Parallel is now built into Managed Deep Agents
Julia Schottenstein says she is partnering with p0 on Managed Deep Agents. Parallel is now built into the agents, which she says lets them search the web quickly and efficiently.
Related AI news
Databricks says it cut an estimated $1.2M a year in AI waste in one hour
Databricks says Unity Gateway tracing and Genie One identified seven MCP-server bugs behind about $499,000 a year in wasted tokens, roughly 12,000 engineering hours a year of agent wait time, and 1,409 tool errors in 24 hours. Genie One ranked the fixes, and a coding agent helped close them within an hour.
Microsoft Autopilot preview rolls out to first customers on OpenClaw
Omar Shahine said a preview of Microsoft Autopilot, a persistent personal agent, is reaching Microsoft’s first customers and is built on OpenClaw. Peter Steinberger said work with Microsoft to prepare the codebase for large-scale deployments has been underway since March.
Best Taste-Bench model chooses the better direction 59.7% of the time
A paper from Microsoft and colleagues reports that the best model answers 59.7% of Taste-Bench questions correctly when choosing the better open direction in long engineering and research tasks. Forks decided by later evidence are much harder, a larger reasoning budget does not raise accuracy, and distilling a teacher’s outcome judgment improves held-out SWE-bench Pro success.
LangSmith Custom Apps is now generally available
LangChain says LangSmith Custom Apps can create interfaces from agent data with a prompt, including views for labeling runs, comparing experiments, and reviewing traces.
Managed Deep Agents 0.8 supports user memories
Managed Deep Agents 0.8 adds user memories with control over where they are stored. Nathan Drezner said memories created in private contexts are never shared, while Context Hub lets developers inspect general agent memories and keeps user memories private.