AI Development & Programming: Build Apps with AI

Claude Code suddenly stops with "log in again," "rate limit," "prompt is too long," "MCP won't connect" — and googling each one gets tedious. This is a practical reference that catalogs the errors you commonly hit, with the cause and the command to run for each. It starts with the three diagnostic commands to run first (claude doctor for full diagnostics, /status for active auth, /context for the context breakdown), then focuses on the four common families (usage/rate limits, context overflow, expired auth, MCP connection failures) with symptom→cause→fix-command tables across auth & login, usage/rate limits (one debugging session can use more than a day of chat), context & tokens (prompt too long, compaction thrashing), server & model (500/529/timeout/model not found), install/PATH/update, network & proxy (ECONNREFUSED, TLS), MCP, permissions (deny beats bypass), and misc (thinking blocks 400, image/PDF, IDE). It ends with an error→fix cheat sheet and FAQ. Based on the official Claude Code docs (as of 2026): when stuck run the three diagnostic commands, and if it is not fixed, run claude update.

Cursor, Claude Code, GitHub Copilot, and Codex used to be explained by type: editor, plugin, CLI, and cloud. But when we reread all four vendors' official documentation on September 22, 2026, every one of them runs in the terminal, the IDE, a desktop app, the cloud, and on your phone, and they even run inside one another. This article lays out, with sources, the three things that now set them apart: available models (Cursor and Copilot span multiple vendors, Claude Code is Claude only, Codex is OpenAI only), how pricing and usage are counted (free tiers, monthly prices from Go at $8 up to $200, monthly allowances versus 5-hour and weekly limits, and how you pay when you go over), and home base (their own editor, GitHub, and the Claude and ChatGPT subscriptions). It also covers the differences in GitHub PRs and reviews, how to choose across eight scenarios, how to use them together, and a 30-minute way to compare them on your own repository. Errors in the previous version, such as "Copilot is the cheapest" and "about 4x more token-efficient," are corrected at the end.

You finish a feature in Claude Code and go to press "Create PR" when a red banner appears: "Pull request status couldn’t be checked and may be out of date." This is not a code defect — Claude Code simply reached out to GitHub to fetch the latest PR state and that one request failed, and it is usually a harmless sync delay. This article covers the exact meaning of the error, how Claude Code fetches PR state according to the official docs and CHANGELOG (the desktop app requires gh; the terminal PR badge normally uses gh pr view), the 6 root causes (gh not installed, not signed in or token revoked, no push/PR yet, network/proxy, PAT permissions, transient), a 4-step diagnostic order starting from gh --version and gh auth status, a command cheat sheet (gh auth login/refresh/pr view and more), how to tell when "may be out of date" is safe to ignore vs. when to act, the gh pr create workaround, a recurrence-prevention checklist, and an FAQ. The rule: suspect the GitHub connection before you suspect the code.

You are working in Claude Code when suddenly a 400 error appears and every subsequent input repeats it: "thinking or redacted_thinking blocks in the latest assistant message cannot be modified." This is a known bug with multiple open issues on Anthropic's official repository, and in most cases it is not the user's fault. This article covers what the error means, how extended thinking's thinking blocks and cryptographic signatures work, the 5 root causes of signature mismatch (session-resume bug, streaming interleaving, repair logic going rogue, third-party proxies, history modification in your own app), 3 recovery fixes for Claude Code users (Esc x2/rewind, new session /clear, JSONL-repair tool), the most important permanent fix (update to the latest version), prevention for API/SDK developers (send assistant turns back as-is, thinking blocks included, and keep the history append-only), how to tell it apart from 3 similar errors, and a recurrence-prevention checklist — all current as of 2026.

GitHub Copilot launched in 2021 as smart code completion; by 2026 it is something else. Assign it a single GitHub Issue and walk away, and the AI writes the code, passes the tests, opens a pull request, and hands it back — Copilot cloud agent (formerly Copilot coding agent). GitHub Copilot is an AI coding-assistance service from GitHub (owned by Microsoft), with three ways to use it: completion, chat, and agent. Its defining trait is installing as an extension into existing editors like VS Code and JetBrains — you add AI without changing your usual editor. This article covers what Copilot can do, the 2026 headliner that is Agent Mode and the cloud agent, Free/Pro $10/Pro+ $39/Max $100 pricing and the June 2026 shift to usage-based billing (AI credits), how it differs from Cursor and Claude Code, who it fits, and how to get started — all with the latest information.

