<?xml version="1.0" encoding="UTF-8"?><rss version="2.0"><channel><title>Restato Labs</title><description>Reviewed software engineering articles from Restato Labs, drawn from build pipelines, deployments and developer tooling we operate, and from primary sources we read and verify ourselves.</description><link>https://blog.restatolabs.com/</link><item><title>Claude Code vs Codex, Cursor, and GitHub Copilot: Choose by Workflow, Not Model Hype</title><link>https://blog.restatolabs.com/claude-code-comparison-guide/</link><guid isPermaLink="true">https://blog.restatolabs.com/claude-code-comparison-guide/</guid><description>Compare coding agents by execution surface, repository control, parallelism, GitHub delivery, customization, and verification responsibility, then choose a practical tool stack.</description><pubDate>Sun, 09 Aug 2026 00:00:00 GMT</pubDate><category>Claude Code</category><category>Codex</category><category>Cursor</category><category>GitHub Copilot</category><category>Developer Tools</category></item><item><title>Claude Code Context, Models, Limits, and Cost: A Diagnostic Guide</title><link>https://blog.restatolabs.com/claude-code-context-model-cost-guide/</link><guid isPermaLink="true">https://blog.restatolabs.com/claude-code-context-model-cost-guide/</guid><description>Diagnose context pressure, model capability, latency, usage limits, command runtime, and cost in Claude Code without relying on stale thresholds or pricing shortcuts.</description><pubDate>Sun, 09 Aug 2026 00:00:00 GMT</pubDate><category>Claude Code</category><category>Context Window</category><category>Models</category><category>Cost</category><category>Performance</category></item><item><title>Claude Code Git and Parallel Workflows: Branches, Worktrees, Subagents, and Safe Integration</title><link>https://blog.restatolabs.com/claude-code-git-parallel-workflows/</link><guid isPermaLink="true">https://blog.restatolabs.com/claude-code-git-parallel-workflows/</guid><description>Choose between one session, subagents, agent teams, and Git worktrees; isolate writes, preserve user changes, and integrate parallel Claude Code work through reviewable commits and pull requests.</description><pubDate>Sun, 09 Aug 2026 00:00:00 GMT</pubDate><category>Claude Code</category><category>Git</category><category>Worktrees</category><category>Subagents</category><category>Parallel Development</category></item><item><title>Claude Code Hooks, MCP, and Automation: Build a Verifiable Agent Harness</title><link>https://blog.restatolabs.com/claude-code-hooks-mcp-automation/</link><guid isPermaLink="true">https://blog.restatolabs.com/claude-code-hooks-mcp-automation/</guid><description>Choose the right Claude Code extension mechanism, write fail-safe hooks, constrain MCP trust, and run headless or GitHub Actions workflows with deterministic validation.</description><pubDate>Sun, 09 Aug 2026 00:00:00 GMT</pubDate><category>Claude Code</category><category>Hooks</category><category>MCP</category><category>Automation</category><category>GitHub Actions</category></item><item><title>Claude Code Permissions and Security: Authentication, Rules, Sandboxing, and Secrets</title><link>https://blog.restatolabs.com/claude-code-permissions-security-guide/</link><guid isPermaLink="true">https://blog.restatolabs.com/claude-code-permissions-security-guide/</guid><description>Separate authentication from authorization, grant Claude Code minimum task authority, combine permission rules with sandboxing, and protect secrets in local and automated workflows.</description><pubDate>Sun, 09 Aug 2026 00:00:00 GMT</pubDate><category>Claude Code</category><category>Security</category><category>Permissions</category><category>Sandbox</category><category>Secrets</category></item><item><title>Claude Code Setup Guide: Install, Authenticate, and Complete a Safe First Task</title><link>https://blog.restatolabs.com/claude-code-setup-guide/</link><guid isPermaLink="true">https://blog.restatolabs.com/claude-code-setup-guide/</guid><description>Install Claude Code on macOS, Linux, or Windows, choose the right authentication path, verify one repository change, and add a concise project harness.