All Articles
Moving My Automation Off the Gemini CLI Before the June 18 Shutdown
On June 18, the Gemini CLI stops responding for hosted plans. Here is how I moved unattended scripts that called gemini from the shell over to the google-genai SDK, with structured output, retries, and cost measurement built in.
Keep Your Flash-to-Pro Routing Threshold Honest with Shadow Re-evaluation
A Flash-generates, Pro-on-low-confidence router starts drifting the moment you hand-pick its threshold. This is a working build of a loop that samples your kept-Flash outputs, scores them against Pro, and recalibrates the threshold from a quality budget.
Watching the 'Voice' of Generated Text: Catching a Silent Default-Model Swap Through Style Drift
When the default model changes over your head, the output can stay factually correct while its voice quietly shifts. This walks through fingerprinting the style of generated text and detecting drift statistically, with a dependency-free implementation you can drop into your pipeline.
Before You Let a Managed Agent Ship: Designing Your Own Acceptance Gate
Let the public-preview Managed Agents generate files and broken artifacts will flow straight into production. Here is how to build a verification gate that artifacts must pass before you accept them, with runnable Python and a rejection-feedback loop.
Wiring Gemini Managed Agents Into Your Automation: Keeping Conversation State and Environment State Apart
Managed Agents spin up a Linux sandbox, run an agent loop, and return a result in a single API call. The first thing that trips you up when moving off a hand-rolled loop is that conversation state and file state are two separate things. Here's that design, worked through live.
Don't Break When the Default Model Moves: A Startup Capability-Probing Layer for Gemini
Pinning a model name breaks on deprecation; trusting the default breaks when the weights swap silently. This is the design I settled on: probe what the served model can actually do at startup, then build every request from that answer. Includes runnable Python.
Your Gemini Live API session forgets the conversation every time it reconnects — field notes on token refresh and session resumption
Why a Gemini Live API WebSocket drops the conversation and the user's in-flight speech on every reconnect, and how to close the gap with single-use ephemeral tokens, session resumption handles, and the goAway warning.
Put Help Docs and Screenshots in One File Search Store and Return Answers That Cite the Image Too
Your text help docs and your screenshots live in separate stores, so a single question can never return both the steps and the matching screen. With gemini-embedding-2 going multimodal in File Search, here is how I merged them and returned the cited screenshot alongside the answer.
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.
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.