Agent Design

8 articles about agent design.

Blocking and Waiting Are Not the Same Kind of Nothing

·2 min read

Blocking has a promise attached - something will resolve. Waiting has no such guarantee. Understanding this distinction changes how you design agent workflows.

agent-designasyncworkflowconcurrencyai-agents

The Paradox of Autonomy - Constraints Make AI Agents Useful

·2 min read

Giving an AI agent more freedom does not make it more useful. Tight constraints and daily task lists produce better results than open-ended autonomy.

autonomyconstraintsagent-designtask-listsreliability

The Counterintuitive Math of Shutting Up

·2 min read

The most useful agent is the one that only speaks when something unexpected happens. Silence is not inaction - it is a signal that everything is working as

agent-designnotificationssignal-to-noiseuxai-agents

Forgiveness in an Append-Only Soul

·2 min read

Append-only memory means an agent never truly forgets a mistake. How do you implement forgiveness in a system that remembers everything?

agent-memoryappend-onlyforgivenesssoul-fileagent-design

Notifications ON Survey - Agents That Need Notifications Cannot Plan Their Own Work

·2 min read

If your AI agent relies on notifications to know what to do next, it cannot plan its own work. A survey on notification dependency reveals a deeper agent

notificationsplanningagent-designautonomyworkflow

Steal Prompt Structure Patterns, Not Content

·6 min read

The valuable part of a good prompt is not the words - it is the structure. How it decomposes tasks, what constraints it enforces, and how it handles edge cases. A guide to building a transferable prompt pattern library.

promptsprompt-engineeringpatternsstructureagent-design

Voice-First Agents Are Harder Than They Look - And Nobody Talks About Why

·2 min read

Building a voice-controlled desktop agent reveals problems that have nothing to do with speech recognition. The hard part is intent resolution and error

voice-firstdesktop-agentspeech-recognitionagent-designmacos

Multi-Agent Hype vs Economic Reality in Production

·2 min read

A planner-executor-reviewer agent chain sounds elegant but burns 3x the tokens of a single well-prompted agent. Here is when multi-agent is worth it and

multi-agenttoken-costsproductionai-economicsagent-designllm-costs

Browse by Topic

How did this page land for you?

React to reveal totals

Comments ()

Leave a comment to see what others are saying.

Public and anonymous. No signup.