AI Development & Programming: Build Apps with AI

Many indie developers stall at "I built it, but how do I earn, and what do I charge?" This article covers, from a solo developer's point of view, how to choose a monetization model (free / one-time / subscription / freemium / ads / donations), value-based pricing that starts from "the value the customer gains" rather than cost or competitors, the Free→Pro→Business three-tier plan and the annual-discount playbook, how to land your first paying users, and unit economics that fold in AI costs such as API tokens. It goes deep on the "grow" phase of the hub article, the AI indie development roadmap.

The biggest reason indie projects never get finished is "over-building." Piling on feature after feature makes it complex, and it vanishes before it ever launches. The one way to avoid that is to narrow the smallest product that conveys value—the MVP—to a single feature and ship it as fast as possible. This article explains, from the point of view of an indie developer who makes AI their partner, the right way to see an MVP, scope decisions for cutting features, two routes to build fastest with AI (vibe coding where you write no code, and the hands-on AI-editor route), judging "finished," and getting one person to use it after launch.

Now that AI has a hand that writes code, one person can build a product and ship it. But the information is scattered by stage, so it is easy to get lost about where to start. This article is a full map (roadmap) from idea to design to implementation to launch to monetization, organizing solo development into five phases (Decide, Prepare, Build, Ship, Grow) and, for each stage, showing what to do and which tools to use, then sending you to a dedicated guide for the parts that need a deeper dive. It guides you along two lanes: a Beginner route where you barely write code, and a Hands-on route where you write code in an AI editor, so following whichever fits gets you to something that works without detours. It gathers spec-driven development, AI app builders, Claude Code and Cursor, wiring in AI features (API, RAG, gateway), deploy, SEO/AEO traffic, monetization, cost management, and five pitfalls of solo dev with AI onto one page, with links into the existing hands-on guides.

You hit Claude Code's weekly token limit, yet the allowance fully replenished before seven days passed — more than once. Online there are even "hidden-mechanism" write-ups claiming the weekly limit resets every 72 hours. Is that true? This article traces the phenomenon to primary sources. But Anthropic has not documented the internal reset mechanism, and the limits keep changing, so we clearly label three kinds of information: facts confirmable from official sources, events multiple users reproducibly observe but that Anthropic never addressed, and single-source unconfirmed speculation. The core: early full recovery is, in most cases, Anthropic's irregular global resets (announced repeatedly by @ClaudeDevs); the displayed reset time is also demonstrably unstable; and the circulating "72-hour cadence" is single-observer, unreproduced, and contradicted by another observation (24h), so it cannot be taken as fact. Since September 2026 there is also a new kind of reset you are given and use whenever you choose ("Reset for free" under Settings > Usage on the web or in Claude Desktop; Claude Code in the terminal has no button for it). Where something can't be stated, we say so — an investigation current as of September 2026.

You built on OpenAI, then wanted to try Claude and compare Gemini — and lost hours to the different SDKs, formats, and error handling per provider. An LLM gateway (AI gateway / LLM proxy) is a relay you slot between your app and the providers: it exposes one OpenAI-compatible API to reach every model and takes over the cross-cutting chores — fallback, cost tracking, virtual keys, caching, rate limiting, and observability. This guide covers why you need one, what a gateway really is, the three types (self-hosted proxy = LiteLLM / hosted = OpenRouter / SDK = Vercel AI SDK), how to choose among LiteLLM, OpenRouter, and the Vercel AI SDK, minimal setup code that only swaps the endpoint, and the limits — a hop of latency, the gateway as a new failure point, fees (OpenRouter charges 5.5% on purchases), feature loss, and privacy.

After you build an AI agent, you always hit the same wall: "OK, but is it actually working?" The mechanism for deciding whether a prompt or model change made things better or worse with data instead of gut feel is evals. LLMs produce different output every time for the same input, so exact-match unit tests don't fit. This article centers on the steps for actually building and running them, covering five ways to measure quality (① ground-truth matching ② rule-based checks ③ LLM-as-judge ④ regression testing ⑤ production monitoring), agent-specific evaluation (task success rate, correct tool calls, trajectory, cost), how to start small from 20 failure examples, common pitfalls, and key tools (Anthropic Console/Evals, OpenAI Evals, LangSmith, Langfuse, Ragas) — written for practitioners.

