Explore a candidate level for your workflow

JavaScript is off (or still loading), so here is the whole worksheet at once: every question, what each answer points to, and all eight possible results below it. With JavaScript on, this becomes one question at a time with a result built from your actual answers.

1. Can the job be done by a fixed rule, a search, or a plain form, with no model involved at all?

   Consider fixed logic only if the complete workflow meets your automation and hands-on effort requirements. Technical feasibility alone does not establish the best fit.

   • Yes. A rule, a lookup table, a search, or a plain form covers every case. — settles at Level 00 · Conventional software.
   • No. It needs to understand or produce language, or use judgment a rule cannot capture. — not enough on its own: continue to Does one request, written well, with everything the model needs already in it, reliably get a good answer?

2. Does one request, written well, with everything the model needs already in it, reliably get a good answer?

   This covers rewriting, drafting, or answering a question when all the facts are already in your message.

   • Yes. One clear message, sent once, does it. — settles at Level 01 · Direct prompting.
   • No. It needs information the model was not given: documents, current data, or something specific to us. — not enough on its own: continue to Does finding the right information and putting it in front of the model answer this, where one search or one set of documents is enough?

3. Does finding the right information and putting it in front of the model answer this, where one search or one set of documents is enough?

   This covers answering from a manual, a knowledge base, or a set of notes, where a single lookup finds what is needed.

   • Yes. Hand it the right document or search result and it answers well. — settles at Level 02 · Added context.
   • No. It takes more than one step, or the steps have to happen in a set order. — not enough on its own: continue to Can you define the steps and allowed branches in advance, including how model outputs choose among those branches?

4. Can you define the steps and allowed branches in advance, including how model outputs choose among those branches?

   This covers sorting inputs into categories, chaining prompts, and checking drafts. A model can select a predefined branch; software owns the available paths and stopping rules.

   • Yes. Software defines the steps and branches, even if a model helps choose a branch. — settles at Level 03 · Workflows.
   • No. It has to act on the world while it works: look something up live, run code, or operate something. — not enough on its own: continue to Can the model do this by picking one bounded action (calling a function, running a lookup, clicking one thing), with your code carrying out that action and stopping there?

5. Can the model do this by picking one bounded action (calling a function, running a lookup, clicking one thing), with your code carrying out that action and stopping there?

   The model chooses which action to take and with what details, but only one action, and your code performs it and hands back the result.

   • Yes. One action; your code runs it and the task is done. — settles at Level 04 · Tool use.
   • No. What happens next depends on what the last action returned, and the model has to decide that for itself, more than once. — not enough on its own: continue to Can the steps NOT be known in advance, so the model has to plan, act, look at the result, and decide for itself what to do next and when it is finished?

6. Can the steps NOT be known in advance, so the model has to plan, act, look at the result, and decide for itself what to do next and when it is finished?

   This is the difference between following a plan you wrote and working one out as it goes, the way debugging or open-ended research does.

   • Yes. It plans, acts, checks its own result, and decides for itself when it is done. — settles at Level 05 · Agent loops.
   • No. Even one model working alone in a loop is not enough for this. — not enough on its own: continue to Does the work need to be split across more than one agent or checked independently, or does it have to start on its own or keep running for a long time?

7. Does the work need to be split across more than one agent or checked independently, or does it have to start on its own or keep running for a long time?

   Pick the closest answer. "Independent" means an agent with its own access, not a second pass by the same one.

   • It is too big for one agent to hold, or the subtasks cannot be known until the work is split among several agents. — settles at Level 06 · Teams of Agents.
   • It needs a second, independent agent to check the work, with its own access: one agent checking itself shares its own blind spots. — settles at Level 06 · Teams of Agents.
   • It has to start without being asked, run on its own schedule, or keep going for days or longer. — settles at Level 07 · Always-on agents.

8. If the model gets this wrong, what does that cost?

   Does not change the level. Answered after the level is settled, and only changes the cautions shown with the result.

   • Not much. Someone notices quickly and it is easy to fix.
   • Real rework, a bad customer moment, or a delay before someone catches it. — A wrong answer here costs real time or trust. Check the work before it goes out, and keep a record of what was decided and why.
   • Money, legal exposure, safety, or something that cannot be undone. — A wrong answer here is expensive or dangerous. Keep a person in the loop before anything ships, and be able to say why the model was trusted with it.

9. How easily can someone check the result before it is used?

   Does not change the level. Answered after the level is settled, and only changes the cautions shown with the result.

   • Easily and fast: a glance, or a simple test, confirms it.
   • It takes real effort: reading closely, or running it, to know if it is right. — Build the check into the process instead of relying on a read-through. A standing eval set catches drift a one-off spot check misses.
   • It is hard or impossible to check: there is no ground truth, or checking takes as long as doing the job. — When nobody can easily confirm the result, treat it as unverified until proven otherwise, and keep a person responsible for what happens with it.

10. If the action turns out to be wrong, can it be undone?

    Does not change the level. Answered after the level is settled, and only changes the cautions shown with the result.

    • Yes, easily: nothing has shipped, been spent, or changed yet.
    • With some effort: it can be corrected, but it takes real work. — Log every action taken so a wrong one can be traced and reversed without guessing what happened.
    • No: money moved, a message went out, or something was deleted. — An action that cannot be undone needs approval before it happens, not review after the fact.

11. Does private or sensitive data leave your own machine to do this?

    Does not change the level. Answered after the level is settled, and only changes the cautions shown with the result.

    • No: everything runs on infrastructure you control.
    • Yes: a cloud model or a third-party service sees it. — Know what leaves the machine and who can see it. Check the provider's data-handling terms before sending anything sensitive.