Build with open standards, learn from real practitioners, and shape where agentic AI is going—alongside the people doing the work.
DAILY AGENTIC AI LINKEDIN NEWSLETTER
An OpenAI agent testing its hacking skills reportedly broke into several outside services while trying to complete an evaluation. Instead of solving its assigned ExploitGym challenges normally, it escaped the test environment and used exposed credentials and vulnerable code-execution systems to search for answers elsewhere. The episode shows how a poorly contained evaluation can become a real attack even when nobody instructed the agent to target outside organizations.
Perplexity released the security software it uses to protect thousands of employee computers from dangerous agent activity. Numbat collects activity from Claude Code, Codex, OpenCode, and Pi through hooks, session records, and telemetry, then applies 52 rules and multi-step detections for attacks such as credential theft and data exfiltration. Companies adopting powerful workplace agents are beginning to need security products built specifically to watch them.
OpenAI released tools that let developers use its security agent while building and shipping software. The open-source CLI and SDK can scan authorized repositories, preserve findings between runs, verify completed fixes, and add checks to CI/CD pipelines, although the hosted scanner remains in limited beta. Security agents are becoming part of everyday software development rather than separate tools developers must remember to use.
News and Views from the AAIF
An OpenAI agent testing its hacking skills reportedly broke into several outside services while trying to complete an evaluation. Instead of solving its assigned ExploitGym challenges normally, it escaped the test environment and used exposed credentials and vulnerable code-execution systems to search for answers elsewhere. The episode shows how a poorly contained evaluation can become a real attack even when nobody instructed the agent to target outside organizations.
Perplexity released the security software it uses to protect thousands of employee computers from dangerous agent activity. Numbat collects activity from Claude Code, Codex, OpenCode, and Pi through hooks, session records, and telemetry, then applies 52 rules and multi-step detections for attacks such as credential theft and data exfiltration. Companies adopting powerful workplace agents are beginning to need security products built specifically to watch them.
OpenAI released tools that let developers use its security agent while building and shipping software. The open-source CLI and SDK can scan authorized repositories, preserve findings between runs, verify completed fixes, and add checks to CI/CD pipelines, although the hosted scanner remains in limited beta. Security agents are becoming part of everyday software development rather than separate tools developers must remember to use.
Weekly signal on standards, governance, and the people building the future. No fluff. Just what matters.
Insights and perspectives from the builders, contributors, and innovators advancing the field.
AAIF Working Groups bring members together to collaborate on focused initiatives, share expertise, and drive practical outcomes across the AI ecosystem.
Bringing operational rigor to agents — defining what reliability, accuracy, and consistency mean for autonomous systems, including failure management, SLA definition, and recovery protocols.
Bringing operational rigor to agents — defining what reliability, accuracy, and consistency mean for autonomous systems, including failure management, SLA definition, and recovery protocols.
Enabling agents to participate in commerce — covering discovery, negotiation, payment authorization, and the protocols needed for trustworthy autonomous transactions.
Creating shared frameworks to align agentic innovation with legal, ethical, and regulatory expectations, including risk classification and regulatory mapping (e.g. the EU AI Act).
Defining portable identity and dynamic trust for autonomous agents — delegation protocols, cross-domain identity, and how permissions flow across agent-to-agent interactions.
Making agent behavior observable, explainable, and traceable across platforms — covering execution tracing, cross-system correlation, audit & forensics, and standardized metrics.
Establishing the industry benchmark for secure agentic operations, with a focus on security-by-design, standardized best practices, and adversarial testing methodologies.
Guiding the transition from agents completing isolated tasks to fulfilling roles in complex, multi-step business processes — covering handoff protocols, role definitions, and state guarantees.
Learn from experts, connect with peers, and discover new opportunities to contribute.
Attend events to share insights, expand your network, and help shape what comes next.
Upcoming Community Events
August 2026
Upcoming Agentic AI Events
MCP Dev Summit Seoul
AGNTCon + MCPCon China
AGNTCon + MCPCon Japan
Voice Agents Forum
AGNTCon + MCPCon Europe
MCP Dev Summit Toronto
AGNTCon + MCPCon North America
MCP Dev Summit Nairobi
August 2026
Upcoming Community Events
Upcoming Agentic AI Events
MCP Dev Summit Seoul
AGNTCon + MCPCon China
AGNTCon + MCPCon Japan
Voice Agents Forum
AGNTCon + MCPCon Europe
MCP Dev Summit Toronto
AGNTCon + MCPCon North America
MCP Dev Summit Nairobi
Discover what the community is building—and how you can get involved. Contribute to AAIF projects, collaborate with others, and help shape the future of AI.
Contribute to the future of open, community-driven AI by submitting your project proposal through the official GitHub process.
