# Developer Experience & Platform Engineering Blog | Port News and stories about internal developer portals, platform engineering, software catalogs and developer experience. This is one page of public article previews, not the complete archive. Follow Next page to continue. Summaries are not the original full articles. ## Port vs. Jellyfish: Engineering Intelligence Compared DevFeed: [Port vs. Jellyfish: Engineering Intelligence Compared]() Original publisher: [Read original article]() Author: Tomasz Skora Published: 2026-09-15T12:02:54Z Content type: comparison Language: en Sources: [Developer Experience & Platform Engineering Blog | Port]() Topics: [Software Engineering](), [Developer experience](), [dora metrics](), [AI Strategy](), [code productivity]() Tags: [ai-adoption](), [compare](), [devex](), [dora-metrics](), [engineering](), [software-engineering](), [workflows]() ### AI overview A comparison of Port and Jellyfish as Engineering Intelligence platforms. Jellyfish focuses on analytics and decision support for engineering performance, investment, developer experience, and AI impact, while Port connects findings to software context, owners, standards, and governed workflows so teams can act and measure outcomes. ### Source excerpt Compare Port and Jellyfish across Engineering Intelligence, AI impact, DevEx, software context, governed workflows, and measurable outcomes. ## Claude Managed Agents: How They Work and Where They Fit DevFeed: [Claude Managed Agents: How They Work and Where They Fit]() Original publisher: [Read original article]() Author: Matar Peles Published: 2026-09-14T11:29:41Z Content type: article Language: en Sources: [Developer Experience & Platform Engineering Blog | Port]() Topics: [Agent Harness](), [Claude](), [Artificial Intelligence](), [sdlc](), [context window](), [Network](), [Processes]() Tags: [agent](), [agents](), [ai](), [claude](), [context-window](), [infrastructure](), [network](), [platform](), [sandbox](), [sdlc](), [software](), [tools]() ### AI overview This article explains Claude Managed Agents, a hosted runtime and managed agent harness operated by Anthropic. It describes how the harness coordinates tools and execution, the sandbox provides isolated command and file access, and the session preserves durable task history outside the model's context window. It also discusses the additional platform layer needed to connect multiple agents across a business process and the SDLC. ### Source excerpt What Claude Managed Agents are, how the runtime works, and how platform teams connect several agents across the SDLC. ## Agent Harness vs Platform Harness: Why Teams Need Both DevFeed: [Agent Harness vs Platform Harness: Why Teams Need Both]() Original publisher: [Read original article]() Author: Zohar Einy Published: 2026-09-10T04:47:42Z Content type: article Language: en Sources: [Developer Experience & Platform Engineering Blog | Port]() Topics: [Agent Harness](), [AI Engineering](), [AI Agent](), [Orchestration](), [Software]() Tags: [agentic](), [ai-agent](), [ai-engineering](), [article](), [governance](), [memory](), [orchestration](), [platform](), [tools]() ### AI overview This article distinguishes between an agent harness, which wraps a model with prompts, tools, orchestration, memory, and guardrails, and a platform harness, which adapts an agent to an organization's systems, standards, skills, tools, and governance requirements. It explains why teams need both layers and why vendor-agent adopters should build the platform harness first. ### Source excerpt Agent harness vs platform harness: what each layer covers, who owns it, what breaks when you have only one, and why you need both. ## What does DX do? Key features, use cases, and alternatives DevFeed: [What does DX do? Key features, use cases, and alternatives]() Original publisher: [Read original article]() Author: John Crowley Published: 2026-09-09T15:53:52Z Content type: article Language: en Sources: [Developer Experience & Platform Engineering Blog | Port]() Topics: [code productivity](), [developer-productivity](), [Developer experience](), [atlassian](), [Git](), [Instrumentation](), [sdlc](), [Artificial Intelligence]() Tags: [agentic](), [ai](), [atlassian](), [developer-experience](), [developer-productivity](), [engineering](), [git](), [instrumentation](), [metrics](), [sdlc](), [survey]() ### AI overview This article explains what DX does as an engineering intelligence platform. DX measures developer productivity, developer experience, delivery data, and AI's impact on codebases using developer surveys and data from Git and Jira. It describes DX's DevEx Cloud, DX Data Cloud, DX AI, and Fabric