Fetching from the wire…
01
02
03
04
05
06
07
08
Tools2026-07-29 · source-backed
Google made Gemini 3.6 Flash the default for the antigravity-preview managed agent with no code changes, and added environment hooks that run custom scripts around tool calls: pre_tool_execution can block with a denial reason, post_tool_execution can enforce validation like linting, both with regex matchers and command-line or HTTP handlers. Also new: a max_total_tokens budget cap with resumable interactions, cron triggers, and an Environments API for programmatic sandbox management. AI investment bank OffDeal uses post-execution hooks for pixel-level logo validation before deck publication, which is a delightfully specific use of a generic hook.
Each link below shares sources, entities, or timing with this story.
GA and stable for production across the Gemini API, Enterprise, and Antigravity, and now the default in the Gemini app and AI Mode in Search globally. Google pitches frontier-level intelligence at ~4x the speed of comparable models, priced at $1.50/$9 per 1M tokens, 1M-token c...
"Gemini is Cooked but GCP is Cooking" argues Google quietly shelved 3.5 Pro, which industry chatter placed at roughly Opus 4.5 level, shipping Gemini 3.6 Flash as a bridge the authors call worse than Muse Spark 1.2, Grok 4.5, and tier-1 Chinese open-source models. The hard num...
Google shipped it August 13: FrontierCode 1.1 at 43.6% (from 34.4%), DeepSWE v1.1 at 65.3% (from 49.0%), WebDev Arena Elo 1588 (from 1538), AutomationBench enterprise workflow completion at 30.4% (from 17.0%). Introductory pricing is $0.75/M input and $3.75/M output through De...
Microsoft unveiled MAI-Code-1-Flash at Build, its first model that turns written descriptions into source code for apps and websites, explicitly aimed at lowering developer costs and cutting its dependence on OpenAI (CNBC). Same week, Google pushed Gemini 3.5 Flash to general...
Google DeepMind shipped computer use as a built-in tool inside Gemini 3.5 Flash on June 24, collapsing the standalone Oct-2025 computer-use model into the same model you already use for function calling, Search grounding, and Maps. One agent sees a screen, clicks, types, and l...
Willison's August 13 release adds Gemini 3.7 Flash, 3.6 Flash and 3.5 Flash-Lite plus gemini-embedding-2 and -001, rebuilding on LLM 0.32's structured message and streaming APIs so reasoning, tool calls and results emit as typed stream events while preserving Gemini thought si...
MindPattern daily
One email a day at 7 AM. Sources and a take on every story. Unsubscribe anytime.