Three types of AI agents, and how to pick one before you build
Most internal AI projects don't fail on the tech. They fail because nobody decided what kind of agent they were building. Some agent jobs start with a specific input. Some start with a question in plain language. Others start when a clock or an event fires. Those differences decide what a useful an
Posted on Oct 29 • Originally published at hubzoid.com
Most internal AI projects don't fail on the tech. They fail because nobody decided what kind of agent they were building.
Some agent jobs start with a specific input. Some start with a question in plain language. Others start when a clock or an event fires. Those differences decide what a useful answer looks like, and what can go wrong.
So choose the shape of the work before you choose the model or the interface.
Trouble starts when a job of one shape is built as another:
The shapes are patterns, not product categories. A chat can ask for an invoice check, and a scheduled job can use an agent to explain exceptions. What matters is that each job gets what its shape needs.
An invoice check says what it expects: an invoice, a purchase order and the current matching rules. It says what it returns: matched lines, mismatches and any missing document.
A paragraph that looks convincing is not a contract. A fixed output format doesn't make every model-generated value deterministic, either.
People ask the same policy question in many forms. A useful Q&A agent finds the current policy, names its source and asks a follow-up when the answer depends on details it doesn't have. A returns question may depend on the purchase date or the account type, and guessing them changes the answer.
Test the refusal too. Ask for a number the agent's sources don't hold, and check that it says what's missing instead of estimating from unrelated data.
When nobody is watching, a duplicate report or a silent failure can go unnoticed for days. Before you schedule anything, answer:
The last one bites hardest. If a run restarts halfway, any step with an external effect needs its own protection against running twice.
Input: what the agent receives, and from whom Output: the exact result, and where it goes Trigger: a person asking, or a schedule or event Failure: what happens when an input is missing or a step fails Enter fullscreen mode Exit fullscreen mode If you can't fill in the trigger, you don't know the shape yet.
This short video shows the three shapes running on one shared set of team knowledge:
The longer version, including how each shape maps to chat, workflows and assistants over MCP in Hubzoid, is on our blog: Three types of AI agents, and when to use each.