Uber has been hit with an €825 million fine in Europe over its automated system for suspending and deactivating drivers. The Dutch Data Protection Authority says Uber used automated systems between 2018 and 2022 to make decisions that could seriously affect drivers’ income, without proper human involvement or enough information for the drivers. “From one moment to the next, they no longer had any income through Uber.” “A computer should not make decisions on its own that have major consequences for you.”

# Practical and Useful Patterns with ADK Memory enables "long-term recall" across sessions. Build agents that learn from past conversations and deeply understand each user 🧠 📌 **Title**: Memory 🔗 **URL**: ## 🧩 Overview Memory manages long-term knowledge that is searchable across sessions. While State holds data for "the current conversation," Memory accumulates "knowledge gained from past conversations" and makes it searchable via natural language. The two key APIs are: - `add_session_to_memory` / `add_events_to_memory`: Add session or event content to memory - `search_memory`: Search memory with natural language queries Backends can use vector databases like Chroma, improving agent response quality through RAG (Retrieval-Augmented Generation) patterns. ## 🛠 How to Use Import and instantiate `InMemoryMemoryService` from `google.adk.memory`. When a session ends, call `await memory_service.add_session_to_memory(session)` to store the session content in memory. To search, use `await memory_service.search_memory(app_name=..., user_id=..., query="previous network connection issues")` with a natural language query. Iterate over the returned results and access each `memory.content` to retrieve related past conversation content for use as agent context. ## 🏗 Practical Usage **Customer support scenario:** 1. User reports "My network isn't connecting again" 2. Search Memory for "network connection issues" 3. Retrieve: "User had the same issue 3 days ago, resolved by router restart" 4. Agent suggests: "Was your previous issue resolved? If the symptoms are the same, try restarting your router" This enables personalized support informed by past interaction history. **Learning assistant agent:** 1. User asks "I don't understand derivatives" 2. Search Memory to find "This user prefers visual explanations" and "Last time they understood through concrete examples" 3. Provide graph-based, example-driven explanations ## 💡 Use Cases - 🎧 Customer support: Informed responses based on past inquiry history. "Was your previous issue resolved?" - 📚 Learning assistance: Remember user learning styles and comprehension levels to choose optimal teaching approaches - 🏥 Health management: Understand trends from consultation history for continuous advice - 🛒 Personal shopper: Remember purchase history and preferences for accurate product suggestions ## ⚠️ Caveats - Storing personal information in Memory requires compliance with privacy policies and data protection regulations - Vector DB search accuracy depends on embedding model quality. Choose an appropriate model - Search costs increase as memory volume grows. Consider periodic cleanup or TTL (time-to-live) settings - `InMemoryMemoryService` loses data on process restart. Use persistent backends like Chroma in production ✨ With Memory giving agents long-term recall, you build deeper user relationships and agents that get smarter with every interaction! #ADK# #AIAgent#

$CRWD CrowdStrike CEO George Kurtz: “What we're hearing from customers is they want to deploy more AI, but they're being held back because of security, compliance, privacy, data protection type issues.”

UBER HAS BEEN FINED €825 MILLION ($963 MILLION) BY DUTCH AUTHORITIES FOR USING AUTOMATED SYSTEMS TO SUSPEND DRIVER ACCOUNTS, IN WHAT IS THE SECOND-LARGEST PENALTY UNDER THE EUROPEAN UNION’S GENERAL DATA PROTECTION REGULATION

Uber has been fined €825 million ($963 million) by Dutch authorities for using automated systems to suspend driver accounts, in what is the second-largest penalty under the European Union’s General Data Protection Regulation

Uber has been fined €825 million ($963 million) by Dutch authorities for using automated systems to suspend driver accounts, in what is the second-largest penalty under the European Union’s General Data Protection Regulation

CertiK 🤝 @MidnightNtwrk We’re excited to announce a new ecosystem partnership with Midnight, a blockchain designed to enable data protection and privacy-preserving applications. Together, we’ll explore opportunities to support the security and continued growth of the Midnight ecosystem as it expands. We look forward to working alongside the Midnight team and contributing to a more secure Web3.

🔎 Frontier model smarts alone don't run production AI. It works only when paired with a retrieval layer that pulls enterprise data accurately, with permissions and audit. TL;DR: Elastic and OpenAI expand their partnership, turning Elasticsearch into a permission-aware persistent memory layer to boost agents, observability, and security at once. Title: Elastic and OpenAI collaborate to bring frontier intelligence to unstructured enterprise data URL: Key points 🧠 Elasticsearch as a persistent memory layer (lexical + vector + reranking + access control) 🎯 Precomputed Knowledge Indicators cut input tokens up to 75%, lift accuracy 60%→92% 🔒 Internal tests show 0.89 recall with complete cross-user data protection 🛡 Attack Discovery correlates alerts into attack chains, mapped to MITRE ATT&CK ⚡ Visa cut triage from 10-20 min to seconds; Airtel up to 40% faster analysis, 30% faster investigations 🔌 Agent Builder exposes skills via MCP; migrates Splunk/QRadar rules A pragmatic design: intelligence + retrieval + governance together is what makes production AI real. #Elasticsearch# #OpenAI#