Skip to content

Category

AI agents

216 events 20 over 7 days → 0 % 25 sources report highest score 85

Importance: monitoring AI agents 1 source

Haiqu introduced AgenticOS, a platform for automating quantum research

AgenticOS combines specialized AI agents with automated tests, reference calculations and human approval. According to Haiqu, in a demonstration experiment on a quantum processor from IBM, the platform reduced circuit depth by 75 % while maintaining agreement between the results.

Part of a broader thematic overview; only this AI event has been covered.

Importance: monitoring Amazon AI agents 1 source

Postman and AWS described the architecture of Agent Mode on Amazon Bedrock

Agent Mode in Postman runs on Amazon Bedrock. The case study describes task-based tool selection, reading data using schemas and user approval of changes. According to Postman, errors increased when more than approximately 40 tools were made available.

Importance: monitoring AI agents 1 source

Maia assistant has over 400 thousand users, according to Rohlik Group, and supports payment authorization

According to Rohlik Group, the Maia assistant has over 400 thousand users and has handled more than 750 thousand transactions. During a conversation, it assembles a basket, selects a delivery slot and authorizes payment using a saved card. If 3D Secure is not required, the purchase can be completed within a single environment.

Importance: monitoring Anthropic AI agents 1 source

The Claude Science product coordinated agents to create an ultraviolet map of the entire sky

The Claude Science product coordinated AI agents that combined data from space missions and reconstructed missing regions of an ultraviolet sky map. According to the project description, predictions differed from measurements by an average of approximately 10 % in tests. The map is intended for teaching.

Importance: monitoring AI agents 1 source

Incarna deployed payments for individual model calls through BlockRun

According to an article on AWS Machine Learning Blog, Incarna deployed payments for individual model calls through BlockRun. Amazon Bedrock AgentCore payments signs transactions and enforces spending limits. According to the source, the integration took three days.

Importance: monitoring AI agents 1 source

Startup Persona launched a free AI assistant beta and raised 10 million dollars

Startup Persona has raised 10 million dollars and launched a free beta of its personal AI assistant through iMessage. Vine Ventures led the funding round. A wearable wristband priced at 179 dollars is expected to be available in December.

Importance: monitoring AI agents 1 source

Author uses ML Intern to create a smaller model for rewriting prompts

The author used ML Intern to create a prompt-rewriting model with 0.8 billion parameters that, according to the author, runs on a CPU. The compute costs of the project amounted to 16 USD; the author reports 99.7 % valid outputs and approximately a quarter of the token usage.

Importance: important GitHub AI agents ✓ official

Local sandboxing in GitHub Copilot is generally available

GitHub has made local sandboxing generally available in GitHub Copilot CLI, the GitHub Copilot app and VS Code editor sessions with Agent Host. The feature, available at no additional charge, restricts access by running tools to system resources according to policies set by the developer or organization.

Importance: monitoring AI agents 1 source

Cornerstone OnDemand deployed Orion AI and cut database diagnosis time from 45 to 10 minutes, according to internal measurements

Cornerstone OnDemand deployed Orion AI, which coordinates specialized agents for operational tasks. According to internal measurements, it shortened database diagnosis time from 45 to 10 minutes. The system uses Amazon Bedrock and Strands Agents; a three-person team built it in six months.

Importance: monitoring AI agents 1 source

Muse adds native iPad support, more integrations and planning based on a business goal

The update to Muse from Meta adds native support for iPad tablets and more app integrations, including Granola and Notion. According to the company, the agent can independently plan marketing, client proposals and the preparation of product pages based on a business goal entered by the user.

Importance: monitoring Anthropic AI agents 1 source

Claude Managed Agents now applies allowed_hosts to web tools as well

In Claude Managed Agents, the allowed_hosts list now also applies to web_search and web_fetch in cloud environments with restricted networking. Servers that are not allowed are omitted from search results, and the tool returns an error when fetching a page.

Importance: monitoring AI agents 1 source

Mismatched network rules block session creation and updates

Under restricted network access, HTTP 400 is returned if allowed_domains for the enabled web tool contains a host outside allowed_hosts. The check applies both to session creation and to an update that adds such an entry.

Importance: monitoring AI agents ✓ official

OpenAI investigates problems with responses from workspace agents

OpenAI is investigating degraded service in Workspace Agents. According to the status page, responses may not appear for users during the incident. The Agent component is experiencing degraded performance.

Importance: monitoring AI agents 1 source

Instinct rolls out an AI agent in group chats to early-access users

Instinct is gradually rolling out an AI agent in group chats to early-access users. According to the company, friends without an account can also join. The agent is intended to help with tasks such as planning trips together.