The perennial automation question: "AI agents or RPA?" The answer isn't either/or — choose by role, and the 2026 winning pattern is a hybrid of both. RPA is deterministic "hands" that run a fixed procedure fast and precisely (but break when the screen/spec changes); an AI agent is a probabilistic "brain" that reads the situation and decides (strong on ambiguity and exceptions, but not identical every time). This article covers the operating-principle difference, a comparison table (the reproducibility-vs-resilience trade-off), how to choose (the axis is "can it be fully written as rules?" — yes → RPA, judgment you can't write → AI agent), the 2026 trend (RPA leaders UiPath, Automation Anywhere, Blue Prism going agentic — convergence; the question is no longer "which one" but "where should the reasoning live" = orchestration-first), and the practical answer: a hybrid where the brain (AI agent) handles judgment/orchestration and the hands (RPA) run deterministic execution — don't put an agent where determinism is required, and pair delegated judgment with guardrails and human approval. Based on vendors' official information, with an FAQ.

Claude Fable 5 and Opus 5 are both top-tier, but the answer is neither "always Fable 5" nor "always Opus 5" — choose by task. And the arrival of Opus 5 on July 24, 2026 moved that answer a long way: the previous generation, Opus 4.8, was "a notch below Fable 5 but half the price", whereas Opus 5 holds the same $5 / $25 price while matching or beating Fable 5 on agentic benchmarks (Frontier-Bench 43.3% vs 33.7% and OSWorld 2.0 70.6% vs 66.1%, both from Anthropic's comparison table; on CursorBench 3.2 Anthropic states it lands within 0.5% of Fable 5 at roughly half the cost). Where the gap is small, the order depends on whose table you read: on DeepSWE v1.1, Fable 5 leads 69.7% vs 68.8% in Anthropic's table, while Opus 5 leads 73.7% vs 69.9% in OpenAI's. Specs match on the 1M context window and 128K max output; fast mode (about 2.5x) is Opus 5 only but costs 2x and is Claude API only, and Opus 5 carries the newer knowledge cutoff of May 2026. The decision flow: try Opus 5 first and escalate to Fable 5 only where it plateaus. In practice, "Opus 5 as the base, Fable 5 for the hard parts" is optimal, backed by the app-side auto-switch on safety blocks and the new API fallback "default" mode. Covers availability (June suspension, July redeployment), avoiding single-model dependence, effort tuning for cost, and an FAQ — tying the Fable 5 cluster to the Opus 5 release guide.

The first hurdle in building an AI agent into real work is "which framework to build it on." From a developer and tech-selector viewpoint, this article compares six major frameworks — LangGraph, CrewAI, AutoGen (folded into the Microsoft Agent Framework, GA April 2026), OpenAI Agents SDK, Google ADK, and Claude Agent SDK — by orchestration approach (directed graph / role-based crew / conversational GroupChat / handoffs / hierarchical tree / autonomous tool loop), language, learning curve, control, production maturity, token cost, and best-fit use case. The key caveat: the framework that is "fastest to prototype" (CrewAI) can be the most expensive in production — around 3× the tokens (41k vs LangGraph 18.5k in one benchmark) and non-deterministic, making it a poor fit for finance and healthcare. It also explains how 2026 brought interoperability via MCP (tools) and A2A (agent-to-agent), so agents from different frameworks can now work together and lock-in has faded. Includes a use-case selection guide and FAQ.

