14 field notes

Prompting

Effective agent prompting is mostly context, constraints, and feedback. These articles show patterns that make multi-step work clearer and more reliable.

Latest in Prompting

Prompting articles and guides

Browse every All Agents Considered article filed under Prompting.

The One File That Made Hermes Finally Learn From Its Mistakes

August 4, 2026

Prompting

The One File That Made Hermes Finally Learn From Its Mistakes

Persistent memory keeps useful context. A small ledger beside each workflow keeps the verified lesson where the next run can find it.

Dan Cucolea Read more: The One File That Made Hermes Finally Learn From Its Mistakes
How I Built A Substack API With Hermes And Codex

July 21, 2026

Product Thinking

How I Built A Substack API With Hermes And Codex

I wanted Hermes to schedule my Substack Notes. A missing scheduling feature turned into an open-source tool built across Hermes, Codex, and a set of independent checks.

Dan Cucolea Read more: How I Built A Substack API With Hermes And Codex
The Twenty Minute Audit That Found Where Hermes Was Getting Lost

July 7, 2026

My Stack

The Twenty Minute Audit That Found Where Hermes Was Getting Lost

I kept upgrading my stack and Hermes kept getting confused. Twenty minutes looking at the right layer told me why.

Dan Cucolea Read more: The Twenty Minute Audit That Found Where Hermes Was Getting Lost
Tear Down Your AI Workflow and Rebuild It Like This

June 30, 2026

My Stack

Tear Down Your AI Workflow and Rebuild It Like This

Most AI workflows produce 80% noise because people tend to connect tons of systems before validating them against what their work needs. Here's the one test that saves you days of configuration.

Dan Cucolea Read more: Tear Down Your AI Workflow and Rebuild It Like This
My Hermes AI Agent Maintenance Routine For Maximum Reliability

May 26, 2026

My Stack

My Hermes AI Agent Maintenance Routine For Maximum Reliability

Copy-paste prompts for checking Hermes memory, gateways, scheduled jobs, model IDs, and backups before silent drift breaks your agent workflows.

Dan Cucolea Read more: My Hermes AI Agent Maintenance Routine For Maximum Reliability
How to Add Approval Gates to Your Hermes Agent

April 28, 2026

Prompting

How to Add Approval Gates to Your Hermes Agent

A practical guide to adding human checkpoints to Hermes workflows, with examples for outbound content, system changes, and paid actions.

Dan Cucolea Read more: How to Add Approval Gates to Your Hermes Agent
How My Hermes Agent Plans My Morning Before I Have My Coffee

April 21, 2026

Prompting

How My Hermes Agent Plans My Morning Before I Have My Coffee

Set up Hermes in 20 minutes and wake up to sorted tasks and curated articles instead of manual scrolling.

Dan Cucolea Read more: How My Hermes Agent Plans My Morning Before I Have My Coffee
The Agentic Engineering Shift

April 14, 2026

Prompting

The Agentic Engineering Shift

Karpathy named two extremes. Here is the spectrum that covers everything in between, and the habits that shift you in the right direction.

Dan Cucolea Read more: The Agentic Engineering Shift
Forgetting to Forget - How Infinite Memory Reinvents OpenClaw

March 10, 2026

Prompting

Forgetting to Forget - How Infinite Memory Reinvents OpenClaw

OpenClaw finally remembers everything. Here's what changed, how I set it up, and what it means for anyone building with AI agents.

Dan Cucolea Read more: Forgetting to Forget - How Infinite Memory Reinvents OpenClaw
The 'First Dollar' Stack

February 24, 2026

My Stack

The 'First Dollar' Stack

The First Dollar stack: Why React + Supabase + Cloudflare is the only V1 combo that doesn't waste your weekends.

Dan Cucolea Read more: The 'First Dollar' Stack
Accepting AI's First Answer Is Bad For Your Code

December 16, 2025

Prompting

Accepting AI's First Answer Is Bad For Your Code

When AI suggests an approach, your immediate thought should be “What else exists?” instead of “Let me implement this.”

Dan Cucolea Read more: Accepting AI's First Answer Is Bad For Your Code
Why AI Gets Stupid Deep in the Thread

December 9, 2025

Prompting

Why AI Gets Stupid Deep in the Thread

Why fresh sessions outperform long threads, according to new research from Chroma and Anthropic.

Dan Cucolea Read more: Why AI Gets Stupid Deep in the Thread
How to Prompt AI for Consistent JSON Responses

December 2, 2025

Prompting

How to Prompt AI for Consistent JSON Responses

AI JSON fails silently in prod. Fix it forever with these 5 checkpoints. 🚀

Dan Cucolea Read more: How to Prompt AI for Consistent JSON Responses
How To Architect A Feature In 5 Minutes Before Talking To AI

November 25, 2025

Prompting

How To Architect A Feature In 5 Minutes Before Talking To AI

AI code works on the surface but can be expensive underneath. Here is the architecture framework that fixes it.

Dan Cucolea Read more: How To Architect A Feature In 5 Minutes Before Talking To AI

The Weekly Dispatch

One tested agent setup every Tuesday.

Step-by-step workflows, prompt and memory configs, and real tradeoffs sent straight to your inbox. No fluff, no sponsored vendor hype.

Free weekly email. Unsubscribe anytime.