Agent Prompts Daily
For operators building with AI agents. One agent-ready system per week. Context engineering, MCP setup, and agent prompts so you and your team ship real work.
- Indexed issues, last 90 days
- 2
- Latest publication
- Sep 28, 2026
- Audience
- Checking…
- Earliest in this view
- Jul 17, 2026
Latest issues
Which of your tasks actually need an AI agent (opens the original)
Read excerpt
This is the doc I fill in before deciding tasks for my agent gets.Copy it, run the audit prompts on your own chat history.[Link to Doc →]<source typ
How to build an MCP stack for real work (opens the original)
Read excerpt
TL;DR: Build around one recurring job and connect only the capabilities it needs at each stage.I was about to connect GitHub to a coding agent when I stopped and ran a smaller test first.A useful MCP stack connects the full job, from research through action, without giving every tool unlimited access.The task was simple. Find a broken function in a local repository, prepare the smallest fix, run the tests, and hand the change back for review.The agent needed four files. It changed one line and g
Publishing over time
Last 90 days. Choose a month to open its work.
Recurring subjects
Named in the text we hold. One piece can cover several.
Audience
No verified audience measurement yet.
About this data
Counts cover the work we have indexed. Tone needs enough text and a confident classification. Excerpts and episode notes are not full articles or transcripts.
Identity or attribution wrong? Suggest a correction.