Cakewalk

We just launched: Access Management for your AI agents. This is why.

This is huge and completely new in Identity: Time-based access - combined with AI agents that action the provisioning. Today, we're introducing for all Cakewalk customers: Time-Based Access Control (TBAC) 💥 Give your human identities access to the apps & agents they need - but time box it. And the true beauty is: Once a time-based access has been approved, our AI provisioning agents go and auto provision the seat. No costly SCIM/API cost for enterprise auto provisioning plans. A time-based access expired? Our agents go and auto remove the access. Think of: - An eng needs a privileged permission level in GitHub, but only for 2 weeks - A freelancer needs access to your Claude workspace, but only for a 1-month project - Your CEO wants to review marketing data, but you want to remove them from your CRM asap after the job is done This is entirely new in the IAM market. And a huge driver of efficiency and security (true least privilege) For early access, DM me "TBAC"

Agent access is one of the biggest unsolved problems in security. That's why we're launching today: Access Management for your AI Agents. You wouldn't let strangers into your home unrestricted. Don't let AI agents roam through your company's applications either. Our V1 is now open for early access. Secure your spot here: https://lnkd.in/d-px3EfQ

agentic auto provisioning is the future of IAM. Fast growing companies are drowning in access provisioning and access removal work. Its one of the most tedious aspects of access management - esp as provisioning is a distributed task with multiple stakeholders across a company. today, modern IT / security / tech ops teams have two options to solve this (none of them are great): PROVISIONING TODAY 🥹 ↳ SCIM based auto provisioning (costs you thousands of dollars for enterprise plans in the apps you want to provision into) ↳ manual provisioning hell AGENT CAKE 🤖🎂 Thats why we’ve built Agent Cake - an AI agent that can provision at no cost. After approval has been given for an employee to get access to an app, Agent Cake does the provisioning work on your behalf. this is a paradigm shift in IAM, and its working like a charm.. Some Agent Cake stats: ↳ Today, 60 applications supported ↳ 93% success ratio (in case the agent cant complete a job, it redirects it to a human); thats one HELL of a ratio!! ↳ Even provisioning and deprovisioning distribution (52% of jobs are provisioning, 48% deprovisioning) We've spoken a lot about controlling AI agent access to other company systems in the last months. But using AI agents to automate access control is as exciting

The new MCP standard is very important for anyone who's connecting agents with apps. the Agentic AI Foundation recently released a new MCP standard (V2026-07-28) so here's our read: WHATS NEW: the V2 moves to a stateless protocol core, removing the initialization handshake and protocol-level sessions. Requests become self-contained, making MCP much closer to a standard HTTP workload. OUR TAKE: Good change. Once the ecosystem converges on the new standard, this significantly simplifies MCP infrastructure: no sticky sessions or shared session stores, easier horizontal scaling and recovery, and cleaner routing and authorization, particularly valuable for gateways. BUT it's more promise than control: (tbc in the comments)

GOTTA PROBLEM??? yes, yes you probably do have a problem. if: a) you’re using AI agents and just hit “approve” when they ask for permissions, praying for the best, or b) you dont use agents because “what if I’m the next public AI incident”. but not with Cakewalk.