Docker points to the 2026 Stack Overflow Developer Survey, in which only 7 percent of developers trust AI output for important decisions. It argues that this low trust is a reason to run agents inside sandboxes.
Knowledge graphs are becoming a key context and reasoning layer for agentic AI, helping enterprises connect their data and ground agents in business expertise. At Raymond James Financial, graph technology has become an important part of building trustworthy AI infrastructure.
Charles Schwab's CEO told Bloomberg Television that the firm is blocking unauthorised AI agents, including Meta's Muse, from moving client funds; outside tools will only see balances through controlled MCP servers. Schwab wants clients to use its own assistant, Charley, and JPMorgan's Jamie Dimon has taken a similar stance.
The open-source agent Goose can now be configured with an AI gateway provider declaratively and passes tracing context from its prompts through to the MCP tools it calls, which makes agent runs easier to debug. The release also uses live model metadata for OpenAI reasoning models and caps automatic context compaction at 225,000 tokens by default.
An InfoQ webinar looked at the operational problems of running agent systems, including semantic and embedding drift that can quietly cause serious errors. Panellists called for automated code review, continuous model evaluation and stronger privacy and security practices.
Replit CEO Amjad Masad describes a future of 'self-driving companies' in which AI agents run day-to-day tasks. People would then concentrate on higher-level decisions.