Notes
All notes · 37
- How do you trust AI output without checking every line?Stop rechecking every line of AI output: agree what right means, show sources, run rule based checks that flag what to look at, and sample the rest.
- How do employees use AI agents day to day?You don't need a new app for AI agents. People approve drafts in Slack, Teams or email, ask their own AI tool, and review what agents left in their systems.
- How to build a context graph from the systems you already haveWhich system holds which part of a context graph, how the same customer is matched across them, and how the graph stays current, without moving data out of the ERP.
- Who owns the AI platform after launch?After an AI agent goes live, one person inside the company must own the rules and approvals. Three ways to split the job with a partner, and what to agree first.
- What a CompanyOS actually isA CompanyOS is not a manual agents read. It is the structure they act through: an ontology surfaced from your tools, rules on each action, kept as code.
- The company context layer: one approved source for every AI toolA company context layer is one approved, maintained source of definitions, documents and permissions that ChatGPT, Copilot, Claude and your agents all read from.
- AI for order intake and quoting on a legacy ERPCan AI agents handle order intake and quotes when your ERP is old or has no API? What they read, what they draft, where a person approves, and how to start.
- How to build a company OS for AI agents without migrating your toolsA company OS gives AI agents the rules of your business. What it should hold, why agents should act through an ontology on a graph instead of your tools, and how to start without a migration.
- Context graph vs knowledge graph vs ontologyAn ontology defines the kinds of thing, a knowledge graph fills them in, a context graph is the slice one task needs. Side by side, with a manufacturing example.
- AI agents vs RPARPA runs fixed scripted steps in UIs and APIs. AI agents use judgement within agreed limits on a world model. When each fits, and when to combine them.
- Context graph vs world modelA world model is the maintained company map over time. A context graph is the task-scoped slice agents get for one job.
- How to build a world model for your companyBuild a world model for your company: start from one piece of work, audit it, write the ontology, connect sourced data, then grow it in two-week cycles.
- What is an enterprise world model? Three meaningsAn enterprise world model means one of three things: a simulation that predicts outcomes, a synthetic agent environment, or a sourced map of the company.
- Approvals and control for AI agentsHow to design human in the loop approvals, permissions and audit trails for AI agents, so they can act in your systems without losing control.
- Why AI agents fail in productionWhy AI agents that work in a demo fail in production: no agreed standard, a missing model of the business, too much access, no owner. How to fix each one.
- Agentic vs generative AI: what’s the difference?Generative AI produces content when asked. Agentic AI pursues a goal over several steps, using tools in your systems. The difference, and agents vs chatbots.
- Forward deployed AI companies in 2026: who embeds engineersWhich companies embed AI engineers on site in 2026: model labs, cloud and software vendors, platform companies and consultancies. Sourced, checked 11 Oct 2026.
- Forward deployed engineer vs consultantA forward deployed engineer builds and runs the system inside your company. A consultant recommends. A solutions engineer helps you buy. Which you need.
- How to build an ontology for AI agentsHow to build an ontology for AI agents in seven steps: start from one piece of work, name the kinds of things, their sources, relationships and allowed actions.
- How to measure the ROI of AI agentsMeasure AI agent ROI per piece of work: baseline quality, cost, time and effort, track cost per accepted task, then stop or scale. With a worked example.
- Why do AI agents give confident wrong answers?AI agents give confident wrong answers because they get your tools but not the map of your business. Why prompts and more tools fall short, and the fix.
- How to deploy AI agents in an enterpriseHow to deploy AI agents in an enterprise in seven steps: start from one piece of work, audit it on site, redesign it, agree the standard, then build and run it.
- Map first, tools secondAI agents get tools built for people and rebuild a map of the company on every run. A world model for knowledge work gives them the map; the tools feed it.
- World model vs knowledge graph: what is the difference?A knowledge graph records what exists and how it connects. A world model adds when each fact was true, where it came from, and which facts are accepted.
- What is a context graph for AI agents?A context graph for AI agents is a connected record of what one task needs: the things involved, their current state and the decisions behind them, sourced.
- What the EU AI Act asks of B2B companiesThe EU AI Act asks little of the AI work that creates most value and a lot of AI that decides about people. The dates, the tiers and what we would do now.
- One week at one companyAI agents for sales, a week after the first call: a list that refreshes itself, meeting prep before every call and a territory model new reps can ask.
- The case for GraphRAGGraphRAG builds a connected view of your documents once and reuses it, to answer questions no single document answers, more fully than plain retrieval.
- Agree the standard before you buildBefore you build an AI agent, agree the standard on real examples: quality, cost, time and human effort. The pilots that die never agreed what good meant.
- Redesign the work before you automate itAn agent on the current process makes it faster, waste included. So the first two weeks of a deployment redesign the work, and only then do we build.
- More context makes agents worsePast a point, adding context degrades an agent. It needs the smallest sufficient view of the work, and only a model of the company can decide what that view is.
- Why coding agents work and company agents don'tCoding agents took off because a repository is already a world an agent can stand in. A company is not, so you build that world before the agent can work.
- The model can be rented. Your world cannot.Every company rents the same AI models at a falling price. The advantage that lasts is a maintained model of your own business for them to work in.
- What sight meansConnected facts show what no single source contains. That is the real payoff of a world model, and the larger bet we are making.
- What is a world model for knowledge work?A world model for knowledge work is a sourced, current map of a company that AI agents query instead of guessing. What it holds, its layers and examples.
- What is an ontology for AI agents?An ontology defines what exists in a business, what it means, how things relate and what can be done, so AI agents can act on it. With a sales example.
- Access is not a mapConnecting an agent to the CRM, Slack and email gives it territory. The map, what those things are and how they relate, still has to be built.
No featured notes yet.
Newsletter
Get new notes by email.
Unsubscribe at any time.
Start with a call.
We look at where the work in your company is held up and whether an audit is worth it. You don’t need to know yet what AI should do.
