All Articles
Vertex AI Agent Engine × Gemini 2.5 Pro — Production Deployment for Managed Agents
Deploy ADK-based agents powered by Gemini 2.5 Pro on Vertex AI Agent Engine. Covers the trade-offs vs Cloud Run, sessions, tool calls, tracing, and a realistic cost model.
Stop Gemini From Phoning In the Last Few Paragraphs — Prompt Patterns That Hold Density to the End
When Gemini writes long pieces, the final paragraphs often go thin. A solo creator's three-layer routine — pre-declared footer, staged generation, verifier agent — to keep density consistent from start to finish.
Teaching Gemini Your Own Writing Voice: Prompt Design for Solo Creators, and How to Avoid Overfit
Letting AI write for me always produced text that sounded like 'someone else.' Here's how I taught Gemini to keep my voice across articles, plus how I avoid the surprising overfit problem when you feed it too many samples.
Building Local Agents with Gemma 4's Function Calling
Learn how to implement private, on-premises AI agents using Gemma 4's dedicated Function Calling tokens without relying on cloud APIs.
Designing a Daily Reading Practice With Gemini as Your Reading Partner
How to use Gemini at a closer distance than 'researcher' — as a daily reading assistant. The operating model I have settled into for cross-domain reading as a solo developer and artist.
Putting Gemini 2.5 Pro's Million-Token Window to Real Use — A Design Playbook
Gemini 2.5 Pro's million-token window isn't a 'dump everything in' tool. After running it across full-codebase analysis, deep document review, and long-running conversations, here's the design playbook that actually pays off.
Self-Healing Architecture for Gemini Computer Use — Production Patterns That Keep Browser Automation Alive Beyond Day Three
Gemini Computer Use looks magical in demos but breaks daily in production: vanishing elements, surprise modals, network jitter, off-by-four-pixel clicks. This guide builds a five-layer self-healing architecture in Python that classifies failures and recovers them automatically, with working code you can drop into your agent loop today.
Custom Gemini API Agent Loop Without ADK — A Complete Production Guide to Tool Calling, Memory, and Parallel Execution
Build production-grade AI agents using Gemini API directly without Google ADK. This guide covers custom agent loops, tool calling patterns, sliding window memory, parallel execution, and battle-tested error recovery strategies.
Writing Gemini Gems Custom Instructions That Actually Behave
The way you structure custom instructions for a Gemini Gem changes its behavior dramatically. Here are the patterns I converged on after several Gems and a lot of iteration.
Building Self-Critiquing Agents with Gemini API: A Production-Ready Guide to Reflection and Critic-Refiner Patterns
A production-grade walkthrough of Reflection and Critic-Refiner patterns with Gemini 3 Pro and 3.5 Flash-Lite. Covers implementation, cost guards, over-correction defenses, and monitoring signals from real deployments.
Safely Migrating Gemini Model Versions with Shadow Traffic — A Production Pattern for Measuring Output Drift
Stop treating Gemini model migrations as a coin flip. This guide walks through a production-ready shadow traffic architecture — duplicate real inputs to the new model, quantify output drift, and cut over progressively. Includes Python and Cloud Tasks code you can ship today.
Reading a 200-Page Contract with Gemini 2.5 Pro — Five Techniques That Move Long-Context Analysis to Production Quality
Using Gemini 2.5 Pro's long context for real business work takes more than stuffing the whole document in. Here are the five techniques I found most effective for contracts, meeting minutes, and technical specs.