AI news

AI news, first-hand

Short notes on model releases, tools and regulation — from official blogs, changelogs and GitHub releases. No retelling: every note links to its primary source.

30-day median: a note shows up here 11 h 21 min after the source publishes it

Today

Yesterday

AgentsLangChain

Announcing Data Annotation Queues

Review logs, annotate data, and build datasets with LangSmith's Data Annotation Queues. Improve LLM app performance from prototype to production.

Primary sourcecaught 16 h 24 min after publication

November 18, 2026

November 17, 2026

November 16, 2026

AgentsLangChain

From tasks to goals

LangChain CEO and Co-founder Harrison Chase shares how we're moving from task-specific agents to goal-focused agents. Learn more.

Primary sourcecaught 6 h 7 min after publication

November 14, 2026

AgentsLangChain

Goal Engineering

The future of agents is them taking on open ended goals and driving towards completion of those goals. Learn more.

Primary sourcecaught 14 h 1 min after publication

November 13, 2026

November 12, 2026

November 10, 2026

November 9, 2026

November 5, 2026

AgentsLangChain

Agents Are Going Async

Async subagents let an agent stay responsive while background workers run long tasks. How the orchestrator, notifications and approvals work in Deep Agents.

Primary sourcecaught 9 h 57 min after publication

November 4, 2026

November 3, 2026

November 2, 2026

October 29, 2026

AgentsLangChain

Browser Use in Managed Deep Agents

Managed Deep Agents now runs a browser for your agent, with tools tuned for context-efficient browser use and a handoff so you can sign in yourself.

Primary sourcecaught 13 h 15 min after publication

October 28, 2026

AgentsLangChain

The Art of Loop Engineering

Agents automate real-world work, but reliable performance requires more than a good model, it requires a carefully designed harness built for specific tasks.

Primary sourcecaught 8 h 59 min after publication