AI agents, from demos to real work.
Useful autonomy / Clear boundaries / Human control
OpenAI shares early data on coding agents in AI research
OpenAI reports 3.1 agent-workdays per human workday, but its internal data also shows why more automated activity is not the same as faster research.
6 min read
How AWS designed lifecycle policies for Amazon Bedrock AgentCore memory
A nightly AWS workflow combines TTL expiration, relevance scoring, LLM-based consolidation, regression testing, and deletion controls to keep long-running agents’ memories useful, auditable, and manageable.
9 min read
How t54 built a trust gate for autonomous payments on Amazon Bedrock AgentCore
The x402-secure system checks endpoints before agents pay them, while session spending limits, isolated credentials, role separation and audit logs constrain what happens when software transacts…
7 min read
OpenAI Codex 0.153.0 strengthens session recovery, plugins, Guardian history and context controls
The Codex release improves terminal editing, remote plugin management, reconnection behavior, account-scoped MCP approvals and long-running session state, while adding an opt-in experimental context-management mode with…
7 min read
How to build an AI agent without writing code: A five-step Microsoft 365 Copilot guide
A practical, source-led walkthrough for turning a clearly defined workplace problem into a testable AI agent, connecting it to relevant knowledge and improving it through real-world…
8 min read
From theory to delivery: How Atos gave 400 engineers hands-on agentic AI experience
A three-day AWS AI League event asked a mixed-experience Atos cohort to build and optimize multi-agent systems, turning abstract lessons about prompts, tools, memory, safety and…
9 min read