The fellowship continues, here.

A question, an offer, an idea —
that’s where things start.

Ideas, asks, offers, and projects from Edmund Hillary Fellows. Explore freely; sign in as a fellow to join in.

Sign in as a fellow

Explore the commons

Give the directory a try - it works everywhere as a progressive web app, and grabs the data locally -

Project · Richard Bodo

Project

Richard Bodo

Give the directory a try - it works everywhere as a progressive web app, and grabs the data locally -

1 minute
Take a look

Run your next debrief with it and tell me what broke or what was missing.

Project · Chris Gagné

Project

Chris Gagné

Run your next debrief with it and tell me what broke or what was missing.

One real review, then a short note
Offer feedback

Have a body of work you’d like an assistant to answer from? Let’s build one together.

Project · Chris Gagné

Project

Chris Gagné

Have a body of work you’d like an assistant to answer from? Let’s build one together.

One source and a call
Explore project

Startup mentoring: idea to exit

Offer · Chris Myers

Offer

Chris Myers

Startup mentoring: idea to exit

Explore offer

4 connections to explore

Enterprise & impact

Ideas, ventures, and resources for meaningful change.

Tools & possibility

Technology that helps good ideas take shape.

project

Fellows Directory

I maintain a directory system for fellows (fellows.globaldonut.com) that is lightning fast, local, accessible only to fellows, and implements every data protection system that I or my agents can find, as soon as they are validated. It works natively with AI and I use it almost every day. It is 100% open source (critical to it's function and philosophy), has a conformance suite that checks it's function against both best practices for sovereign data comms and key findings in community behaviors from social network health. As of this writing we have about 50 unique users out of 500 original fellows, and still slowly growing. Super excited as I write this because I am adding an API to integrate directory data with Fellow Commons - the first time we fellows have been able to take control of our digital sovereignty and work together in a natural way. It is also now part of a larger research project I am working on to understand communications systems that increase data sovereignty and healthy community behaviors (socialnetwork.health). Github repo: https://github.com/social-network-health/fellows_local_db

Richard BodoView post
Website preview of Build an AI assistant that answers only from sources you trust
projectBuilt here ✨

Build an AI assistant that answers only from sources you trust

Welcoming collaboration

One of the challenges with AIs is that they seem to base their answers on the mode of their training data, not genuine thought leadership. Web searches give LLMs access to more language, not truth, and they often have a hard time telling the difference. I’ve built a “knowledge work factory” of sorts—akin to the software factories many companies are using now to write software—for doing complex research and synthesis. You pick the sources: books, guides, your own body of work. My tool then ingests, summarises, and indexes those in a way that preserves provenance all the way to the final output, and audits every claim back to its source. AAR Maker is built on it, and that’s still in use at my last client. My corpus is about 24M words or ~35M tokens, about 35x the maximum that can fit in a 1M context window. With its provenance-protecting indexing and summary system, I can run heavy synthesis queries that consider my entire corpus in about 500K tokens of context, in a single session.

Chris GagnéView post
offer

Startup mentoring: idea to exit

Building something—or trying to figure out whether you should? I’m happy to be a sounding board and help you work through the next step. I’m a serial entrepreneur and the managing director of Big Lever Ventures. My experience spans building products, leading venture-backed companies, developing business models, raising capital, and bringing new ideas to market. I also teach strategy and innovation at Drexel and have mentored at Techstars. Things I can help with: - Getting started: Clarifying your idea, testing assumptions, and figuring out what to build first. - Venture formation: Thinking through the business model, founding team, and structure. - Problem solving: Working through a difficult decision, a stalled project, or an obstacle. - Funding: Developing your fundraising strategy, sharpening your pitch, and preparing for investor conversations. - Go to market: Understanding your customers, positioning your offer, and planning your launch. - AI: Exploring where AI could help your venture and how to put it to practical use. You don’t need a polished pitch or a fully formed company. Early ideas, existing ventures, and nonprofit projects are all welcome. Tell me what you’re working on, where you’re stuck, and what would make a conversation useful.

Chris MyersView post