offerings, along with their research-backed metrics, use cases, limitations, and alternatives. ### Source excerpt What DX does: its engineering intelligence features, survey-based metrics, common use cases, where it stops, and the alternatives ## Bring Claude and Cursor Coding Agents Into Your Port Catalog DevFeed: [Bring Claude and Cursor Coding Agents Into Your Port Catalog]() Original publisher: [Read original article]() Author: Sagi Keren Published: 2026-09-07T13:53:22Z Content type: article Language: en Sources: [Developer Experience & Platform Engineering Blog | Port]() Topics: [cursor](), [coding](), [Claude](), [AI-assisted coding](), [Orchestration](), [Automation]() Tags: [agents](), [ai](), [automation](), [claude](), [cloud](), [coding-agents](), [cursor](), [governance](), [workflows]() ### AI overview The article explains how Port integrates Claude and Cursor coding agents into a centralized catalog. It focuses on governance, ownership, auditing, workflow integration, and self-service creation through governed templates. ### Source excerpt Port catalogs, creates, and triggers Claude and Cursor coding agents, giving platform teams one governed registry for AI agents. ## Agentic Software Engineering Platform: Definition, Capabilities DevFeed: [Agentic Software Engineering Platform: Definition, Capabilities]() Original publisher: [Read original article]() Author: Aaron Taylor Published: 2026-09-07T12:48:46Z Content type: article Language: en Sources: [Developer Experience & Platform Engineering Blog | Port]() Topics: [Software Engineering](), [AI Development](), [sdlc](), [Orchestration](), [Model Context Protocol](), [CI/CD](), [real-time](), [Slack]() Tags: [agentic](), [ai](), [ai-agents](), [ci-cd](), [mcp](), [orchestration](), [platforms](), [sdlc]() ### AI overview The article defines an Agentic Software Engineering Platform as infrastructure that enables AI agents and developers to work safely across the software development lifecycle. It describes a unified engineering context layer, workflow orchestration, governance, MCP connections, CI/CD integration, and ways to demonstrate return on investment. ### Source excerpt Learn what an Agentic Software Engineering Platform is, its five core capabilities, when to adopt one, and how to measure its ROI. ## AgentOps: How to build AI agents at scale DevFeed: [AgentOps: How to build AI agents at scale]() Original publisher: [Read original article]() Author: Matar Peles Published: 2026-09-06T18:44:36Z Content type: tutorial Language: en Sources: [Developer Experience & Platform Engineering Blog | Port]() Topics: [AI Agent](), [Artificial Intelligence](), [Provisioning](), [Authorization](), [Cloud]() Tags: [agents](), [ai](), [ai-agents](), [best-practices](), [build-ai-agents](), [developer](), [how-to](), [platform](), [provisioning](), [workflow]() ### AI overview This article presents AgentOps as the practice of creating, running, and operating AI agents reliably in production and at scale. It recommends governing agents throughout their lifecycle, starting with an agent registry and a standardized golden-path workflow for creating new agents. The proposed workflow captures an agent's purpose and dependencies, obtains approval for sensitive access, creates scoped service accounts with minimum permissions, provisions the agent on a selected platform, and registers it. ### Source excerpt AgentOps is the practice of running AI agents reliably at scale. See what it covers, which teams own it, and where to start. ## How Every Team Can Build in Port at Scale, Without the Bottleneck DevFeed: [How Every Team Can Build in Port at Scale, Without the Bottleneck]() Original publisher: [Read original article]() Author: Guy Berman Published: 2026-09-03T14:39:07Z Content type: article Language: en Sources: [Developer Experience & Platform Engineering Blog | Port]() Topics: [Authorization](), [Scalability](), [sdlc](), [pull-requests](), [Security]() Tags: [agent](), [agentic](), [compliance](), [dashboards](), [development](), [production](), [pull-requests](), [scalability](), [scale](), [sdlc](), [security](), [workflow]() ### AI overview The article explains how every team can build and own a scoped part of Port at scale. It presents fine-grained permissions, role-based access controls, and controlled promotion across development, staging, and production environments as ways to reduce platform-team bottlenecks while limiting risk. ### Source excerpt How every team can build in Port at scale: scoped permissions, dynamic policies, and safe rollouts across environments. ## What Is Bmad? Understanding the Bmad Loop and how to scale It DevFeed: [What Is Bmad? Understanding