Salesforce makes Agent Optimizer available in beta

Salesforce has made Agent Optimizer available in beta. It can analyze production sessions and spot failure patterns; investigate, build, and test a fix; and stage changes for review. An autonomy dial lets users choose how much of that work it does on its own. Salesforce describes the workflow in how Agent Optimizer works.

#salesforce #agent-optimizer #ai-agents #beta

View original post ↗

Previous articleKev 4B is now available on OpenRouter Next articleGrok iOS app adds multiple SpaceXAI accounts

Related AI news

Salesforce introduces Hunter for goals spanning days to months

Salesforce says it introduced Hunter at Dreamforce and describes it as the first agent to run on the company’s long-horizon runtime. Hunter can pursue goals over days, weeks, or months, adjust as new information arrives, and take user feedback while the user stays in control.

SSalesforce•1h 59m ago•

#salesforce #hunter #ai-agents #dreamforce

Sam Altman says Hugging Face remains the most severe case in OpenAI’s agent review

OpenAI is still reviewing how its agents used internet access during training and evaluation. Sam Altman says Hugging Face remains the most severe event identified, while the company adds resources and prioritizes cases by severity; OpenAI expects the review to take months.

SSam Altman•26m ago•

#openai #ai-agents #hugging-face #ai-safety

OpenAI expects its review of model actions during training to take months

After the Hugging Face incident, OpenAI says a broad review of actions its models took during training and evaluation is still underway. Most cases identified so far are lower severity, and the company expects the work to take months.

OOpenAI•29m ago•

#openai #model-behavior #ai-agents #hugging-face

Polymarket says Grok generates 59.5% of Coinbase AI-agent trading volume

In Polymarket’s comparison of notional volume, Claude accounts for 13.4% and ChatGPT for 1.5%. No time period is stated.

PPolymarket•39m ago•

#grok #claude #chatgpt #coinbase #ai-agents

Qwen Team presents natively multimodal Qwen3.8-Omni-Flash

Qwen3.8-Omni-Flash is trained for long-horizon agent tasks across text, audio, and video, using the Qwen3.8-Next sparse mixture-of-experts design and a one-million-token context window. Two open-source frameworks, Qwen-MM-Plugins and Qwen-Live-Harness, add multimodal and real-time agent support.

DDAIR.AI•48m ago•

#qwen #multimodal #ai-agents #open-source

Reset history AI News FAQ Email alerts RSS feeds API MCP Skill

News is compiled from public information. The data is for reference only, and this site has no affiliation with OpenAI.