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
The MCP 2026.07.28 release candidate removes mandatory handshakes and session IDs, so any request can hit any server instance instead of being tied to one long-running connection. Remote MCP servers can now behave more like normal cloud services: easier to load balance, easier to restart, easier to scale, and less fragile when agents start calling tools in production. Also added first-class extensions, including MCP Apps and Tasks, and tighter auth
Tessl analyzed 1,281 coding-agent runs in large codebases and found the useful story is not that agents fail, but how they fail. The patterns point to the next wave of agent infrastructure: tighter context boundaries, better repo understanding, verification loops, evals, and workflow design instead of just yelling “use a smarter model”
Anthropic’s official Claude Code plugin repo hit GitHub Trending after a real maintenance burst: 24 new first-party plugins from major-brand orgs, MCP tunnels support, nightly plugin SHA updates, HTTP MCP server liveness checks, broken config fixes, and updates for Snowflake, MercadoPago, Carta, Convex, Spotify, ZoomInfo, CrowdStrike, PagerDuty, Vanta, and Box. This is starting to look like maintained distribution infrastructure for Claude Code
News and Views from the AAIF
The MCP 2026.07.28 release candidate removes mandatory handshakes and session IDs, so any request can hit any server instance instead of being tied to one long-running connection. Remote MCP servers can now behave more like normal cloud services: easier to load balance, easier to restart, easier to scale, and less fragile when agents start calling tools in production. Also added first-class extensions, including MCP Apps and Tasks, and tighter auth
Tessl analyzed 1,281 coding-agent runs in large codebases and found the useful story is not that agents fail, but how they fail. The patterns point to the next wave of agent infrastructure: tighter context boundaries, better repo understanding, verification loops, evals, and workflow design instead of just yelling “use a smarter model”
Anthropic’s official Claude Code plugin repo hit GitHub Trending after a real maintenance burst: 24 new first-party plugins from major-brand orgs, MCP tunnels support, nightly plugin SHA updates, HTTP MCP server liveness checks, broken config fixes, and updates for Snowflake, MercadoPago, Carta, Convex, Spotify, ZoomInfo, CrowdStrike, PagerDuty, Vanta, and Box. This is starting to look like maintained distribution infrastructure for Claude Code
Weekly signal on standards, governance, and the people building the future. No fluff. Just what matters.
Signals from the people building agentic AI
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.
Access working group outputs. Shape standards being written right now.
Work with like minds, build amazing projects
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
Learn what others are building and how you can be a part of this. By contributing to this , you get to build your future and be a pioneer
Contribute to the future of open, community-driven AI by submitting your project proposal through the official GitHub process.