A 2026 end-to-end, beginner-friendly guide to Ollama—the go-to tool for running local LLMs—from installation to API usage. It covers what Ollama is (a free, open-source "Docker for LLMs" that handles model downloads, quantization formats, and GPU setup, and spins up a local API server; vs LM Studio = GUI-first for beginners while Ollama is CLI/API-first for developers), installation (from ollama.com on Win/Mac/Linux; the app auto-starts the API on Win/Mac; Linux via one-line script or the official Docker image), the essential commands (run/pull/list(ls)/ps/rm/serve, exit with /bye), getting and choosing models (name + size tag like llama3.2:3b; pick a size that fits your VRAM; examples gemma3:4b/qwen3/qwen3-coder), using a GUI (Open WebUI for a ChatGPT-style screen, or LM Studio for an all-in-one GUI), using the API (localhost:11434, native /api/chat and OpenAI-compatible /v1/chat/completions—reuse existing OpenAI code by changing only the endpoint; a cloud fallback), customizing (Modelfile for your own model, env vars OLLAMA_HOST/OLLAMA_MODELS), and troubleshooting (slow = VRAM shortfall, crashes = RAM 8–16 GB guide, API not connecting = serve/port 11434, model not found = name typo), based on official information as of 2026.

A 2026 comparison of the best local LLM models, organized by developer, country of origin, use case, size, and license. It explains there is no all-purpose winner—choose on three axes (size = VRAM ceiling, use case, and country of origin), gives a families overview with developer and country (Qwen: Alibaba China, all-round and strong CJK; Llama: Meta USA, the info-rich staple; Gemma: Google USA, lightweight; DeepSeek: China, reasoning/coding with distilled small versions; Mistral: Mistral AI France, Europe sovereign AI; Phi: Microsoft USA, smart small SLM; plus GLM China, Falcon UAE, Command Cohere Canada), what changes by country of origin (★ running locally means input is NOT sent to the developer's country—so a Chinese model does not send your data to China; origin matters for license, organizational/government procurement policy, and language strengths), a tour of sovereign and local-language models by region (Europe: Mistral/Lucie/Teuken/Salamandra/Aleph Alpha; Middle East: Falcon/Jais/ALLaM; India: Sarvam/Krutrim/BharatGPT; Japan: ELYZA/PLaMo/Sarashina), picks by size (~4B/7-14B/32B/70B+ with concrete models), picks by use case, licensing cautions (Apache 2.0/MIT permissive, including Gemma 4; the Llama license, the Gemma Terms of Use for Gemma 3 and earlier, and the licenses of large Qwen3.8 models need checking), and a selection flow plus getting started with Ollama. Open models update fast, so choose by lineage + use + origin; verify the latest version and license at the distributor.

A beginner-friendly guide to the PC specs you need to run a local LLM. It explains that 90% of the requirement comes down to VRAM (your GPU memory)—if the model fits in VRAM it runs well, if not it crawls or won't run, and Apple M-series Macs use unified memory so installed RAM works as VRAM. It covers quantization basics (FP16 ~2 bytes/param, Q8 ~1 byte = half, Q4 ~0.5–0.7 bytes = about a quarter and the personal go-to, with the rough formula params(B) × bytes + 10–20% for the KV cache), a VRAM quick table by model size at Q4 (7B–8B ≈ 6–8 GB, 13–14B ≈ 8–12 GB, 32B ≈ 20–24 GB, 70B ≈ 40–48 GB+, 100B+ exceeds 60 GB even at Q4), the context-length / KV-cache trap (on a 7B, 4k ≈ +0.3 GB, 32k ≈ +2.5 GB, 128k ≈ +10 GB), GPUs and Macs in practice with speed guidance (RTX 3060 entry, RTX 4090 up to 32B and 100+ tok/s on 7B, RTX 5090 32B at Q8 or 70B, Apple M4/M5 Max 64 GB runs 70B at ~10 tok/s, CPU-only is slow), what else you need (16–32 GB system RAM, SSD, power and cooling), three budget tiers (entry 8–12 GB / standard 24 GB / serious 40–64 GB+), and how to tell which model you can run (check VRAM → size × 0.6 + context → does it fit), based on 2026 information.