the Bmad Loop and how to scale It]() Original publisher: [Read original article]() Author: Yonatan Boguslavski Published: 2026-09-01T08:40:17Z Content type: tutorial Language: en Sources: [Developer Experience & Platform Engineering Blog | Port]() Topics: [Agile](), [AI Development](), [AI-assisted coding](), [Open Source](), [Software Engineering](), [agent observability]() Tags: [agentic](), [ai](), [ai-agents](), [ai-coding](), [autonomous](), [coding](), [coding-agents](), [development](), [open-source](), [review](), [testing]() ### AI overview This article explains the BMAD method, an open source framework for AI-driven software development, and its BMad Loop for unattended story-by-story implementation, review, testing, and commits. ### Source excerpt Learn how the BMAD method runs agentic software development, from AI-driven planning to autonomous coding, review, and commits. ## AI Skills Adoption: How to Measure Reuse and Engineering Impact DevFeed: [AI Skills Adoption: How to Measure Reuse and Engineering Impact]() Original publisher: [Read original article]() Author: Tomasz Skora Published: 2026-08-31T08:53:02Z Content type: article Language: en Sources: [Developer Experience & Platform Engineering Blog | Port]() Topics: [Artificial Intelligence](), [incident](), [Pull Request](), [migration]() Tags: [ai](), [engineering](), [how-to](), [incident](), [migration](), [projects](), [pull-request](), [review](), [skills](), [workflow]() ### AI overview The article explains how to evaluate the value of AI Skills as they spread through engineering organizations. It recommends measuring adoption first, then examining consistency and reuse, and finally connecting Skill usage to improvements in the engineering work those Skills are intended to support. ### Source excerpt AI Skills adoption is only the starting point. See how consistency, reuse, and engineering context reveal which Skills matter. ## Implementing the Anthropic AI-Native SDLC Playbook: How to get it right DevFeed: [Implementing the Anthropic AI-Native SDLC Playbook: How to get it right]() Original publisher: [Read original article]() Author: Yonatan Boguslavski Published: 2026-08-28T16:15:46Z Content type: article Language: en Sources: [Developer Experience & Platform Engineering Blog | Port]() Topics: [anthropic](), [sdlc](), [Platform Engineering](), [Agent Harness](), [Artificial Intelligence](), [AI-assisted coding]() Tags: [agentic](), [ai](), [anthropic](), [monitor](), [platform](), [platform-engineering](), [sdlc](), [tooling]() ### AI overview The article explains how to implement Anthropic's AI-native SDLC playbook at organizational scale. It describes agents contributing across the software lifecycle, producing artifacts from intent and specifications through plans, pull requests, and production, with governance, human judgment, orchestration, and monitoring built into a platform foundation. ### Source excerpt Implement Anthropic's AI-native SDLC playbook. Learn the key requirements and foundation needed to run agentic SDLC at scale. ## Port Workflows: Orchestrate Agents, Approvals, and Automations DevFeed: [Port Workflows: Orchestrate Agents, Approvals, and Automations]() Original publisher: [Read original article]() Author: Dor Meiri Published: 2026-08-28T12:34:07Z Content type: article Language: en Sources: [Developer Experience & Platform Engineering Blog | Port]() Topics: [Orchestration](), [Automation](), [Low code](), [CI/CD](), [incident]() Tags: [agents](), [automation](), [ci-cd](), [incident](), [low-code](), [orchestration](), [workflows]() ### AI overview Port Workflows is an orchestration layer that combines agents, automations, business rules, and human approvals in a governed flow using shared, real-time context. It is designed to reduce context loss, platform-team bottlenecks, and delays in incident approvals, while enabling non-engineering teams to build and edit workflows with a low-code builder. ### Source excerpt Port Workflows chains AI agents, automations, and human approvals into one governed flow. Features, use cases, and how to start. ## AI Software Factory: What It Is, Why You Need One, Who Owns It DevFeed: [AI Software Factory: What It Is, Why You Need One, Who Owns It]() Original publisher: [Read original article]() Author: Zohar Einy Published: 2026-08-25T12:53:22Z Content type: article Language: en Sources: [Developer Experience & Platform Engineering Blog | Port]() Topics: [Artificial Intelligence](), [sdlc](), [Platform Engineering](), [DevOps]() Tags: [ai](), [devops](), [incident](), [platform-engineering](), [pull-requests](), [sdlc](), [testing]() ### AI overview The article argues that AI