All Articles
When the Default Model Silently Upgrades: Catching Prompt Regressions in Numbers
Gemini 3.5 Flash is now the default and you can no longer turn it off. Assuming your responses can shift without you touching the prompt, here is how to bundle prompt, model, and sampling into one variant and catch regressions with canaries and an LLM judge — in working code.
Building Web Apps with Gemini — Prompt Design and Pitfalls in Google AI Studio
How to structure your prompts when asking Gemini to build web apps in Google AI Studio — and the pitfalls I actually ran into as an indie developer.
Getting Ready for the Gemini CLI and Code Assist Personal Shutdown: A June 18 Migration Inventory
On June 18, personal access to Gemini CLI and Code Assist stops. Here is how I found every place I depended on it and moved each one to either Antigravity CLI or direct API calls, using my own setup as the example.
Defending Against Prompt Injection When You Pass External Text to the Gemini API
User reviews, scraped articles, and other untrusted text are the entry point for indirect prompt injection when you feed them to the Gemini API. Here is a prioritized, code-backed defense you can drop into a production pipeline: trust-boundary isolation, schema constraints, a two-stage screening pass, and output sanitization.
Permission-Aware RAG — Designing Gemini Search That Only Cites What the User Is Allowed to See
The day you add RAG to internal search, drafts and finance memos nobody should see start leaking into answers. This is a production design — metadata filtering, defense in depth, and audit logging — for letting Gemini search while respecting permissions, with working code.
How a Deep Think Verification Step Tripled My API Bill, and How thinking_level Got It Back
After wiring API-accessible Gemini 3 Deep Think into my output-verification step, my projected monthly cost jumped roughly 3x. Here is the implementation record of capping it with thinking_level and a cost guardrail, then settling on a two-stage design with Flash.
Trusting Gemini Structured Output in Production — Schema Design, Double Validation, and Bounded Retries
Gemini's structured output guarantees parseable JSON, not correct values. Notes on schema design with @google/genai, why propertyOrdering matters, a Zod double-validation layer, handling MAX_TOKENS truncation, and a bounded-retry extraction pipeline.
Generate With Flash, Escalate to Deep Think Only When Unsure: A Two-Stage Pipeline
With Deep Think opening up on the API, the move is not to route every request through the heavy model but to have Deep Think verify only when Flash's output looks shaky. Here is the cost reasoning and working code.
Keeping Gemini API's Default-Model Shift From Becoming an Incident — Pinning Model IDs and Detecting Silent Upgrades in Production
When the default model quietly moves up, your output length, reasoning behavior, and cost change with zero code edits. This guide shows how to pin model IDs in a single source of truth and verify the effective model from the response to detect default changes.
Controlling Image Tokens with the Gemini API media_resolution Setting — Tuning Batch Image Classification by Measurement
media_resolution, introduced in the Gemini 3 line, switches how many tokens an image input consumes across three levels. Through real batch-classification measurements, this guide shows how to balance cost and accuracy by assigning the right tier per task.
Switching Image Models Quietly Degrades Quality — A Gate That Catches It Without Manual Review
When you move image generation from preview to GA models, the API keeps returning 200 and quality slips silently. This is the three-layer gate I built to detect that drift without staring at every image: deterministic property checks, multimodal embedding similarity, and a Gemini judge, wired together in Python with thresholds and a cutover procedure.
When Gemini API Cuts Your Response Off Mid-Sentence — Detecting finish_reason: MAX_TOKENS and Stitching the Continuation
Long-form generation that ends mid-sentence is usually finish_reason: MAX_TOKENS. This failure arrives as a quiet HTTP 200, no exception. Here is how to detect it, stitch a continuation to recover the full text, and avoid the thinking-token trap that makes it worse on 3.x models.