</description><pubDate>Sun, 09 Aug 2026 00:00:00 GMT</pubDate><category>Claude Code</category><category>Setup</category><category>CLI</category><category>CLAUDE.md</category><category>Developer Tools</category></item><item><title>One Front Door, Many Domain Agents: The Enterprise Agent Operating Model</title><link>https://blog.restatolabs.com/one-front-door-many-domain-agents-enterprise/</link><guid isPermaLink="true">https://blog.restatolabs.com/one-front-door-many-domain-agents-enterprise/</guid><description>Decide what stays in one company assistant, what domain experts should publish as skills and tools, and when a capability deserves a separate governed agent.</description><pubDate>Thu, 06 Aug 2026 00:00:00 GMT</pubDate><category>Enterprise AI</category><category>AI Agent</category><category>Agent Platform</category><category>Governance</category><category>Multi-Agent</category></item><item><title>Building Arc Note: An Ad-Supported AI Tarot Reflection Product</title><link>https://blog.restatolabs.com/arc-note-ad-supported-ai-tarot-case-study/</link><guid isPermaLink="true">https://blog.restatolabs.com/arc-note-ad-supported-ai-tarot-case-study/</guid><description>How Arc Note separates a useful free tarot reflection from optional ad-unlocked AI detail while protecting private reading URLs.</description><pubDate>Wed, 05 Aug 2026 00:00:00 GMT</pubDate><category>product-engineering</category><category>ai</category><category>nextjs</category><category>advertising</category><category>case-study</category></item><item><title>Govern the GitHub Copilot App and Cloud Agent with Managed Settings</title><link>https://blog.restatolabs.com/github-copilot-managed-settings-governance-guide/</link><guid isPermaLink="true">https://blog.restatolabs.com/github-copilot-managed-settings-governance-guide/</guid><description>Separate Copilot app access, enterprise managed client behavior, plugin policy, and cloud-agent repository authority with a valid managed-settings rollout.</description><pubDate>Tue, 28 Jul 2026 00:00:00 GMT</pubDate><category>GitHub Copilot</category><category>AI Agent</category><category>Governance</category><category>Enterprise</category><category>Developer Tools</category></item><item><title>After GitHub Models Retirement: Migrate Inference and Remove Legacy Access</title><link>https://blog.restatolabs.com/github-models-retirement-migration-guide/</link><guid isPermaLink="true">https://blog.restatolabs.com/github-models-retirement-migration-guide/</guid><description>Recover from GitHub Models retirement by finding dependencies, choosing a replacement, validating provider behavior, and removing dead fallbacks and permissions.</description><pubDate>Tue, 28 Jul 2026 00:00:00 GMT</pubDate><category>GitHub</category><category>AI API</category><category>Microsoft Foundry</category><category>Migration</category><category>LLM</category></item><item><title>Audit Vercel Flags Rollouts with Evaluation Metrics and Version Diffs</title><link>https://blog.restatolabs.com/vercel-flags-rollout-audit-guide/</link><guid isPermaLink="true">https://blog.restatolabs.com/vercel-flags-rollout-audit-guide/</guid><description>Join Vercel Flags revision history, semantic diffs, evaluation dimensions, and application outcomes into a reviewable rollout and rollback evidence trail.</description><pubDate>Mon, 27 Jul 2026 00:00:00 GMT</pubDate><category>Vercel Flags</category><category>Feature Flags</category><category>Observability</category><category>Vercel CLI</category><category>DevOps</category></item><item><title>Vercel Sandbox Dashboard Incident Response: Observe Before You Mutate</title><link>https://blog.restatolabs.com/vercel-sandbox-dashboard-incident-response-guide/</link><guid isPermaLink="true">https://blog.restatolabs.com/vercel-sandbox-dashboard-incident-response-guide/</guid><description>Use the Sandbox dashboard to inspect, contain, and recover agent workloads without leaking secrets, destroying evidence, or reusing suspect state.