AI Systems
Agent audit trail: reconstruct the action, approval, and outcome
If the only witness is the agent, you do not have an audit trail. You have a testimony.
Category
AI Systems
Practical analysis of AI agents, reasoning systems, and reliable automation for founders and operators shipping production software.
AI Systems
Agent runtime budget: keep retries inside the same ceiling
A cap that resets on every retry is a cap per attempt, not per task.
AI Systems
Agent shadow mode: evaluate proposals before granting action rights
Let the agent be wrong on paper first, where a mistake costs a comparison instead of a customer.
AI Systems
The Agent Trust Ladder: how an AI role earns autonomy
A scorecard records how the role performed. The ladder decides what it may do next. The action still sets the ceiling.
AI Systems
An agentic workflow is not an automation
A script repeats a path. An agentic workflow holds a goal, uses tools, and needs a ceiling.
AI Systems
AI agent or chatbot: three tests before you mix the words
If it cannot refuse a tool call, it is not an agent you can run. It is a demo that can spend money.
AI Systems
AI Agents for Startup Strategy: Build the Strategic Intelligence Layer
Agents are infrastructure, not toys. This book installs a strategic intelligence layer you can design, govern, and run in ninety days.
AI Systems
AI fake citations: a 15-minute check for the claims that matter
A citation makes two claims: this document exists, and it says this. Check both in the source itself, not by asking the tool.
AI Systems
CHORUS and Chorus AIDLC: which one do you mean?
One is a way of working you write down. The other is software you install.
AI Systems
Dutch costs 20% more GPT tokens than English. We measured it on 78 article pairs
Same content, same author, two languages. The Dutch version was 2% longer in words and 20% longer in tokens.
AI Systems
Evaluate the reasoning, not the fluency
A fluent answer is not a graded one. Score the trace before you trust the sentence.
AI Systems
Frontier, workhorse, or local: three classes, not a religious war
The forum fight is cloud versus local. The operator question is which class owns this task.
AI Systems
Governed agent memory: what may persist, and who may write it
An agent's memory is a database that the agent writes itself. Give it the rules you would give any other database.
AI Systems
HITL in AI workflows: put the named person on the irreversible step
If the model can ship while the reviewer is on a plane, you did not apply HITL. You labelled a spectator.
AI Systems
How many AI agents can one person supervise?
Starting another agent is a one-time decision. Reading its work, checking its handoffs and handling its exceptions come back every week.
AI Systems
When nobody approves in time, your AI agent must not act
An expired request records silence. A rejected request records a decision. Both must block the action.
AI Systems
Human in the loop meaning: a named person who can fail the work
If nobody can fail the output against written criteria, the loop is decorative.
AI Systems
Human on the loop: watching is not a fail gate
If the work can ship while the watcher is on the gallery, the loop is already the wrong loop.
AI Systems
Introducing Undominated.ai: the independent AI inference price index
Best first. Then price. The board that names every model something else beats without a trade-off.
AI Systems
Literary agent or AI agent: two different jobs
One is a human representative. The other is a worker with a ceiling. They do not replace each other.
AI Systems
LLM integration is an operating-design problem
The scarce work is ownership, permission, and review, not the model name on the invoice.
AI Systems
MCP explained for founders
Care about the permission and the log. The logo on the protocol is the least interesting part.
AI Systems
MCP is not USB-C: where the favourite analogy breaks, and why that matters
The plug is standard. What the model reads through it is not.
AI Systems
MCP meaning: Model Context Protocol, not a product
The full form is the least interesting part. The permission boundary is the operating decision.
AI Systems
MCP OAuth is not tool authorization: a valid token is not a yes
OAuth tells your server the token is genuine and meant for it. Your code decides whether this call may approve this expense.
AI Systems
MCP vs function calling: two layers of the same tool call
In most MCP setups the model still makes a function call. MCP changes where the tool lives, not how the model asks for it.
AI Systems
Model registry vs vendor list: know which models run
A contract can clear a supplier while a production model remains unknown. Compare actual calls with the register before you trust it.
AI Systems
Why multi-agent LLM systems fail: the 14 MAST failure modes
An agent's mistake and the workflow that let it through are two different problems. MAST gives you a vocabulary for both.
AI Systems
Is one AI model enough? When a single model works, and when you need a portfolio
The number of models is the wrong question. The right one: did anyone write down why each model runs, and what happens when it stops?
AI Systems
What an agent may never do
HITL is who can fail the output. The doctrine is what must be refused when no one is watching.
AI Systems
Prove you can stop an agent: interrupt the run and revoke access
An instruction to stop is a request. A stop is a control that someone outside the agent can operate.
AI Systems
RAG freshness: last month's PDF is not a lookup problem
The system can retrieve clause 12.3 perfectly and still miss the signed amendment.
AI Systems
RAG vs fine-tuning vs agents: three jobs, not a ladder
A vector store is not a trained model. A trained model is not a worker. A worker without a ceiling is a demo.
AI Systems
How to retire a production agent (stopping it is not enough)
A stopped agent is not a retired agent. The next schedule, a copied key or a monthly plan can keep it working and billing.
