Idempotency Key Design for the Gemini API: Patterns I Use to Prevent Duplicate Generation Across Six Sites
After five months of running six AI-driven sites in parallel, I built an idempotency layer in front of the Gemini API to neutralize retry storms. This deep dive shares the SHA-256 + Cloudflare Workers KV design, the operational numbers behind it, and the four gotchas that only surface in production.
Why Gemini API Returns Empty Responses with finishReason: RECITATION, and the Prompt + Post-Processing Design That Stopped It
Run a Gemini content agent long enough and one day logs fill with finishReason: 'RECITATION' and empty content arrays. This is the verbatim-quotation safety system firing. Here is the prompt rewriting pattern and TypeScript post-processor I deployed across six auto-publishing pipelines at Dolice — it dropped my incident rate by 90%.
Designing Event-Driven AI Workflows with Gemini API and Cloud Pub/Sub — Notes from an Indie Developer
An implementation memo on wiring Gemini API into Cloud Pub/Sub event-driven workflows. Using an app-review analysis pipeline as the running example, the article covers retry policy, dead-lettering, idempotency, and cost guardrails — from the perspective of someone running it solo.
Designing a Continuous Quality Monitoring Pipeline for the Gemini API
A practical, indie-developer-friendly design for a Gemini API evaluation pipeline that catches silent quality regressions using a Golden Dataset and a multi-aspect LLM-as-Judge, with full code and real cost numbers.
Evolving Gemini API Structured Output Schemas in Production — Design Notes from an Indie App
How I rebuilt the JSON contract layer for a Gemini-powered recommendation feature in a long-running indie app — Dual-Emit, Sunset protocol, and a Python compatibility checker.
Wiring Circuit Breakers and Graceful Degradation into Gemini API — an Indie App's Stability-First Notes
When you run Gemini API in production for an indie app, something upstream breaks at least a few times a month. Here are the building blocks for circuit breakers and graceful degradation I settled on, with the implementation traps I actually hit.
Gemini API asyncio Patterns for Production: How I Cut Processing Time by 80% in My Indie App Backend
A hands-on report on integrating Gemini API asyncio into a production backend. Covers Semaphore-based rate limiting, exponential backoff, and partial failure handling from real experience building a 50M+ download wallpaper app.
Personalized Push Notifications at Scale: Gemini 3 Pro × Firebase Cloud Messaging for Indie App Developers
If your push notification open rates have plateaued, this guide shows how to combine Gemini 3 Pro with Firebase Cloud Messaging to generate per-user copy. Includes the production architecture, working code, PII guardrails, and real cost numbers from a live indie app.
Turning my own artworks into 120 wallpaper variants in 30 days with Gemini 3.2 Pro and Imagen 4 — an artist-developer's content supply pipeline
A 30-day production log of building a pipeline that takes one of my own paintings and expands it into a 120-piece wallpaper series, using Gemini 3.2 Pro for structural analysis and Imagen 4 for variations. Includes real costs, quality gates, and downstream app KPIs.
Migrating from Gemini 2.5 Pro to 3.2 Pro in 7 Days — A Production Playbook for Compatibility Testing, Output Diff Scoring, and Rollback Design
A 7-day playbook for moving production systems from Gemini 2.5 Pro to 3.2 Pro: compatibility testing, LLM-as-Judge scoring, shadow traffic, and rollback.
Building a RAG Evaluation Framework with Gemini API: RAGAS, LLM-as-Judge, and Custom Metrics Production Masterclass
Complete guide to building a quantitative RAG evaluation framework using RAGAS, LLM-as-Judge with Gemini API, and custom domain metrics — including CI/CD integration and production monitoring.
Gemini 2.5 Pro in Production: The Pitfalls Nobody Talks About
A practical guide to the production-specific problems with Gemini 2.5 Pro—rate limit architecture, Thinking mode cost control, long-context quality management, and response quality diagnostics—with complete code examples.