</description><pubDate>Mon, 27 Jul 2026 00:00:00 GMT</pubDate><category>Vercel</category><category>Sandbox</category><category>Incident Response</category><category>Security</category></item><item><title>Vercel Blob WAF: Traffic Controls, Private Storage, and Safe Rollout</title><link>https://blog.restatolabs.com/vercel-blob-waf-security-guide/</link><guid isPermaLink="true">https://blog.restatolabs.com/vercel-blob-waf-security-guide/</guid><description>Protect public Blob traffic with shared WAF rules while keeping identity-based access in Private Blob, then roll out deny, rate limit, and challenge without breaking clients.</description><pubDate>Sun, 26 Jul 2026 00:00:00 GMT</pubDate><category>Vercel</category><category>Security</category><category>WAF</category><category>Blob Storage</category><category>Web Development</category></item><item><title>Vercel Workflow 30-Minute Steps: Design for Retry, Cancellation, and Cost</title><link>https://blog.restatolabs.com/vercel-workflow-30-minute-step-duration-guide/</link><guid isPermaLink="true">https://blog.restatolabs.com/vercel-workflow-30-minute-step-duration-guide/</guid><description>Enable 1,800-second Workflow steps safely by choosing recoverable boundaries, idempotent effects, cooperative cancellation, and bounded retry budgets.</description><pubDate>Sun, 26 Jul 2026 00:00:00 GMT</pubDate><category>Vercel</category><category>Workflow</category><category>AI Agent</category><category>Operations</category></item><item><title>Migrate to Claude Opus 5: Thinking, Effort, Prompts, and Copilot</title><link>https://blog.restatolabs.com/claude-opus-5-migration-copilot-guide/</link><guid isPermaLink="true">https://blog.restatolabs.com/claude-opus-5-migration-copilot-guide/</guid><description>Move from Claude Opus 4.8 or earlier by re-budgeting thinking, sweeping effort, updating prompts and tool assumptions, evaluating regressions, and enabling Copilot policy.</description><pubDate>Sat, 25 Jul 2026 00:00:00 GMT</pubDate><category>Claude Opus 5</category><category>Anthropic API</category><category>Claude Code</category><category>GitHub Copilot</category><category>Migration</category></item><item><title>OpenAI API Spend Limits: Layer Hard Caps with Application Controls</title><link>https://blog.restatolabs.com/openai-api-spend-limits-guide/</link><guid isPermaLink="true">https://blog.restatolabs.com/openai-api-spend-limits-guide/</guid><description>Combine OpenAI organization and project hard spend limits with early alerts, project isolation, application budget states, and bounded fallbacks.</description><pubDate>Sat, 25 Jul 2026 00:00:00 GMT</pubDate><category>OpenAI API</category><category>Cost Control</category><category>MLOps</category><category>AI Agent</category><category>Production</category></item><item><title>Operate GitHub Issues Agent Automation with Confidence, Approvals, and Safe Outputs</title><link>https://blog.restatolabs.com/github-issues-agent-automation-controls-guide/</link><guid isPermaLink="true">https://blog.restatolabs.com/github-issues-agent-automation-controls-guide/</guid><description>Roll out GitHub Issues agent automation with confidence thresholds, approval suggestions, rationale, safe-output constraints, staged previews, and action-level calibration.</description><pubDate>Fri, 24 Jul 2026 00:00:00 GMT</pubDate><category>GitHub</category><category>GitHub Issues</category><category>Copilot</category><category>Agentic Workflows</category><category>AI Agent</category><category>Automation</category><category>Human in the Loop</category><category>Security</category></item><item><title>MCP 2026-07-28 Migration Guide: Stateless Requests and Conformance CI</title><link>https://blog.restatolabs.com/mcp-2026-07-28-stateless-migration-guide/</link><guid isPermaLink="true">https://blog.restatolabs.com/mcp-2026-07-28-stateless-migration-guide/</guid><description>Migrate MCP clients and servers to stateless requests, explicit state handles, MRTR, subscriptions, cache metadata, and versioned conformance tests.