@craigsolomon

Craig Solomon

@craigsolomonFloridaJoined April 2026

Founder, Fulcrum Enterprises — Building the Foundation for an AI Driven Future

About

Founder, Fulcrum Enterprises. Building the foundation for an AI driven future.

Available for

Freelance work

Craig Solomon's blogs

Craig Solomoncraigsolomon.hashnode.dev23 posts

Articles Comments

Recently published

CSCraig Solomoncraigsolomon.hashnode.dev1h ago · 7 min read

Tuning Keyword Weights From Thumbs Up/Down Feedback in a Monitoring Agent

A keyword pre-filter is the cheap half of any two-pass monitoring pipeline. Items arrive from your sources, the filter matches terms you own, sums their weights, and decides which survivors are worth

CSCraig Solomoncraigsolomon.hashnode.dev2d ago · 7 min read

How to Make MCP Tool Guards Fail Closed in Python

Look at three MCP tool signatures: call_api(url: str, method: str, body: str | None) query_database(sql: str) read_text_file(path: str) Every one of those arguments arrives from a model. Not from you

CSCraig Solomoncraigsolomon.hashnode.dev2d ago · 7 min read

Sanitize or Fail: Two Ways to Handle Rule Violations in LLM Output

An em dash in generated text has one correct fix. Swap it for a comma, swap it for a period, or recast the sentence. The first two are a string replacement. You do not need a second model call to do i

CSCraig Solomoncraigsolomon.hashnode.dev2d ago · 7 min read

How to Make an LLM Score Feed Items Against Your Business, Not in General

Relevance is not a property of an article. It is a function of two arguments: the item, and the business reading it. A scoring prompt that receives only the item can answer only the general question,

CSCraig Solomoncraigsolomon.hashnode.dev5d ago · 8 min read

Idempotent Scheduled AI Drafts: No Duplicates After a Restart

A scheduled drafting agent looks correct right up until the process restarts. The scheduler comes back, the trigger fires, the model returns text, and now you have a second copy of a draft you already