Rich Schefren

Right now, somewhere in your team's notes, decisions, and meeting transcripts, sit dozens of margin claims, partner commitments, and customer promises that quoted the old price. They are now wrong. Your memory system — Notion, your vault, Slack search, whatever — does not know. I shipped a memory layer today that does. It's called Atlas. github.com/RichSchefren/atla… Atlas is open-source, local-first, and runs on your laptop. When a fact in your memory changes, it walks the dependency graph and re-evaluates every belief that depended on it. Automatically. Not at retrieval time, when you ask the question — at *ingestion time*, the moment the new fact lands. The math is the AGM postulates from 1985 (Alchourrón-Gärdenfors-Makinson). The same formal correctness Young Bin Park proved on a property graph in his 2026 paper at Kumiho. Atlas re-implements it as fully open-source local-first code anyone can audit. 49 of 49 compliance scenarios pass at 100%. Local-first means: Neo4j on your machine, SQLite ledger on your machine, your data never leaves your hardware. No cloud, no telemetry, no API keys for the core path. Apache 2.0. If you build with AI agents, plug it in: Claude Code MCP, Hermes, OpenClaw. If you keep an Obsidian vault, point Atlas at it — when contradictions emerge, they show up as markdown files in your vault for you to resolve. The repo, the paper draft, the 49-scenario reproducibility artifact, the BusinessMemBench head-to-head benchmark, and a 12-second demo are all at lnkd.in/exiXPmYK. If you've been frustrated by AI tools that "remember" everything but reason about none of it, this is the open-source layer that closes the gap. — Rich #opensource #ai #knowledgemanagement #memory #localfirst github.com/RichSchefren/atla…

Your AI system is learning whether you manage it or not. It learns from what you accept, what you correct, which source you trust, and which mistakes you let pass. The question is whether it's learning the right lesson.

Adapt the tools. Keep the faculties that let you adapt.

Three things I would protect through any technology shift: Proximity to the customer The ability to make a hard call The habit of testing belief against data Everything else can be rebuilt.

The founders who win the AI shift won't be the ones who tried every model first. They'll be the ones who kept their judgment sharp, redesigned the business, and learned faster without handing the company to the machine.

The best asset is one that teaches you while it works.

Tools don't compound. Skills can. Customer knowledge can. Trust can. Decision quality can. Own more of what gets better with use and less of what expires with an update.

Content does not compound because you keep publishing it. It compounds when each piece sharpens the idea, attracts the right person, teaches you what resonates, and improves what you say next.

You cannot redesign a business you're still describing from memory.

Describe the business as it works today, not as the org chart says it works. Who really decides? Where does work really wait? Which offer really drives profit? Start there.

At some point, you realize the company you built is not the company you now run. The customers changed. The team changed. The economics changed. Your role changed. But the operating model never caught up.

The hardest rules to question are the ones that once made you successful.

When growth stalls, don't begin with new tactics. Find the oldest important assumption in the current model and test whether it's still true. The constraint may be a decision everyone stopped noticing.

Most business ceilings are made from decisions that once worked. The offer, org chart, price, approval rule, and customer definition were answers to an older problem. Growth changes the question.

More intelligence does not excuse a mess.

Every new part of an AI system should earn its place: What failure does it prevent? Who owns it? How will we know it's broken? Can a simpler part do the job?

AI makes it easy to add one more agent, workflow, rule, and integration. Soon nobody knows which part made the decision or why a simple change broke three things. Complexity is still debt, even when AI wrote it.

An install without upkeep becomes a very expensive snapshot.

When an AI system plateaus, inspect the feedback loop: Are corrections captured? Do they reach the next run? Can anyone retire a bad rule? Is the result measured? The model may not be the bottleneck.

"We installed AI and then plateaued." Of course. Installation gives you a starting system. Improvement comes from real use, honest correction, and someone owning what gets learned.