MODULE 1.1
Models: choose by task
Compare models with a real task and a quality criterion.
What it is
A model generates responses; a system organizes how those responses become work. OSWork combines model, interface, files, instructions, tools, memory, and automations. Think of a small workshop: the professional’s skill matters, but tools, materials, and quality criteria also determine the outcome. We are not installing a new computer operating system: we use that expression as a metaphor for organization.
Why learn
Without this distinction, every failure turns into an attempt to write a larger prompt. Sometimes only the input file, a permission, or the way to verify the output is missing. Separating the pieces allows you to fix the right point.
Key concepts
Model reasons; interface receives the goal; files provide evidence; tools execute; you verify.
What it is
In the documentation consulted on 20/09/2026, the GPT-5.6 family includes Sol, Terra, and Luna. Sol offers the highest capacity in this family; Terra balances everyday work and cost; Luna favors clear and repeatable tasks. GPT-6 Astra appears as an option for complex work. Availability varies by account, client, authentication, and release.
Why learn
A model’s name does not guarantee it appears in your account. Choosing based on what is available avoids turning the lesson into a promise of access. No model eliminates the need to verify results.
Key concepts
Model family; capacity; speed; cost; availability.
What it is
The model is the chosen mechanism. Reasoning effort is a setting of that mechanism. Higher levels may consume more time and tokens, units of text processing. The selector names change between Chat, Work, and Codex; there is no single list of Instant, Medium, High, and Pro that represents all products.
Why learn
Requesting the maximum on every task can increase consumption without improving the result. Increasing effort also does not provide a missing document. First complete the inputs, then assess whether the problem requires more analysis.
Key concepts
Model and effort are different axes; start with the default; compare under equal conditions.
What it is
A rubric turns opinion into observation. Define before the request which facts must appear, which errors are unacceptable, and how the output will be used. Use three small criteria: fidelity to the data, combined format, and verifiability of the conclusions.
Why learn
Without criteria, you choose the prettiest answer. A report can sound convincing and alter values. The test should reflect the work you need to deliver, not a demonstration made to impress.
Key concepts
Acceptance; evidence; representative sample; controlled comparison.
What it is
Login with ChatGPT uses the rights and limits associated with the account and workspace. An API key uses consumption‑based billing on the platform. Subscribing to ChatGPT does not mean you receive free credit for any program that calls the API. Check the active method before a long execution.
Why learn
This precaution avoids discovering later that an experiment is consuming a different account. Usage limits, model access, and data rules can change; the source of truth is the current configuration of your account.
Key concepts
Subscription; authentication; API; consumption; spending limit.
What it is
Autonomy is an authorization with scope, not an invitation to do anything. Combine objective, permitted files, authorized actions, time limit, and stop condition. The output must include what was done and how it was verified.
Why learn
An agent can execute more steps than a chat, including making multiple mistakes. A simple limit protects time, budget, and files without preventing useful work. Technical permission and written instruction complement each other.
Key concepts
Scope; approval of external actions; execution ceiling; reviewable result.