workflow templates: Universal workflows.

Workflows that fit any kind of work, from a quick task to a multi-phase plan. The AI drives the same structured process every time, so outcomes stay consistent across teams and tools.

← all templates

universal

GoalDrive strategic objectives from definition to completion. The AI drives through Capture, Active tracking, and Review.4 steps · 4 gates

universal

PhaseExecute an implementation phase from ready to verified. The AI drives through Ready, Implement, and Verify.4 steps · 2 gates

universal

TaskTake any work item from intake to verified completion. The AI drives through Intake, Analyze, Implement, and Verify.6 steps · 3 gates

universal

PlanTurn strategic work into reviewed, executable plans. The AI drives through Analyze, Draft, phases, and execution.10 steps · 5 gates

universal

Research ReportAnswer a research question with a sourced report. The AI drives Scope, Gather, Synthesize, and a review checkpoint.6 steps · 3 gates

universal

Decision MemoMake a decision you can defend later. The AI drives Options and a recommendation checkpoint, then records the call.4 steps · 2 gates

Universal templates fit any kind of work: a single task, a goal, a plan split into phases, a decision memo or a research report.

They are the building blocks most workspaces start with. Your AI runs the same structured steps every time, and every step is saved, so any session can pick a run up where it stopped.

Questions

How do I install one of these templates?

Open the template, then install it into your workspace in the ConvOps app. Once installed, your AI runs it from any connected MCP client: Claude Code, Cursor, ChatGPT and others.

Can I change a template after installing it?

Yes. An installed template is a workflow in your workspace. Ask your AI client to change it in conversation, for example to add a review step or an approval gate. Edits are made to the one step that needs them.

Does a template run the AI for me?

It can. Work locally and your own AI client walks the workflow one step at a time. Or run it unattended: an executor starts the agent on ConvOps Cloud, on your own runners, or self-hosted. Either way the model is yours, and the engine checks each gate before the run moves on.