I'm writing account research into HubSpot from a Claude workflow. The agent uses Coresignal's MCP to pull company and employee context, then produces a brief and a priority score.

The brief gets regenerated when new information comes in. Historical headcount trends are part of the analysis, so sometimes the score changes even when the latest headcount hasn't moved much. The longer-term picture has changed, or the model has enough new context to reassess the account.

Right now, the latest output replaces the previous one. I'd like to retain the old score, the new score, and a short explanation of what caused the change.

One option is to store a JSON snapshot for each run in a separate table and keep only the current version in HubSpot. Another is to write a small change log to a custom object.

If you've done this, which approach turned out to be less painful to maintain? I'm trying to avoid building a whole audit service for something fairly simple.

For a long time, we had one lead score. It mixed engagement with fit, which sounded reasonable until we actually looked at the leads it was ranking.

Someone from a company that would never buy could score highly because they were reading everything we published. At the same time, someone from an ideal account could visit once, book a call, and end up with a surprisingly low score.

The problem wasn't the formula. We were trying to make one number answer two different questions.

So we split it.

One score tracks engagement in HubSpot. The other looks at fit: firmographics, plus whether the company is actively hiring for the function we sell to. We use Coresignal for that part, mainly because the hiring data needs to be fresh enough to use as a signal.

A low-engagement, high-fit lead now goes into a different workflow from a high-engagement, low-fit one. Before, both could land in the same middle of the score range.

The annoying part was getting everyone to accept two scores. Sales wanted one number they could sort by. Fair enough, but the second score explained why some of the leads at the top weren't actually worth pursuing.

How are others handling this? One combined score, or separate scores for fit and engagement?