</description><pubDate>Fri, 24 Jul 2026 00:00:00 GMT</pubDate><category>MCP</category><category>Model Context Protocol</category><category>AI Agent</category><category>GitHub</category><category>Protocol</category><category>Migration</category><category>Conformance Test</category></item><item><title>Streaming Transcription in Production: Audio, Tokens, and Voice-Agent Boundaries</title><link>https://blog.restatolabs.com/ai-gateway-streaming-transcription-guide/</link><guid isPermaLink="true">https://blog.restatolabs.com/ai-gateway-streaming-transcription-guide/</guid><description>A production guide to Vercel AI Gateway streaming transcription: raw PCM, browser capture, ephemeral tokens, transcript state, latency, privacy, reliability, evaluation, and voice-agent architecture.</description><pubDate>Thu, 23 Jul 2026 00:00:00 GMT</pubDate><category>Vercel</category><category>AI Gateway</category><category>AI SDK</category><category>Speech to Text</category><category>Voice Agent</category><category>Production Architecture</category></item><item><title>Enterprise LLM Strategy: Choose Models by Workload, Cost, and Control</title><link>https://blog.restatolabs.com/enterprise-llm-model-selection-platform-strategy/</link><guid isPermaLink="true">https://blog.restatolabs.com/enterprise-llm-model-selection-platform-strategy/</guid><description>A July 2026 guide to commercial and open LLMs, model size, context, GPUs, leaderboards, routing, evaluation, cost optimization, governance, and enterprise platform design.</description><pubDate>Thu, 23 Jul 2026 00:00:00 GMT</pubDate><category>LLM</category><category>Enterprise AI</category><category>Open Models</category><category>AI Platform</category><category>AI Governance</category><category>Cost Optimization</category></item><item><title>Build eve Extensions as Versioned Capability Boundaries</title><link>https://blog.restatolabs.com/eve-installable-agent-extensions-guide/</link><guid isPermaLink="true">https://blog.restatolabs.com/eve-installable-agent-extensions-guide/</guid><description>Package eve tools, connections, skills, instructions, and hooks without losing control of namespaces, secrets, approvals, runtime policy, or upgrade risk.</description><pubDate>Thu, 23 Jul 2026 00:00:00 GMT</pubDate><category>AI Agent</category><category>Vercel</category><category>eve</category><category>Agent Skills</category><category>TypeScript</category></item><item><title>Gemini 3.6 Flash Migration: API Changes, Copilot, and AI Gateway</title><link>https://blog.restatolabs.com/gemini-3-6-flash-migration-guide/</link><guid isPermaLink="true">https://blog.restatolabs.com/gemini-3-6-flash-migration-guide/</guid><description>Migrate to Gemini 3.6 Flash or 3.5 Flash-Lite by fixing deprecated sampling options, prefilled turns, thinking settings, Copilot policy, and AI Gateway IDs.</description><pubDate>Wed, 22 Jul 2026 00:00:00 GMT</pubDate><category>Gemini</category><category>Google AI</category><category>GitHub Copilot</category><category>AI SDK</category><category>Migration</category></item><item><title>Vercel AI Gateway Service Tiers: Route for Latency, Verify What You Bought</title><link>https://blog.restatolabs.com/vercel-ai-gateway-service-tiers-guide/</link><guid isPermaLink="true">https://blog.restatolabs.com/vercel-ai-gateway-service-tiers-guide/</guid><description>Choose default, priority, and flex by workload, then use applied-tier metadata and accepted-outcome cost to verify the operational result.</description><pubDate>Wed, 22 Jul 2026 00:00:00 GMT</pubDate><category>Vercel</category><category>AI Gateway</category><category>AI SDK</category><category>Operations</category></item><item><title>Astro 5 to 7.1 Migration Audit: Content Layer, Node 22, and Tailwind</title><link>https://blog.restatolabs.com/astro-5-to-7-1-migration-audit/</link><guid isPermaLink="true">https://blog.restatolabs.com/astro-5-to-7-1-migration-audit/</guid><description>Audit an Astro 5 GitHub Pages site for Node 22, Content Layer, entry API, route, and Tailwind changes before upgrading to Astro 7.1.