Tag: ai-agents
All the articles with the tag "ai-agents".
-
Field Log 7 ReferencesWrite the Spec Before the Prompt: A Copy-Paste Template for Spec-Driven Agent Work Orders
Prompts are one-shot utterances; specs are contracts. Here is the minimal spec template we hand to coding agents — plus the scaling rules for when one page is enough and when you need four files.
-
Field Log 0 ReferencesThe Zero-Cost Vibecoder Stack: Building a Research Agent for Free
How to build a fully automated research and summarizing agent using 100% free APIs: Firecrawl, Groq, and ArXiv.
-
Field Log 1 ReferencesOne Command, Full Research: Building a Local Knowledge Engine with musu-crawl-ai
How a single Go binary replaces your scattered research workflow — fetching YouTube, Arxiv, GitHub, and the open web into a structured, searchable wiki.
-
AI Tool Note 1 ReferencesSelf-Improving Agents Need a Judge Outside the Loop
A self-improving AI agent without an external judge is just a machine for producing cleaner mistakes. Why autonomous improvement loops need strict human and technical boundaries.
-
AI Tool Note 1 ReferencesThe Writing System Needs a Harness, Not More Prompts
A packet-backed draft on why better agent writing needs an evaluation harness, not prompt taste alone. How to build a writing loop that can actually say no.
-
AI Tool Note 3 ReferencesUse HTML to Review Agent Output, Not to Replace the Contract
HTML is great for reviewing complex AI agent outputs, but dangerous as a system of record. Learn why the final decision must always export back to Markdown or JSON.
-
AI Tool Note 3 ReferencesThe Work Disk Contract: Managing Artifacts in AI Coding Agents
AI coding agents generate artifacts like builds, tests, and logs. Discover why defining a strict 'Work Disk Contract' is crucial to prevent operating system failures and lost evidence.
-
AI Explainer 3 ReferencesHow to Stop AI Agents From Losing Their Memory: The Operating Structure
Long LLM prompts are not operating memory. Learn how to build an artifact-driven memory stack with source notes, specs, and searchable indexes for autonomous AI agents.
-
Field Log 3 ReferencesDESIGN.md: Turning Visual Taste Into a Strict Agent Contract
Visual design for AI agents fails when built on screenshots and vibes. Learn how DESIGN.md turns UI taste into an inspectable, lintable technical contract.
-
AI Explainer 3 ReferencesSoftware 3.0 Is a Verification Problem
The useful Software 3.0 lesson is not that LLMs replace engineering. It is that faster generation moves the bottleneck to context, review, and evidence.