coding assistants alone do not improve end-to-end delivery because review, testing, and incident work can remain bottlenecks. It proposes an AI software factory that orchestrates agents, shared context, governance, and measurement across the SDLC. ### Source excerpt Discover what an AI software factory is, why it beats coding assistants, and who owns it in your engineering organization today. ## Product Release Notes - July 2026 DevFeed: [Product Release Notes - July 2026]() Original publisher: [Read original article]() Author: Matan Grady Published: 2026-08-20T08:13:19Z Content type: release Language: en Sources: [Developer Experience & Platform Engineering Blog | Port]() Topics: [AI Agent](), [Artificial Intelligence](), [Claude](), [anthropic](), [dashboards](), [Model Context Protocol](), [sdlc](), [Single sign-on (SSO)](), [pull-requests]() Tags: [2026](), [agent](), [agentic](), [agents](), [ai](), [ai-agent](), [anthropic](), [claude](), [dashboards](), [events](), [integration](), [integrations](), [mcp](), [product](), [product-release](), [pull-requests](), [release](), [release-notes](), [sdlc](), [workflows]() ### AI overview Port's July 2026 release notes describe expanded Port AI capabilities for planning and executing approved platform changes. The release adds agentic catalog actions, Ask, Plan, and Build modes, dashboard creation tools, inline integration setup, structured clarifying questions, visible reasoning, Claude Managed Agents integration, conversational onboarding, Survey Intelligence, and end-to-end SSO administration. ### Source excerpt July brings Port AI's biggest step yet toward taking action on your behalf -- from an AI Agent that can create blueprints and trigger workflows, to AI-guided conversational onboarding that sets up new orgs automatically, plus a brand new way to capture team sentiment with Survey Intelligence. Here's everything that's new in Port this month. ## What Does Xirp Do? Key Features, Use Cases, and Alternatives DevFeed: [What Does Xirp Do? Key Features, Use Cases, and Alternatives]() Original publisher: [Read original article]() Author: Zohar Einy Published: 2026-08-18T14:34:23Z Content type: article Language: en Sources: [Developer Experience & Platform Engineering Blog | Port]() Topics: [AI-assisted coding](), [codex](), [Claude Code](), [macOS](), [internal developer portal](), [Backstage](), [MCP](), [sdlc](), [Command-line interface](), [Code]() Tags: [agentic](), [ai-coding-agents](), [backstage](), [claude-code](), [codex](), [coding-agents](), [gemini](), [macos](), [mcp](), [sdlc](), [software-catalog]() ### AI overview Xirp is Spotify's macOS desktop app for running Claude Code, Codex, and Gemini in parallel persistent terminal sessions. It provides isolated git worktrees, preserves session context when switching agents, and can connect to Spotify Portal so agents receive software catalog context through MCP. ### Source excerpt Xirp is Spotify's app for running AI coding agents in parallel sessions. What it does, when to use it, and the main alternatives. ## Introducing the Port plugin for coding agents DevFeed: [Introducing the Port plugin for coding agents]() Original publisher: [Read original article]() Author: Matan Grady Published: 2026-08-11T17:29:31Z Content type: article Language: en Sources: [Developer Experience & Platform Engineering Blog | Port]() Topics: [AI-assisted coding](), [MCP](), [MCP Server](), [Claude Code](), [cursor](), [codex](), [pull-requests](), [Kubernetes]() Tags: [agents](), [automation](), [claude-code](), [codex](), [coding-agents](), [copilot](), [cursor](), [deployment](), [kubernetes](), [mcp](), [mcp-server](), [pull-requests]() ### AI overview Port introduces a plugin for coding agents that packages Port Skills and connects an up-to-date Port MCP server. The plugin gives Claude Code, Cursor, Codex, Copilot, and other coding agents guidance for using Port, reducing repeated tool experimentation and context usage while applying Port's best practices. Examples include building Kubernetes pod self-healing workflows, extending blueprints with deployment-frequency data, and creating ticket-resolution flows that turn Jira tickets into pull requests. ### Source excerpt Give your coding agent the context to work with Port: install the official Port plugin. ## How Platform Engineers Enforce Engineering Standards With AI DevFeed: [How Platform Engineers Enforce Engineering Standards With AI]() Original publisher: [Read original article]() Author: Etay Alony Published: 2026-08-11T12:00:07Z Content type: article Language: en Sources: [Developer Experience & Platform Engineering Blog | Port]() Topics: [AI Agent](), [Platform