All Articles
`gemini-2.5-pro-latest` Returns 404 — Aliases, Base Names, and How to Pin a Version
Diagnose why the Gemini API returns 404 for `gemini-2.5-pro-latest`, understand the alias vs base-name semantics in Gemini 2.5, and choose the right way to pin a model version in production.
Gemini API Keeps Wrapping Code in Markdown Fences — Three Patterns to Get Raw Code Out
Even when you ask Gemini for 'Python code only', responses keep coming back wrapped in triple backticks. System instructions can reduce but not eliminate it. Here's the three-layer pattern I use in production: instruction hardening, regex post-processing, and JSON schema output.
When Your Prompt Works in Google AI Studio But Fails Through the Gemini API
Your prompt ran perfectly in Google AI Studio, but the same call from your own code keeps returning 400, 404, or an empty response. Here's a diagnosis checklist that zeroes in on the exact gap between Studio and the API.
NotebookLM Plans Decoded — Which Gemini Model Each Tier Actually Runs in 2026
A clear breakdown of which Gemini models power NotebookLM across the Free, Google AI Pro, and Google AI Ultra tiers in 2026 — including source limits, audio overviews, and Deep Think availability.
Extract Structured Data from Real-World Photos with Gemini — Surviving Tilt, Shadows, and Occlusion in Production
Getting Gemini to return JSON from clean sample images is easy. Making it work reliably on the messy photos your users actually take is a different problem. Here's how I classify the failures and fix each layer — with the code I run in production.
Designing Production-Grade Safety Controls for the Gemini API: A Layered Moderation Architecture That Minimizes False Positives Without Letting Abuse Through
Relying on the Gemini API's Safety Settings alone leads to legitimate questions getting false-blocked or carefully crafted malicious prompts slipping through. This guide shows a four-layer moderation design that stands up in production.
Gemini API × Langfuse — A Production Playbook for LLM Observability
A practical, production-grade guide to wiring Gemini API into Langfuse — tracing architecture, cost attribution, LLM-as-Judge on live traffic, PII masking, and sampling — with runnable code.
Running Gemini Code Assist Agent Mode on a Real Team: A Production Playbook
Agent Mode in Gemini Code Assist feels like magic on a solo project. The moment you drop it into a team workflow, you meet the issues solo users never see — unbounded change scope, unreviewable diffs, half-finished failures left on disk, and the permission blast radius nobody priced in. This guide ships the guardrails I actually use in production: a scope contract, a diff-submission protocol, a recovery flow, and three anti-patterns to avoid.
Google Project Mariner in 2026: Five Browser-Automation Use Cases That Actually Pay Off
Five concrete, repeatable ways to use Google Project Mariner for real work — pricing research, tech news roundups, form submissions, trip planning, and stock watches — plus the honest limits that tell you when to skip it.
Ollama 'pull model manifest: file does not exist' — A Diagnostic Flow That Actually Isolates the Cause
Every guide tells you to check the tag name when Ollama throws `Error: pull model manifest: file does not exist`, but sometimes the tag is fine and the error persists. This post walks a 5-step diagnostic flow — tag, proxy, storage, registry, version — that isolates the real cause in under ten minutes, for Gemma 4 and beyond.
Running gemini-2.5-pro-latest in Production: Rate Limits, Error Handling, and Cost Control
A production-focused guide to gemini-2.5-pro-latest: when to pin a version instead of tracking the alias, correct retry strategies for every common status code, and the Prompt Caching + Batch API patterns that cut real invoices in half.
Calling Gemini Nano from the Browser: A Practical Prompt API Guide (April 2026)
A hands-on walkthrough of Chrome's built-in AI — how to enable the Prompt API and Summarizer API, implement streaming responses, manage sessions, and gracefully fall back to the Gemini cloud API. Accurate as of April 2026.