The six phases of system development, from requirements to operations, barely changed for over 20 years, but they were rewritten in 2025 and 2026. Gartner predicts that by 2028, 90% of enterprise software engineers will use AI coding assistants. This article covers how time weighting shifts across each phase, the major tools, the quality issue where 43% of AI-generated changes need production debugging, the move from Waterfall to Agile to AI-Native, seven role transformations, and three pitfalls, based on facts as of May 2026. It argues that "engineers who only write code" face the biggest career risk from 2027 on.

In 2025, one role's job-posting count grew by an extraordinary 1,165% year over year: the FDE — the Forward Deployed Engineer. Why has a quiet job that Palantir systematized over roughly 20 years suddenly become "the hottest title" in 2026? An FDE is "an engineer who carries their own company's product into the customer's site and personally owns observation, design, implementation, operation, and product feedback end to end." Generative AI carries a last mile of "the demo works but it doesn't work on site," and the FDE is the role that closes it with human hands. This article covers the definition, why the role exploded in 2026 (the OpenAI, Anthropic, and Google hiring rush), the 5-stage work loop, pay and career (Palantir median $278K, highest reported $620K), the difference from SE / IT consultant / Applied AI Engineer, who fits and who does not, and how to get there from no experience — all with data as of October 2026.

Vercel MCP, the Vercel Plugin, and Agent Skills sound alike but are different things. MCP is a remote server you connect to with OAuth that exposes deployments, logs, and env vars as tools; the Plugin adds five commands such as /vercel-plugin:deploy plus Vercel knowledge; Skills are instructions. Written after re-reading the official docs on September 30, 2026, this article gives a comparison table of the Git integration, CLI, MCP, Plugin, and Skills (what each does, how it authenticates, plan conditions), then walks through three approaches with working config: ① Git integration (auto-deploy on git push), ② straight from the editor (MCP and Plugin), and ③ GitHub Actions (@claude fixes, test and approval gates). It also covers avoiding double deploys from Actions, the Hobby limit of 100 deployments a day, plan conditions for password protection, rollback, and human approval for production.

Type "build me a Todo app" and you get a running preview and a public URL: that's "vibe coding," and its best-known tools are Vercel's v0, StackBlitz's Bolt.new and Lovable. Checked against all three pricing pages and official docs on September 30, 2026, this guide covers each tool's essence in three lines (v0 = designer, Bolt = developer, Lovable = founder), pricing and free tiers (counted in messages, tokens and credits respectively), the code each generates (Next.js / any JS framework / TanStack Start), databases and Figma support (all three have it), six use cases, what the official docs reveal, three production pitfalls, what you can take with you when you switch, and a 5-minute decision flow.

You shipped on the OpenAI API and now want to try Claude and Gemini — and you've burned two hours rewriting against three different SDKs. The Vercel AI SDK (just "AI SDK" since 2026) collapses that into "one import, one function, every provider," with 20M+ monthly downloads and AI SDK 6 shipping Agents, MCP, tool approval, and DevTools — the de facto standard for unified LLM interfaces in 2026. This article covers what the AI SDK is, three practical reasons to use it (free switching, 1/3 the implementation, type safety), a 5-minute quickstart from generateText to streamText, type-safe structured output via generateObject and Zod, tool calling and agent loops, a 10-line React chat UI with useChat, switching between Claude/GPT/Gemini in 3 lines, and the three production pitfalls (provider feature gaps, stream-abort billing, type-inference overload) — all with working code grounded in AI SDK 6 as of May 2026.

Ask Claude Code or ChatGPT where to deploy and you'll almost always hear "push it to Vercel." For a non-commercial Next.js site, starting on the free Hobby plan is fine — but ads, sales or paid client work make it commercial, which requires Pro. Hobby stops features at its limits; Pro keeps running and bills on demand. This article covers why AI recommends Vercel, six questions to decide, the Hobby vs Pro terms (transfer, function duration, deployments, Spend Management), four alternatives (Cloudflare, Netlify, Render, your own VPS) and three beginner traps — all checked against Vercel's official documentation as of October 1, 2026.

Environment setup is where every beginner programmer gets stuck. In 2026, generative AI (Claude Code, Codex, Cursor) is genuinely usable for routine infrastructure work — local environment setup, Dockerfile generation, Terraform drafts, CI/CD pipelines. HashiCorp released its official Terraform MCP Server in 2025 (generally available since June 2026), and Anthropic released Agent Skills so infrastructure expertise can be loaded on demand. But "delegate everything" is a different question: a $3,000 month-end AWS bill, a production DB accidentally made public, an SSH key committed to GitHub — all incidents that can happen when you hand everything off. This article splits five safe-to-delegate areas, three "verify-then-trust" risk zones, four human-only areas, a four-step beginner-safe workflow, and the latest 2026 tooling (Claude Code, MCP, Agent Skills) — focused on capability evaluation, not career impact.