Mobile App Growth Blog

Dating CPI data that carries its sourcing, the platform gates before you can spend, the liquidity problem, and an India campaign structure.

Casual game UA for India: max payable CPI derived from ARPDAU and retention, mediation, ATT, App Campaigns and Apple Ads structure, and budgets.

Launch a photo editing or AI photo app in India: a channel split built from the budget floors up, the export activation event and credits economics.

India runs astrology as a per-minute consultation marketplace. The recharge arithmetic, the astrologer-supply cost, and what Apple and RBI require.

Habit tracker UA for India: streak_3 rates against platform gates, paywall choice, RBI e-mandate rules, Play billing recovery, and real budgets.

Launch a beauty, selfie or AR camera app in India: biometric law, DPDP face data, ad monetisation and creative that survives store review.

An India launch sequence: store hygiene, Apple Ads, App Campaigns, Meta and the event ladder, with every number attributed to a named source.

Launching a UPI app in India: the NPCI TPAP gate, the zero-MDR revenue problem, 31% install fraud, and a campaign plan built on measured CPI.

Launching a broking app in India: KYC funnel arithmetic, SEBI rules in force versus proposed, and the ad platform verification gates.

A launch playbook for B2B apps sold to Indian SMEs: low volume and low ticket, GST as the hook, and a budget that pays for people first.

Launching a scam tracker or caller ID app in India while the category contracts, CNAP nationalises caller ID and ads carry the P&L.

A verified directory of what actually exists for mobile development in Claude Code — skills, plugins and MCP servers — with the corrections that most published lists get wrong and the context cost of installing them all.

Most problems in agent-driven Expo work are setup problems. This is the scaffold to start from, the AGENTS.md template that carries your rules into every session, the eas.json profiles you need, and which MCP servers are worth their context cost.

Expo Go is a preview app, not your app. The moment you add a native module it stops being useful, and that transition catches most projects in week six rather than day two. Here is what actually changes and why to cross it deliberately.

An agent that cannot run your app is guessing. These are the MCP servers that let it build, launch, screenshot and read logs from a simulator or a real device, what each one is actually for, and why to start with one loop rather than five servers.

The question is not which framework is best, but which one an agent writes well. Those are different questions with different answers, and the deciding factors are training coverage, documentation shape and how loudly the framework fails.

Point an agent at Apple’s Human Interface Guidelines and it gets almost nothing back — the page renders client-side. There is a JSON mirror that returns the real content, and this is the verified URL list, plus the Android routing that actually resolves.

Design-to-code demos look convincing and production results rarely match them. This is what Figma MCP actually emits for each mobile platform, the two things that genuinely improve output, and the problem no converter solves.

The design system that produces the best agent output is not the fastest one. It is the one the agent can read. Here is why that is the deciding factor, and how seven mobile options rank against it.

Your rejection notice cites a guideline number and explains almost nothing. This is what Apple actually publishes, which guidelines genuinely catch agent-built apps, and why the statistic everyone quotes about AI apps does not exist.

A reviewer with no memory of writing the code catches what the author cannot. This is how to run one on mobile pull requests, the runner cost trap that surprises people, and an honest account of what it does not catch.

Most growth MCP servers are read-only, and the ones that write are the ones worth being careful with. This maps what an agent can actually do across ads, attribution, analytics, paywalls and lifecycle messaging.

Building a mobile app got very cheap in the last eighteen months. Shipping one did not. This is the ordered path from idea to store listing with Claude Code, including the five cliffs that stop most projects and the compliance work that decides whether you ship at all.

Coding agents write mobile layouts that look right in a screenshot and fail on a real device. The failures are consistent and enumerable: safe-area insets, Dynamic Type, touch-target size and the states nobody screenshots. Here is the full list, with a skill file that encodes the fixes.