai. Those are resolved. If you tried it before and ran into friction, now's a good time to try again. See [...] The post Codex Support, Faster Task Creation, and Flaky Test Visibility appeared first on Semaphore. ## Building an AI-Native CI/CD Experience with sem-ai DevFeed: [Building an AI-Native CI/CD Experience with sem-ai]() Original publisher: [Read original article]() Author: Pete Miloravac Published: 2026-05-27T09:35:38Z Content type: release Language: en Sources: [Semaphore Engineering]() Topics: [CI/CD](), [Artificial Intelligence](), [GitHub Actions](), [Go Language]() Tags: [ai](), [ai-coding-agents](), [audio](), [ci-cd](), [claude-code](), [github-actions](), [go](), [product-news](), [review](), [video]() ### AI overview Semaphore presents sem-ai, an AI-native CI experience that lets developers interact with CI/CD using natural language through tools such as Claude Code. A demonstrated workflow initializes a Semaphore project and proposes CI configuration based on the repository's technology stack. ### Source excerpt Developers don't want to spend their time writing CI configuration, debugging flaky pipelines, or digging through logs to understand why a build failed. They want to ship software. That's the idea behind sem-ai - Semaphore's approach to building an AI-native CI experience where developers interact with CI/CD using natural language, directly from the tools they [...] The post Building an AI-Native CI/CD Experience with sem-ai appeared first on Semaphore. ## Introducing Semaphore for AI Agents: An AI-Native Developer Experience for CI/CD DevFeed: [Introducing Semaphore for AI Agents: An AI-Native Developer Experience for CI/CD]() Original publisher: [Read original article]() Author: Pete Miloravac Published: 2026-05-14T08:28:46Z Content type: release Language: en Sources: [Semaphore Engineering]() Topics: [CI/CD](), [AI Development](), [AI-assisted coding](), [workflow automation]() Tags: [ai-agents](), [ai-coding-agents](), [audio](), [ci-cd](), [cli](), [debugging](), [product-news](), [video]() ### AI overview Semaphore introduces an open-source CLI and agentic interface that makes its CI/CD platform accessible from AI coding agents. The initial release focuses on structured access to pipeline visibility, debugging, and workflow automation, including failing-test information, pipeline summaries, diagnostics, commit metadata, and flaky-test information. ### Source excerpt Developers are no longer spending most of their time inside traditional IDEs. Today, workflows increasingly happen inside AI-powered coding environments like Claude Code, Cursor, and Codex. Developers are collaborating with agents, asking questions in natural language, debugging through conversations, and automating repetitive work directly from their coding environment. At Semaphore, we believe CI/CD needs to [...] The post Introducing Semaphore for AI Agents: An AI-Native Developer Experience for CI/CD appeared first on Semaphore. ## Standalone Activities: Durable job processing, now in Public Preview DevFeed: [Standalone Activities: Durable job processing, now in Public Preview]() Original publisher: [Read original article]() Author: Phil Prasek Published: 2026-05-14T00:00:00Z Content type: release Language: en Sources: [Temporal Blog]() Topics: [Job](), [Cloud](), [observability](), [SDKs](), [API](), [Command-line interface]() Tags: [2](), [api](), [backend](), [cli](), [cloud](), [deployment](), [job](), [observability](), [preview](), [product-news](), [retries]() ### AI overview Temporal announces the Public Preview of Standalone Activities, which provide durable background job processing with retries, observability, and lifecycle controls across most Temporal SDKs and Temporal Cloud. ### Source excerpt Temporal Standalone Activities are now in Public Preview, bringing durable job processing, retries, observability, and lifecycle control to Temporal Cloud. [Next page]()