Blog

Writing

Life, tech, and everything in-between.

Graph Engineering Is Not a New Discipline. That Is the Point.

12 minAI

A new label is going around for building agentic systems as explicit execution graphs. The label is barely real. The shift underneath it is, and the evidence for and against it is more interesting than either side admits.

Scaling and Cost Optimization for LLM Agentic Systems

7 minAI

Multi-agent architectures amplify both capability and error. Google DeepMind measured the amplification across 180 configurations. Anthropic reports 90 percent cost reductions from a planner-plus-workers split. Both results inform how to scale production agents.

Group Chat Patterns: Round-Robin, Selector, and Swarm for LLM Agents

7 minAI

When several agents share a conversation, the question becomes: who speaks next? Microsoft AutoGen names four ways to decide. Each produces a different coordination style, with different strengths on different workloads.

The Shared Scratchpad: A Common Workspace for Collaborating Agents

6 minAI

When agents need to see what each other are doing, neither a supervisor nor a handoff will do. Give them a shared workspace instead. Every agent reads from and writes to the same state. Context sharing is maximal, but so is the risk of distraction.

Handoffs and the Swarm Pattern: Peer-to-Peer Agent Transfer

7 minAI

A supervisor is not the only way to coordinate agents. In the swarm pattern, agents transfer control to each other through handoff tool calls. No central manager; the conversation simply moves to whichever specialist it needs to be with.

Hierarchical Teams: Supervisors of Supervisors in Multi-Agent Systems

7 minAI

A supervisor with five specialists works. A supervisor with twenty does not. Hierarchical teams stack supervisors, each responsible for a department of specialists, and keep a dual ledger to track plan and progress separately.

Supervisor and Router: A Central Agent That Delegates to Specialists

7 minAI

When a single agent carries too many tools and too many responsibilities, the fix is not a bigger prompt but a supervisor whose tools are other agents. Each specialist has its own prompt, its own tools, and its own scratchpad.