AI agents
79 RohitAI articles on AI agents: news, explainers and practical guides, newest first.
LangChain adds browser control and background work to managed AI agents
LangChain’s October 29 update adds browser tasks, human login handoff and background helpers, with shared-state tradeoffs and beta access requirements.
What OpenAI’s updated rules mean for AI memory and permission
OpenAI’s revised Model Spec separates remembered context, permission to act and verified deletion. What the rules mean—and which ChatGPT controls to check.
Windmill adds chat-based building and testing for reusable AI agents
Windmill’s October 28 update adds agent building and testing to AI Sessions, with role-based access, real tool execution and separate model costs.
GitHub previews organization-owned access for background Copilot agents
GitHub’s Copilot preview lets background apps use organization-owned access. Usage is billed to the organization, with no separate budget for each app.
What Salesforce Agent Fabric’s spending controls cover
Salesforce says its AI cost controls are generally available. Check proxy coverage, model prices, budget overshoot and fallback behaviour before buying.
SAP details phased Joule Studio rollout for custom workplace agents
SAP’s Joule Studio rollout separates free authoring from paid production. Here’s what teams need to know about access, runtime charges and n8n availability.
IBM makes identity controls for workplace AI agents generally available
IBM’s Agent Identity links workplace AI agents to owners and delegated permissions. Its launch is separate from Orchestrate’s preview containment tools.
Claude brings scheduled agent tasks to its AWS platform
Claude Platform on AWS now supports recurring agent work. Check permissions, timing limits and per-run budgets before scheduling reports or reviews.
Claude adds tracing tools to help teams investigate slow or failed AI tasks
Anthropic’s tracing beta helps teams investigate Claude application delays. Choose hosted or SDK coverage, then decide which conversation data to export.
When Claude’s new workflow beta makes sense for document review
Claude Managed Agents can coordinate large document jobs. How to choose workflows or batching, check review coverage and compare costs per accepted document.
Sophos’s Daybreak MDR Workflow: What to Check Before Automating Response
Sophos’s Daybreak case study puts MDR automation in focus. Examine the reported metrics, customer response modes and evidence needed for a bounded pilot.
Hugging Face ML Intern: Fine-Tuning Budgets, Baselines and Model Review
Use HuggingChat ML Intern with compute caps, baseline comparisons and model-card checks. A practical guide to budgeting and accepting a custom-model experiment.