Engineering](), [Pull Request](), [sdlc](), [changelog]() Tags: [agentic](), [agents](), [ai](), [ai-agent](), [ai-agents](), [building](), [coding-agents](), [developer](), [engineering](), [platform](), [platform-engineering](), [pull-request](), [review](), [scale](), [sdlc]() ### AI overview The article explains how platform engineering teams can use AI agents to enforce engineering standards across many repositories. Agents inspect scorecards, identify noncompliant services, implement fixes, and open pull requests for service owners to review, allowing platform engineers to focus on exceptions and governance. It also introduces five practices for scaling this approach safely, including providing agents with accurate organizational context and safeguards. ### Source excerpt How platform teams use AI agents to enforce engineering standards across hundreds of repos, and the five foundations it needs. ## Port's Integration Catalog: 200+ Tools for Your Context Lake DevFeed: [Port's Integration Catalog: 200+ Tools for Your Context Lake]() Original publisher: [Read original article]() Author: Alina Barenboim Published: 2026-08-10T16:27:08Z Content type: article Language: en Sources: [Developer Experience & Platform Engineering Blog | Port]() Topics: [CI/CD](), [Kubernetes](), [GitHub](), [Provisioning](), [incident management](), [Application Performance Management (APM)](), [Security](), [Code review](), [Deployment](), [DevOps](), [GitHub Actions](), [GitLab]() Tags: [apm](), [ci-cd](), [deployment](), [devops](), [git](), [github](), [github-actions](), [gitlab](), [incident-management](), [jenkins](), [kubernetes](), [review](), [security](), [vulnerabilities]() ### AI overview Port's Integration Catalog describes more than 200 integrations that unify engineering-tool data in a queryable Context Lake. It covers Git, Kubernetes, CI/CD, incident management, APM, security scanning, service mesh, policy violations, deployments, build results, and code activity, with support for custom integrations through Ocean, connectors, APIs, events, and MCPs. ### Source excerpt Explore Port's 200+ integrations across CI/CD, Kubernetes, incident management, security, and more, all feeding one Context Lake. ## How HoneyBook uses Port to serve engineering & agents across the AI SDLC? DevFeed: [How HoneyBook uses Port to serve engineering & agents across the AI SDLC?]() Original publisher: [Read original article]() Author: Zohar Einy Published: 2026-08-10T14:26:14Z Content type: article Language: en Sources: [Developer Experience & Platform Engineering Blog | Port]() Topics: [sdlc](), [DevOps](), [Deployment](), [Automation](), [GitHub](), [Tooling]() Tags: [agents](), [ai-agents](), [automation](), [deployment](), [developers](), [devops](), [engineering](), [github](), [platform](), [production](), [sdlc](), [workflows]() ### AI overview HoneyBook moved deployment, rollback, and new-service creation workflows onto Port so developers could perform routine platform tasks themselves. The self-service flows expose service state, Argo CD health, production commits, logs, and rollback actions while enforcing deployment safeguards such as end-to-end test completion and manager approval for bypasses. HoneyBook is also extending these workflows to AI agents. ### Source excerpt See how HoneyBook turned deploys, rollbacks, and new-service creation into self-service flows with Port - and is extending them to AI agents. ## Why every engineering org needs an agentic registry DevFeed: [Why every engineering org needs an agentic registry]() Original publisher: [Read original article]() Author: Matar Peles Published: 2026-08-10T11:43:10Z Content type: article Language: en Sources: [Developer Experience & Platform Engineering Blog | Port]() Topics: [Agent Skill](), [MCP](), [cursor](), [Azure](), [bedrock](), [site-reliability-engineering]() Tags: [agent-skill](), [agentic](), [agents](), [azure](), [bedrock](), [coding](), [governance](), [mcp](), [slack](), [workflows]() ### AI overview The article argues that engineering organizations need an agentic registry to manage the rapid growth of agents and skills. It describes registries for SKILL.md files, deployed agents, and approved MCP servers, with capabilities for discovery, standardization, governance, and workflow composition. ### Source excerpt Why every engineering org needs an agentic registry ## Practical AI in Platform Engineering: lessons from Port's latest meetup DevFeed: [Practical AI in Platform Engineering: lessons from Port's latest meetup]() Original publisher: [Read original article]() Author: Matar Peles Published: 2026-08-10T11:42:45Z Content type: article Language: en Sources: [Developer Experience & Platform Engineering Blog | Port]() Topics: [Platform Engineering](), [Artificial Intelligence](), [AI-assisted coding](), [Code review](), [sdlc](), [Code generation](), [Incident response](), [Infrastructure as code](), [Security](), [vulnerability]() Tags: [agentic](), [ai](), [ai-coding](), [engineering](), [iac](), [ide](), [incident-response](), [platform-engineering](), [review](), [sdlc](), [security](), [testing]() ### AI overview Port's Tel Aviv meetup examined how engineering organizations are adopting AI in platform engineering. Speakers discussed agentic workflows for bug triage, platform requests, and the SDLC, while an anonymous survey measured AI maturity, production deployments, evaluation practices, human oversight, and concerns about autonomy. Most teams reported having a few SDLC agents but not scaling them broadly; code review and code generation were the most common production uses, while operational applications such as infrastructure, security, and incident response lagged behind. ### Source excerpt We hosted a meetup with engineering leaders working on AI inside their orgs and ran an anonymous survey. Here's what came out of it. ## Agentic SDLC in Practice: Insights from Engineering Leaders DevFeed: [Agentic SDLC in Practice: Insights from Engineering Leaders]() Original publisher: [Read original article]() Author: Matar Peles Published: 2026-08-10T11:42:34Z Content type: article Language: en Sources: [Developer Experience & Platform Engineering Blog | Port]() Topics: [sdlc](), [Artificial Intelligence](), [AI Agent](), [Platform Engineering](), [Model Context Protocol](), [MCP Server](), [incident](), [Data Quality](), [Amazon Bedrock](), [Slack](), [cursor](), [Pull Request]() Tags: [agent](), [agentic](), [agents](), [ai](), [ai-agent](), [bedrock](), [coding](), [cursor](), [data-quality](), [engineering](), [incident](), [mcp](), [mcp-server](), [platform-engineering](), [python](), [review](), [sdlc](), [server](), [slack](), [workflow]() ### AI overview Engineering leaders share practical examples of an agentic SDLC, including autonomous Jira ticket resolution through pull request creation and AI-powered incident triage. The article highlights adoption challenges such as siloed agents, missing governance, and the need for a shared registry of agents, skills, and MCPs. ### Source excerpt Engineering leaders share how agentic SDLC works in practice: what scales adoption, where teams get stuck, and how to maximize AI ROI. ## The Agentic SDLC: The Software Lifecycle, Rebuilt Around Agents DevFeed: [The Agentic SDLC: The Software Lifecycle, Rebuilt Around Agents]() Original publisher: [Read original article]() Author: Zohar Einy Published: 2026-08-10T11:42:24Z Content type: article Language: en Sources: [Developer Experience & Platform Engineering Blog | Port]() Topics: [AI Agent](), [sdlc](), [AI Development](), [Platform Engineering](), [coding](), [Deployment](), [pull-requests]() Tags: [agentic](), [agents](), [coding](), [deployment](), [platform-engineering](), [pull-request](), [sdlc](), [testing]() ### AI overview This guide explains the agentic SDLC, a software development lifecycle in which AI agents lead work across planning, coding, testing, review, release, production operations, and incident response. Engineers define intent, review outcomes, and govern the process. It emphasizes that scaling from one agent to many requires context, human oversight, guardrails, visibility, and measurable ROI. ### Source excerpt Explore the Agentic SDLC, a software lifecycle rebuilt around smart agents to accelerate planning, coding, testing, and deployment. ## AI SDLC: A Practical Guide to SDLC AI Agents DevFeed: [AI SDLC: A Practical Guide to SDLC AI Agents]() Original publisher: [Read original article]() Author: Zohar Einy Published: 2026-08-10T11:41:56Z Content type: article Language: en Sources: [Developer Experience & Platform Engineering Blog | Port]() Topics: [AI Development](), [sdlc](), [Artificial Intelligence](), [ai-coding](), [coding](), [Software Engineering]() Tags: [ai](), [ai-agents](), [ai-coding](), [coding](), [developer](), [guide](), [sdlc](), [software-development](), [workflows]() ### AI overview A practical guide to using AI agents across the software development lifecycle. It explains how agents differ from coding assistants, describes an agentic SDLC in which agents perform multi-step engineering work while humans review and approve, and introduces organizational options for adopting it. ### Source excerpt Learn how AI agents support the SDLC, improve developer workflows, and help teams build, test, and ship software faster. [Next page]()