Topic
Intelligence selection
What should do each part of the job?
Some steps have a known rule. Others need a prediction, evidence from a source, or help interpreting a message. Break the workflow into decisions before choosing the technology.
The notes separate finding evidence from interpreting it and show how to plan a predictive-model comparison. Check mistakes, review load, cost, and fallback on the same cases. The answer can be a mix of ordinary software and AI.
Notes in this topic
Does this need an agent or a fixed workflow?
A workflow can contain a model without handing it the choice of what happens next. Start by writing down which decisions really need that freedom.
Read the noteThe cheaper model can cost more
A lower model bill can leave the team with more checking and repair. Count that work before choosing the model.
Read the noteWhen the job needs a solver
A schedule can read well and still put one person in two places. When the rules are explicit, use code to find and check the possible assignments.
Read the noteDoes the model need to think, or find the evidence?
Before buying a stronger model, check what information it received. The answer may depend on a document search never found.
Read the noteHow to test whether ordinary machine learning is enough
If the job is predicting late shipments from existing records, compare a rule and an ordinary predictive model before asking a language model to reason through every case.
Read the noteWhich revenue definition should the agent use?
Two reports can both say revenue and mean different things. Settle the definition, scope, and unresolved facts before letting an agent answer.
Read the noteWhich parts of this workflow need a model?
A model can read a vague request while code checks the rules. Split those jobs before choosing a technology.
Read the noteDraw the system before choosing an agent
Follow one request through its records, decisions, approval, and confirmation. Then decide where a model belongs.
Read the note