Refine

Refine is how you iterate on a Research, Strategy, or Media Plan output by sending feedback in plain English. You write what should change, an AI reads your notes against the existing output, and only the agents that need to change actually re-run. The rest of the agents are cloned forward unchanged into a new version, so every tab still has content and the prior version stays intact.

Refine vs rerun

Both produce a new run on the same phase, and both leave the prior version in version history. The difference is what they take as a starting point.

• Refine: improve this with my notes. The prior version carries forward and your feedback is applied on top. Reach for this when most of the output is good and only specific parts need to change.
• Rerun: try again from scratch. The prior version's content is discarded as a starting point and the phase runs fresh against the same upstream inputs. Reach for this when the output missed the mark wholesale.

Where it works

Refine is available on Research, Strategy, and Media Plan.

Research has 5 analyst agents (Category, Competitor, Consumer, Culture, Social) that run in parallel. Strategy has 4 strategists (Goals, Audience, Communication, Media) that run in sequence, so each downstream strategist sees the upstream refined outputs as it goes.

Media Plan refine re-runs the planning agents against your feedback and lands a new version of the whole plan. It covers what those agents own: audiences, benchmarks, channel mix, budget split across channels, flighting, and tactics. Refine will accept a request to change the total budget, the target geographies, or the campaign objective, but the plan is then working against a brief that says otherwise. For changes on that scale, update the campaign and generate a new Media Plan.

Brand Profile does not have a refine affordance. To change it, regenerate it.

How it works

On the Research detail page, the Strategy detail page, or the Media Plan page, open the Refine button. A draggable panel slides in with a field for your feedback. Type what should change. The field accepts up to 2000 characters and a counter on the panel tracks how much you have used.

Submit. The panel stays open with a loading state until the run is dispatched, then closes. The page transitions into a running state. On Research and Strategy, each agent's updated output replaces the previous one inline as it finishes. On the Media Plan, the page shows a REFINING YOUR MEDIA PLAN card with a time estimate and a Cancel button, and the revised plan lands as one whole new version when the run completes.

On Research and Strategy, look at the tab labels when the run completes. A small dot next to a tab means that agent was actually refined in the new version. Tabs without the dot were cloned forward unchanged from the prior version. The dot tells you at a glance which parts of the output the AI decided to update. The Media Plan is one unified output rather than a set of per-agent tabs, so it has no dots. Open the prior version from version history instead.

A refine usually takes 1-2 minutes on Research, 2-3 minutes on Strategy, and 3-5 minutes on a Media Plan. These are typical ranges from production runs, not guarantees.

What gets saved

Every refine produces a new run on the phase, and the previous version stays available in version history on the same page. You can open any earlier version in read-only mode and restore it. Restoring produces its own new run that captures the restore event, so you do not overwrite history when you go back.

If your feedback is general enough that no agent needs to re-run, the refine still completes successfully. Every agent is cloned to the new version and the metadata shows a no-changes state. Nothing breaks. The new version is identical in content to the previous one.

Lineage between a refine and the run it came from is recorded in the run model. See Core concepts for how runs and versions are tracked across the platform.

Limits

• One refine at a time per phase. The Refine button is unavailable while the phase is already running.
• Different phases of the same campaign can refine in parallel. Research and Strategy are independent surfaces, so a Research refine and a Strategy refine can run at the same time.
• Up to 2000 characters of feedback per submission.