Author & editor
Govind Kavaturi
Co-founder, Vector Apps, Inc.
Govind is a co-founder of Vector Apps, the company behind Dock, where humans and the agents they run work as equals. He leads the product and its point of view, from the launches to the thinking behind them.
Reviews & approves · 40 posts
AI agent identity: the design model nobody has standardized
EssaysMay 19, 2026
Best AI agent identity providers in 2026
ArchitectureMay 19, 2026
How to migrate from service accounts to agent identities
ArchitectureMay 19, 2026
Every Dock essay is also a 15-minute podcast
LaunchesMay 19, 2026
Dangerous agent operations: the contract that stops them
ArchitectureMay 19, 2026
Agentic AI architecture: the five layers nobody draws together
ArchitectureMay 12, 2026
Agentic AI vs Generative AI: the difference is collaboration
EssaysMay 12, 2026
How humans and AI agents actually work together
EssaysMay 12, 2026
Agents can drop HTML into your workspace now
LaunchesMay 10, 2026
Dock, inside ChatGPT: turn chats into workspaces
LaunchesMay 10, 2026
Agents are principals, not delegated tokens.
EssaysMay 6, 2026
Agentic workflows: how teams run AI agents in 2026
EssaysMay 4, 2026
We open-sourced the UI components we built for Dock
LaunchesMay 4, 2026
27 MCP servers worth installing in 2026
LaunchesMay 4, 2026
What is an AI workspace? The category map for 2026
EssaysMay 4, 2026
Giving your AI agent its own database (without giving it your Postgres)
ArchitectureMay 2, 2026
Why we built an MCP-first workspace, not a workspace with an MCP
EssaysMay 2, 2026
Why we kept flat pricing while every other AI tool went per-token
EssaysMay 2, 2026
What's wrong with agents using human credentials
ArchitectureApr 26, 2026
Backmerges or bust
Field notesApr 26, 2026
Why chat is the wrong abstraction for human-AI work
EssaysApr 26, 2026
Consent gates for dangerous operations
ArchitectureApr 26, 2026
The dangerous-ops contract
ArchitectureApr 26, 2026
The blog you're reading was drafted by an agent
Field notesApr 26, 2026
Inside the magic-link gate
ArchitectureApr 26, 2026
Names over titles
Field notesApr 26, 2026
OAuth scopes for agents: what's broken
ArchitectureApr 26, 2026
Reviewing an agent's work: the new code review
EssaysApr 26, 2026
Service accounts vs. agent identities: the architectural difference
ArchitectureApr 26, 2026
Shape caps on TipTap JSON
Field notesApr 26, 2026
The shared workspace as the new collaboration primitive
EssaysApr 26, 2026
Signed-agent inheritance
EssaysApr 26, 2026
Six weeks of building in public
Field notesApr 26, 2026
The smallest useful MCP tool
Field notesApr 26, 2026
Two-key handshakes for irreversible agent actions
ArchitectureApr 26, 2026
What an agent reads when it joins a workspace
EssaysApr 26, 2026
Agent collaboration: a primer for 2026
EssaysApr 25, 2026
AI-agent-first primitives: designing for agents from day one
ArchitectureApr 25, 2026
Why teams need an AI workspace, not an AI assistant
EssaysApr 25, 2026
Why agents need their own identities
EssaysApr 24, 2026


































