I built Alice with local self-learning memory. Alice is my outbound research, lead gen and drafting agent. She can crawl and enrich leads, store memory and RAG data locally in SQLite, generate drafts with a local LLM, create reports, and expose MCP tools for other AI clients. But the real feature is this: Alice does not write one email and forget. When I accept, reject, send, or get a reply from a draft, she can store that outcome as memory. The next draft can use those lessons. Every campaign makes the next campaign smarter. Her sales voice is direct, evidence-led, and consultative. No generic “hope you’re well” outreach. Alice studies the business, finds a real angle, and frames the message around value creation. She combines: - lead research - audit evidence - brand voice rules - accepted/rejected feedback - outreach outcomes - sales playbooks - knowledge RAG Every draft has intent: warm first contact, value creation, objection follow-up, or closing. The best part is how she angles things. Alice can turn a small business weakness, unclear offer, or missed opportunity into a useful sales conversation without sounding pushy. No cloud memory. No black-box training. Just local feedback loops, RAG, and measurable outcomes. Less like a prompt. More like a local operating system for outbound.

I scraped dailyremote.com. I have heard of web scraping and thought it sounded so very difficult to do and technical. I mean it is in a way , you need some know how but I'm on day 2 and scraping a site. As a use for this new found skill. I used to manually web scrape sites for a company looking for potential clients. Those were some long days, but I was getting paid. If I had this 5 years ago, I would could have sold this skill to that company and made some good money. I believe it can still be used in that way and so many other ways. Super exited to have learned this skill.