Pulse : ce qui change dans le commerce par agents IA

Building autonomous AI agents that mutate production state requires moving beyond soft system prompts to a robust zero-trust architecture. To secure Google Agent Development Kit (ADK) workflows against prompt injections and malicious execution, developers must implement hardware-backed cryptographic signatures for database writes, kernel-level sandboxing with gVisor for dynamic code, and determini

Moving live voice agents from demo to production requires rigorous, automated testing to handle the unpredictability of real multi-turn conversations. ADK now provides native live evaluation, allowing developers to test graph-based agent workflows against LLM-driven simulated users that generate actual audio via Gemini TTS. By defining evaluation scenarios and natural-language rubrics, you can aut

The recent Google for Startups AI Agents Challenge revealed that the most successful multi-agent systems rely on foundational software engineering patterns rather than just raw model power. Winning architectures consistently implemented bidirectional MCP for seamless inter-agent communication, async event buses for parallel execution, strict unified validation for model fallbacks, and tiered routi

Google has officially released version 1.0 of the Agent Development Kit (ADK) for Kotlin, achieving full feature parity with the Python and Java ADK cores to enable idiomatic, multi-agent AI development. Built on Kotlin Multiplatform (KMP), the framework leverages Kotlin Symbol Processing (KSP) for zero-reflection, type-safe function calling, alongside advanced orchestration capabilities like huma

While end-to-end benchmarks like SWE-bench provide broad performance scores for AI agents, they are often expensive, slow, and lack the root-cause diagnostics needed to explain exactly where an agent's logic broke down. To solve this, developers should adopt behavioral evaluations—fast, local, unit-style tests that assert on discrete intermediate actions, such as verifying specific tool calls or f

The "autofinetune" project introduces an autonomous research loop that fully automates LLM post-training workflows, including Supervised Fine-Tuning (SFT) and Reinforcement Learning via GRPO. By defining boundary conditions and evaluation metrics in a single Markdown specification, developers can deploy an AI agent to iteratively edit training scripts, launch experiments, and automatically commit

This blog post explores how to transition AI agents from static, build-time security controls to dynamic runtime governance using the Gemini Enterprise Agent Platform. It highlights three primary managed defenses: Model Armor for screening edge prompts, Semantic Governance Policies for evaluating tool intent against business rules, and Agent Anomaly Detection for catching multi-turn exploits. By s

Agent Anomaly Detection is a new, out-of-band oversight layer for the Gemini Enterprise Agent Platform that analyzes OpenTelemetry traces and tool calls to catch behavioral risks without adding runtime latency to live requests. It utilizes a multi-tiered detection pipeline—combining lightweight statistical scanning with deep LLM-based reasoning—to identify logical anomalies and policy violations g

Google has partnered with Speakeasy to open-source their OpenAPI code generation suite under the AGPLv3 license, a strategic move prompted by the sudden shutdown of Google's previous proprietary SDK provider. The newly open-sourced suite equips developers with deterministic, multi-language SDK generators that natively support strict typing and SSE streaming, alongside tools for compiling agent-nat

The Google Antigravity SDK now empowers developers to execute offline, agentic workflows locally using models like Gemma 4 26B A4B via LiteRT. This update facilitates powerful hybrid orchestration architectures, allowing a cloud model to act as a lightweight planner while local models securely handle token-intensive tasks—like code auditing and patching—directly on-device. Furthermore, the SDK pro

Google Cloud API Gateway now acts as a native remote Model Context Protocol (MCP) server, eliminating the need to build and maintain custom middleware to expose REST APIs to AI agents. By simply adding specific annotations (like x-google-api-management.mcp) to existing OpenAPI 3.x specifications, developers can instantly convert standard REST operations into discoverable, agent-ready tools. The ga

Summary Apps can now discover Rollouts, inspect their schedules, traffic allocation, and resource changes, and receive notifications when they change. These capabilities help apps understand and respond to coordinated launches, experiments, and temporary events across discounts, catalogs, themes, and checkout and accounts configurations. What's new Discover and read Rollouts. Use the root rollouts

Albertsons Cos. is using ChatGPT Enterprise and the OpenAI API to help teams work faster and make grocery shopping easier for millions of customers.

A new SubscriptionContractCalculation API is now available to manage subscriptions. This new API runs subscription contract edits through Shopify's checkout engine, enabling new capabilities: Shopify Functions, including cart transforms and delivery customizations are supported during contract calculations Contract edits align with what the subscriber sees during billing Get a preview of the full

Open USD (OUSD), a stablecoin built for global money movement, is now available across Stripe. Businesses can use OUSD to manage funds, make payments, and offer new financial services.

Meet GPT-6.1 Sol: near-Astra intelligence for coding, computer use, and professional work at one-fifth of Astra’s standard API input and output token prices.

As agents take on more purchases, agent builders have increasingly asked us to help agents navigate checkout and earn consumer trust. Today, we’re sharing three major improvements to support this broader set of needs.

Browser agents can now read and update Shopify checkouts using WebMCP tools for checkout . The tools let agents interact with the active checkout in the buyer’s browser session. When the buyer’s input is required, such as 3D Secure authentication or for blocking UI extensions, the tools hand back control to the buyer. With storefront and cart tools already live, browser agents can now assist the f

With today's release of AI Toolkit , all existing shopify- skills are consolidated into a single shopify skill. If you use AI Toolkit skills with agents or npx skills , you might need to update your environment. What changed Shopify skills content in AI Toolkit was previously distributed across many skills, such as shopify-dev-onboarding , shopify-admin , and shopify-functions . The agent plugins

Wayfair uses OpenAI models to improve ecommerce support and product catalog accuracy, automating ticket triage and enhancing millions of product attributes at scale.

Using GPT-5.6, Ringg powers multilingual agents across voice, chat, WhatsApp, and web for 90% less cost vs. GPT-4.1.

GPT‑6 Astra allowed Parallel’s agents to research and synthesize labor-market data in half the time and at half the cost vs. prior models.

Using GPT-5.6, V7 turns scattered company files into context agents can use to complete complex, source-linked work.

Last year, Stripe data shows fraud attempts against travel and leisure businesses hit a four-year high. We analyzed payment activity from more than 200,000 active travel and leisure businesses on Stripe to understand where fraud is rising, how effectively it’s being blocked, and what businesses can do in response.

What's Changed ✨ New Features feat(cart): Cart capability for basket building by @igrigorik in #73 feat(extends): multi-parent support + deterministic schema resolution by @igrigorik in #96 feat(errors): spec error handling for UCP negotiation failures by @igrigorik in #128 feat(context): add intent field for relevance and personalization by @igrigorik in #95 feat: Add first-class errors concept b

This release introduces major protocol enhancements, key structural refactorings to support multi-vertical expansion, payments security improvements (3DS2) and structured request constraints, independent capability versioning, and grocery vertical readiness. 📊 Executive Summary 📂 Multi-Vertical Refactoring : Foundation laid for supporting Food and Lodging verticals alongside Shopping, with polym

MCP whats_new {"topic":"standards","days":7} · HTTP https://faceabot.com/api/pulse?days=7 · RSS https://faceabot.com/api/pulse.rss · Indice https://faceabot.com/api/agent-access-index