Dobby

Blog

Practical guides on AI agent governance, the Agentic Gateway, and building production-ready agent infrastructure.

FinOpsArchitectureObservabilitySecurityStrategyGovernanceGetting StartedDeveloper
FeaturedFinOps

How We Track Per-Agent AI Costs Across 13 LLM Providers

Most teams know their total LLM spend. Few know which agent costs what. Here is how we built a gateway that breaks down costs per agent, per model, per day — with one line of code.

Apr 3, 20265 min readGil Kal
FeaturedArchitecture

External Agent Management: Run Anywhere, Control from One Place

Your AI agents run on CrewAI, n8n, Make, LangChain, or custom infrastructure. Dobby gives you scheduling, triggering, approvals, and audit trails without touching your agent code.

Apr 1, 20267 min readGil Kal
FeaturedSecurity

AI Agent Security: 5 Risks You Are Probably Ignoring

Prompt injection, credential exposure, data leakage, model poisoning, and uncontrolled access. How to secure your AI agents.

Mar 30, 20268 min readGil Kal
FeaturedStrategy

Why AI Agents Need a Control Plane

Every infrastructure layer got its control plane -- Kubernetes for containers, Datadog for servers. AI agents are next, and the stakes are much higher.

Mar 28, 20267 min readGil Kal
FeaturedFinOps

How to Control AI Agent Costs Before They Control You

AI agents are powerful and expensive. Without token budgets and provider quotas, a single runaway agent can burn your monthly LLM budget in hours.

Mar 22, 20267 min readGil Kal
FeaturedGetting Started

Getting Started with Dobby AI in 5 Minutes

A practical step-by-step guide to connecting your first AI agent to Dobby AI, setting up governance policies, and running your first fully monitored task.

Mar 20, 20265 min readGil Kal
FeaturedGovernance

Why AI Agents Need a Governance Layer

Without centralized governance, AI agents create security risks, budget overruns, and compliance gaps. Learn how to build a governance layer that works.

Mar 18, 20267 min readGil Kal
Observability

AI Agent Observability: How to Monitor What Your Agents Are Doing

Build real-time visibility into your AI agent fleet. Audit trails, cost dashboards, health checks, and anomaly detection.

Mar 317 min read
Strategy

What Kubernetes Did for Containers, a Control Plane Does for AI Agents

The parallel between container orchestration and AI agent management. Why every infrastructure layer needs its control plane.

Mar 296 min read
Governance

Role-Based Access Control for AI Agent Platforms

Design a 3-level RBAC hierarchy for AI agents. Platform, organization, and tenant roles with 6 permission levels.

Mar 287 min read
Strategy

How to Choose an AI Agent Framework (And Why It Does Not Matter)

CrewAI vs LangChain vs OpenAI Assistants vs custom. The framework matters less than how you manage the agents.

Mar 278 min read
Governance

Human-in-the-Loop: Why AI Agents Still Need Humans

Fully autonomous AI agents sound exciting — until one overspends your budget or sends the wrong email. Approval gates keep agents productive and safe.

Mar 266 min read
Architecture

Managing AI Agents Across Multiple Frameworks

Your team uses CrewAI for orchestration, LangChain for RAG, and OpenAI Assistants for customers. Here is how to manage them all from one place.

Mar 246 min read
Developer

MCP Protocol: Connecting AI Agents to the Real World

The Model Context Protocol (MCP) gives AI agents structured access to tools and APIs. Here is what it is, how it works, and why it matters.

Mar 198 min read
Architecture

The Agentic Gateway: Control All LLM Traffic

A deep dive into the Agentic Gateway pattern -- a unified proxy that authenticates, meters, and enforces governance policies on every LLM and MCP request.

Mar 158 min read

Ready to manage your AI agents?

Start free — no credit card required.

Get Started