A second supplier for a critical part
A plant manager frames the choice on cost, lead time and quality. The agent lays out three suppliers and "do nothing", recommends one, and the manager makes the call at Recommendation.
Recommendation approval
The ConvOps Decision Memo template makes your AI work a decision through four steps: frame it with explicit criteria, lay out the realistic options even-handedly, write a recommendation tied to those criteria, then record the call. The recommendation stops for you, because the decision is yours. Reject it and the AI reconsiders the options.
4 steps · 1 approval · 1 loop back
example · the steps are this template's real steps
For founders, managers and operators facing build-or-buy, vendor or hiring calls they will need to explain months later.
Decision Memo is stored in ConvOps as four steps, and your AI client receives them one at a time. A Decision Memo run holds at Recommendation until an explicit approval is given.
The 4 Decision Memo steps in order, each with the instruction your AI receives there as Decision Memo stores it.
A recorded decision with its criteria, the options weighed, the recommendation and the call made, with a date and a rationale.
Frame the decision before exploring options.
Capture:
A decision with no stated criteria cannot be evaluated. If criteria are unclear, agree them with the operator before advancing.
Save the framing as a task note with task_notes_add. The next step (Options) reads this note.
Read the task notes with task_notes_list: the note from the Frame step contains the decision, stakes, and criteria. Work from it.
Lay out the realistic options. What good looks like:
Be even-handed: do not stack the deck toward a favorite. If a research report informs this, pull from its findings.
Save the options and their trade-offs as a task note with task_notes_add. The Recommendation step reads this note.
Read the task notes with task_notes_list: the Options note holds the options and trade-offs, and the Frame note holds the criteria. Work from them.
Write the recommendation:
Present this as a recommendation, not a verdict. Save the recommendation as a task note with task_notes_add. Then ask the operator to make the call. This is a checkpoint: the decision is the operator's to make, so the AI cannot advance until you decide. If you reject the recommendation, the workflow returns to Options to reconsider.
rejected → back to Options
Read the task notes with task_notes_list: the Recommendation note holds the recommended option and the operator's decision. Work from it.
Record the final decision. Save a task note with task_notes_add capturing:
This note is the durable record of the decision. Close out the task.
A plant manager frames the choice on cost, lead time and quality. The agent lays out three suppliers and "do nothing", recommends one, and the manager makes the call at Recommendation.
Recommendation approval
Decision Memo holds at Recommendation until an explicit approval is given, recorded with the account that gave it.
The AI recommends; you decide. Approve to record the call, or reject and the workflow returns to Options to reconsider.
what you review
reject → back to Options
gates the engine checks without you
Decision Memo runs in a ConvOps workspace and attaches to the task type, so new work of that type starts on it. Decision Memo saves each step's output as a task note in ConvOps, and the next Decision Memo step reads it back. Decision Memo needs no repository, so a chat client such as ChatGPT or Claude can run it. Connect a client , then install Decision Memo from the catalog .
Once installed, Decision Memo is a workflow in your workspace. Ask your AI to change Decision Memo in plain words; the edit lands on the one step that needs it.
new chat
workflow_step_update · Decision Memomore example prompts
The ConvOps Decision Memo template makes your AI work a decision through four steps: frame it with explicit criteria, lay out the realistic options even-handedly, write a recommendation tied to those criteria, then record the call. The recommendation stops for you, because the decision is yours. Reject it and the AI reconsiders the options.
The ConvOps Record step saves a task note with the decision made, the date and who made the call, the rationale (the criteria it satisfied and the trade-off accepted), and the options not chosen, briefly. That note is the durable record of the decision, so anyone asking later why a call was made can read the reasoning instead of reconstructing it.
Yes, where relevant. The ConvOps Options step names each genuine option including "do nothing", scores each against the criteria agreed at Frame, and sets out the trade-offs, the risks and how reversible each path is. Your AI is told to be even-handed and not to stack the deck toward a favorite, and to record any evidence behind the assessment.
Yes. In ConvOps, the Research Report template's final task note is its named input for a Decision Memo, and the Options step pulls from a research report's findings when one exists. Both templates ship in the Chat Essentials kit, so the research and the decision it informs follow one process and stay on one record.
The ConvOps Recommendation step presents the recommended option as a recommendation, not a verdict, with the rationale tied to the criteria, what you trade away by choosing it, and when another option would be better. The run then holds until an explicit approval is given, recorded with the account that gave it. Reject the recommendation and the run returns to Options.