Prompt
The instructions and context given to an AI model to produce a response. In persistent, agentic systems, the goal increasingly replaces the single prompt.
A prompt is the input given to a language model: a question, instructions, examples, documents or a mix. The quality of the output depends heavily on it, which is why prompt writing became a skill of its own.
In a real system the prompt is rarely typed by a person. The harness assembles it from instructions, retrieved information, tool results and conversation history, so the effective prompt can be much longer and more varied than anything a user writes.
Beyond the prompt
Most AI use so far is a tool we operate: write a prompt, read the output. Persistent delegation changes that. The user delegates a goal and the agent keeps working without waiting for the next prompt. That shifts the important design questions from how to phrase a request to what the agent remembers, which actions it is allowed to take and how it reports back.
Prompting also adds to supervision load: time spent prompting, supplying context and correcting is human attention that automation metrics often miss. See LLM.
Read more in OpenAI Dots is a test of whether AI can carry a goal, not just complete a task.
Related terms
LLM
Large language model: an AI model trained on very large amounts of text to predict and generate language, which can be used to answer, summarise, write, reason about and act on text.
Persistent delegation
Handing an AI agent a goal it keeps carrying over time — remembering context, noticing relevant events and acting across applications — rather than completing a single prompted task.
Harness
The software around a model that manages context, tool use, sub-agents and the execution environment. It shapes real-world capability, so it must be evaluated with the model, not ignored.
Used in these essays
How to build an AI strategy: decisions, not a tool list
An AI strategy is a set of decisions about workflows, ownership, evidence and stopping, and this guide walks through them in the order I would take them.
AI agent governance: what executives must decide first
AI agent governance is a short list of leadership decisions about authority, ownership, evidence and supervision that have to be made before an agent acts.
The question your board should ask about AI is not “what are we doing?”
A list of AI projects tells a board what management chose to launch. It does not show where AI already shapes decisions nobody approved.
AI is making intelligence cheap. Judgment is not getting cheaper.
Better and more accessible AI answers do not settle which questions matter, which evidence counts, or who owns a decision.
Who should have the first idea? Human planning in AI-assisted creativity
Putting a human at the end of an AI creative workflow is not the same as letting them shape its possibilities.
Your Synthetic Customer Cannot Tell You What You Forgot to Ask
Synthetic customers can test assumptions, but they cannot reveal what your research never asked.
The safest answer your AI team can give you may be “we should not automate this”
The responsible AI decision is not always a deployment. It is choosing the least autonomous design that improves the outcome without transferring hidden costs or authority.
AI agents are exposing your org chart as fiction
An org chart tells you who manages whom. An agent can reveal who actually authorizes a decision, rescues an exception, and carries the consequences.
How to tell if an AI pilot deserves to survive
A pilot earns another investment only when its result can survive ordinary work, a credible alternative, and an owner who can carry it without the pilot team.
Most AI strategies are software procurement plans with better typography
A vendor shortlist can specify what a company will buy. It cannot decide which work the company will stop, which decisions will change, or who will own the consequences.
Five AI metrics I would remove from an executive dashboard
Licenses, prompts, pilots, hours saved and benchmark scores can all rise while the business stands still. The executive dashboard needs a different contract.
Your AI program can be efficient and still be strategically irrelevant
AI can make low-value work dramatically cheaper. That is still low-value work. The portfolio question is not only what became faster, but whether the work deserved investment in the first place.
Your AI agent estate is becoming a capital allocation problem
Once agents multiply across workflows, the management problem changes: which agents deserve more capacity, which should be merged or constrained, and which should be retired?
An AI agent should get authority per task, not permissions per role
A person's role describes standing access across many situations. An AI agent should receive a narrower authority envelope for the task it is executing now.
Design systems need an interaction policy layer for AI
Components can keep an AI experience visually on-system while the agent is behaviorally off-policy. Design systems now need reusable rules for what AI may present, decide, execute, defer, expose as uncertain, confirm, reverse and escalate.
Your AI agent can follow the objective and still break the company
AI agents can satisfy a local objective while violating the organization’s broader constraints. The control problem is not only model alignment; it is management design.
Stop Adopting AI
AI adoption is rising faster than enterprise value because companies keep installing new intelligence inside old operating models.
OpenAI Decisions API turns probability into policy
The provocative part of OpenAI's Decisions API is not that AI can make choices. It is that a model score can quietly become an action — and an action can quietly become policy.
OpenAI Dots is a test of whether AI can carry a goal, not just complete a task
Dots matters less as another capable assistant than as a test of persistent delegation: can AI keep carrying a goal without giving the user a new system to manage?
Cahit Arf’s 1959 question about thinking machines
In a 1959 text on thinking machines, Cahit Arf moved from clocks and relays to a harder question: what happens when a machine meets a problem that was not anticipated when it was built?
The wrong questions about AI right now
Many of the questions that helped us orient ourselves around generative AI are now too blunt to be useful. The harder work is no longer asking what AI is in the abstract, but specifying where it works, where it fails, what authority it should have, and what the whole system costs.
The first AI incident report should be incomplete
OpenAI's new misalignment disclosure framework exposes a useful enterprise design principle: record anomalous AI behavior before the organization has finished explaining it. Otherwise incident systems quietly become filters for what teams already understand.
The hidden metric in AI automation is supervision
As AI moves from assisting work to leading it, hours saved stop telling the whole story. The scarce resource shifts to human supervision: approvals, exceptions, context and judgment.
The benchmark needs a runtime address
AI systems are increasingly dynamic at runtime. Enterprise evaluation should qualify the serving route, harness, tools and fallback conditions, not just the model name.
The agent is not the operating model
Giving AI more autonomy does not remove organizational complexity. It gives that complexity permission to act.
Your AI data agent is creating a second dataset
AI data agents do more than answer business questions. At scale, the pattern of questions, corrections and dead ends becomes a new signal: a map of what the organization is trying to understand, where its definitions are weak, and which decisions deserve better infrastructure.
Your chatbot is borrowing from the next interaction
AI customer service is usually measured one interaction at a time. But a failed automated interaction can change which channel a customer chooses next time. That makes future adoption part of the economics, not a separate trust metric.