Articles for people who
ship the stack
Rewrites on React, Node.js, TypeScript and AI. A translated body is shown when it exists. If it does not, you see the English text and a note that says so.
Tagged: Gemini
Offloading Apps Script Workloads to a Gemini Managed Agent Linux Sandbox
Google Apps Script driving a Gemini managed agent Linux sandbox: stream files to Drive with ggsrun, dodge the 50 MB limit, run Playwright, FFmpeg and esbuild.
13 min readWhat a Schema Can't Tell Your Agent: Open Knowledge Format on BigQuery
A BigQuery and Gemini ADK experiment: Open Knowledge Format bundles in Git gave an agent what the schema couldn't, stabilized answers and fixed a 29% GMV error.
13 min readManaged Agents in the Gemini API: Sandboxes, Skills and Persistent Agents
A hands-on walk through Google's Antigravity Managed Agents: the remote Linux sandbox, egress proxy, multi-turn state, skills, named agents and production patterns.
40 min readBigQuery Conversational Agent on Vertex AI with Google ADK: Six Traps
Build a natural-language BigQuery agent with Google ADK and Gemini, deploy it to Vertex AI Agent Engine, and avoid the Python, dependency, billing and IAM traps.
10 min readGemini 3.8 Flash at Launch: Speed, Pricing Deadline and Safety Caveats
A review of Gemini 3.8 Flash: official benchmark gains, a 304 tokens-per-second snapshot, promo pricing ending in 2027, the Cyber model and a multilingual safety dip.
7 min readOne Agent, Three Builds: Interactions API vs ADK vs Antigravity SDK
The same Gemini agent built three ways, with the Interactions API, Google ADK and the Antigravity SDK, compared on loops, tools, auth and Cloud Run deploys.
8 min readHybrid Image Search at Scale: SigLIP, SPLADE, YOLOv8 and Gemini Captions
Design of a million-image search system that pairs dense and sparse embeddings with object detection, entity recognition, safe search and LLM-written descriptions.
6 min readA Local RAG Pipeline with Qdrant, fastembed and Gemini in Python
A small RAG pipeline in Python: chunk local docs, embed them offline with fastembed, keep vectors in Qdrant, and answer questions with Gemini from the CLI.
6 min readGoogle ADK Agents: From a Single Gemini Agent to Cloud Run Deploys
Google ADK from one Gemini agent to production: tools, agents as tools, sequential flows, local testing, and deploys to Cloud Run and Vertex AI Agent Engine.
7 min read
About these articles
Request a 24h estimate
Need the same stack in a production operator layer? Send the brief — estimate within 24 hours.