AI Systems
ROSTER vs CHORUS: AI agents for one person, or for a team?
Count the people who can say no to the work. One name means ROSTER. Several names mean you need CHORUS as well.
AI Systems
SENSE: a 90-day strategic intelligence layer
Stop collecting briefings. Start changing Monday.
AI Systems
STACK: version the agent OS like you version the app
Rules in five tools. MCP without contracts. Skills nobody owns. That is not a model problem.
AI Systems
STACK vs AGENTS.md: where instructions end and controls begin
An instruction file is a request. A control is a refusal.
AI Systems
The Agentic Author: Stop Writing Books. Build a Production System.
You are not writing a book. You are building a knowledge-production system that happens to output books. BooksOS makes that system auditable.
AI Systems
The Agentic Codebase: Version the Agent OS Like You Version the App
Prompts in chat are not architecture. Scattered rules are not governance. STACK turns your repository into a maintainable agent operating system.
AI Systems
The Multi-Agent Organization: Close the Coordination Gap With CHORUS
Tools store state. Protocols decide. CHORUS is the operating layer between having agents and running them as one team.
AI Systems
TRACE vs RAG: one fetches the text, the other checks what it proves
An answer can quote the right document and still draw the wrong conclusion.
AI Systems
Using AI agents effectively: one job, a ceiling, a log
A second tool without a ceiling is not leverage. It is a second way to spend.
AI Systems
What is a knowledge graph? Named nodes, typed edges, a walk you can audit
If you cannot name the edge, you have a poster. If you cannot open the node, you have a rumour.
AI Systems
What is a model cascade? Escalate with a stop rule
A cascade without a stop rule is spending until something sounds fluent.
AI Systems
What is a personal health agent? Data architecture, not a clinician
If it answers as a doctor, it is already the wrong worker. If it cannot show the row it used, it is a vibe.
AI Systems
What is agent orchestration? Coordination, not a graph demo
If ownership or review disappears at a boundary, the canvas is not coordinating the work.
AI Systems
What is agent strategy? Selection, sequence, exposure, exit
A well-run agent can still be the wrong worker to deploy first.
AI Systems
What is AI team dynamics? Mixed teams, human accountability
If the founder is the universal exception handler, you do not have dynamics. You have a queue with extra tools.
AI Systems
What is an AI agent? A definition founders can use
If it cannot refuse a tool call, it is not an agent you can run. It is a demo that can spend money.
AI Systems
What is an AI agent charter? Seven fields or it is a demo
If you cannot fill the seven fields, do not hand it a key.
AI Systems
What is an evidence ledger?
The ledger is the product. The reference list is a rendering.
AI Systems
An MCP connector is the plug. Permission is a separate ceiling.
The connector is a plug. The server is the tool. The ceiling is still the product.
AI Systems
What is BooksOS? Seven gates, not a writing CMS
Agents draft. Gates decide. A fluent chapter that cannot survive a fact-check is inventory you will throw away.
AI Systems
What is CHORUS? Coordination, not a choir
Org charts name reporting lines. CHORUS names coordination lines.
AI Systems
What is GRAIN? The inspectable retrieval loop
RAG names the architecture. GRAIN names the honesty check.
AI Systems
What is hybrid search? Two indexes, one inspectable hit
Keywords catch the name. Vectors catch the paraphrase. You still have to open the hit.
AI Systems
What is LLM grounding? The sentence has to open a folder
A real source ID can decorate a false claim. Grounding begins after the citation resolves.
AI Systems
What is model routing? A policy, not a default
If you cannot name which model owns which job, you do not have a routing policy. You have a default.
AI Systems
What is RAG? When AI looks up a source before it answers
A fluent AI answer can still be unsourced. RAG is the method that has to show the page it used.
AI Systems
What is ReasonKit? Structured decisions through MCP
An AI assistant can sound certain. ReasonKit makes it show which claims were checked, and stop when the evidence is missing.
AI Systems
What is ROSTER? How one person manages a team of AI agents
A role is defined by what it may not do. Six written decisions turn an AI agent into a specialist you can grade, fix or retire.
AI Systems
What is SENSE? Five moves, not another unread summary
A digest proves that a system can produce text. SENSE asks where that text changes the work.
AI Systems
What is STACK? Five layers, not a vendor diagram
The agent OS should be versioned like the app. If the rules live in five tools, you have debt, not a model problem.
AI Systems
What is TRACE? Five steps to check research before you act on it
Three links can be one source. TRACE is how you find out before the decision does.
AI Systems
When not to use an AI agent: five signs, and what to use instead
An agent earns its cost only when the next step depends on what it finds. Most tasks never get there.
AI Systems
When to use RAG: named passages, not a vector store
The furniture is optional. The named passage is not. If you cannot open the file, you did not ship retrieval.
AI Systems
Why multi-agent systems fail: the coordination gap
Capability arrived in an afternoon. The protocol never did. That gap is the whole story.
AI Systems
Why your RAG answer is wrong: find the broken step before you change the model
The model is the last thing to blame, not the first.