</description><pubDate>Tue, 21 Jul 2026 00:00:00 GMT</pubDate><category>Astro</category><category>GitHub Pages</category><category>MDX</category><category>Tailwind CSS</category><category>Migration</category></item><item><title>Customize GitHub Copilot Code Review with Instructions, Setup, and Network Controls</title><link>https://blog.restatolabs.com/github-copilot-code-review-customization-guide/</link><guid isPermaLink="true">https://blog.restatolabs.com/github-copilot-code-review-customization-guide/</guid><description>Configure GitHub Copilot code review with head-branch instructions, a dedicated setup workflow, firewall rules, runner isolation, and observable review evidence.</description><pubDate>Tue, 21 Jul 2026 00:00:00 GMT</pubDate><category>GitHub Copilot</category><category>Code Review</category><category>GitHub Actions</category><category>AI Agent</category><category>Security</category></item><item><title>AI SDK 7 Production Agents: Choose the Right Runtime Boundary</title><link>https://blog.restatolabs.com/ai-sdk-7-production-agent-guide/</link><guid isPermaLink="true">https://blog.restatolabs.com/ai-sdk-7-production-agent-guide/</guid><description>Choose between ToolLoopAgent, WorkflowAgent, and HarnessAgent, then add approvals, recovery, isolation, timeouts, and observability at the right production boundary.</description><pubDate>Mon, 20 Jul 2026 00:00:00 GMT</pubDate><category>AI SDK</category><category>Vercel</category><category>AI Agent</category><category>TypeScript</category><category>Automation</category></item><item><title>Prevent Astro MDX Frontmatter Drift with Build-Time Schema Checks</title><link>https://blog.restatolabs.com/align-astro-mdx-frontmatter-with-the-live-schema/</link><guid isPermaLink="true">https://blog.restatolabs.com/align-astro-mdx-frontmatter-with-the-live-schema/</guid><description>A practical workflow for aligning generated MDX with an Astro content collection schema and catching metadata drift before publication.</description><pubDate>Mon, 20 Jul 2026 00:00:00 GMT</pubDate><category>Astro</category><category>MDX</category><category>Content Collections</category><category>Engineering</category></item><item><title>Build a GitHub Content OS for Agents: Policy, Skills, State, and Gates</title><link>https://blog.restatolabs.com/github-content-os-agent-skills-workflow/</link><guid isPermaLink="true">https://blog.restatolabs.com/github-content-os-agent-skills-workflow/</guid><description>Use GitHub as an auditable control plane for agent-assisted content by separating policy, reusable skills, editorial state, public artifacts, and publication gates.</description><pubDate>Mon, 20 Jul 2026 00:00:00 GMT</pubDate><category>Content OS</category><category>GitHub</category><category>AI Agent</category><category>Automation</category><category>Astro</category></item><item><title>GPT-5.6 Sol, Terra, and Luna: API Pricing and Migration Guide</title><link>https://blog.restatolabs.com/gpt-5-6-sol-terra-luna-api-guide/</link><guid isPermaLink="true">https://blog.restatolabs.com/gpt-5-6-sol-terra-luna-api-guide/</guid><description>Compare current GPT-5.6 model IDs, post-price-cut API rates, context and cache rules, then migrate with workload evaluations instead of a global model rename.</description><pubDate>Sun, 19 Jul 2026 00:00:00 GMT</pubDate><category>OpenAI</category><category>GPT-5.6</category><category>API</category><category>AI</category><category>Migration</category></item><item><title>YOLO Clover Detection Experiments: P2, Resolution, and Confidence Thresholds</title><link>https://blog.restatolabs.com/yolo-clover-detection-experiments/</link><guid isPermaLink="true">https://blog.restatolabs.com/yolo-clover-detection-experiments/</guid><description>A qualified first-party report on a YOLOv8 clover detector: the baseline, P2 training recipe, 640-versus-768 result, and confidence-threshold trade-offs.</description><pubDate>Sat, 17 Jan 2026 00:00:00 GMT</pubDate><category>yolo</category><category>machine-learning</category><category>deep-learning</category></item></channel></rss>