Summarize automation requests for prioritization for Operations teams | Copy-Paste AI Recipe

Name: Summarize automation requests for prioritization for Operations teams
Prep time: 37 min
Ingredients: HubSpot AI system; Postgres AI system

NextFlows Contributors

doi:nextflows.ai/recipes/summarize-automation-requests-for-prioritization

⚡ TL;DR

✓ Reduce dropped requests by converting messages and notes into clear tasks, priorities, and accountable owners
✓ 37 minutes to first success
✓ Approval required
✓ Uses HubSpot MCP, Postgres MCP

Before you start

0/4

Claude Desktop installedHubSpot MCP access configuredPostgres MCP access configuredPermission for HubSpot read access, Postgres read access, Write permission for approved automation actions

Setup (37 min)

0/6

1Connect HubSpot MCP in your MCP client and confirm the server shows as available.

2Connect Postgres MCP so the assistant can combine context.

3Grant the minimum read scopes needed for this reporting workflow.

4Open the workspace, channel, repository, database, or account you want the assistant to use.

5Paste the prompt from this recipe into your AI client.

6Review the result, confirm source links, and copy the approved output into your working document.

The prompt

You are helping a Operations teammate with this workflow: Summarize automation requests for prioritization.
Use the connected HubSpot MCP, Postgres MCP tools to gather only the information needed for reporting.
Create a concise result with: summary, important details, recommended next actions, owners, and links to sources.
Flag anything uncertain, stale, sensitive, or missing instead of guessing.
Before taking any write action, show me the exact change and wait for my approval.

Paste into Claude Desktop. It will use your connected AI servers: HubSpot MCP, Postgres MCP.

Expected outcome

Reduce dropped requests by converting messages and notes into clear tasks, priorities, and accountable owners

Success checklist

0/4

The output explains the reporting context in plain English.Every recommendation includes a source, owner, or next action.Sensitive data is summarized only at the level needed for the task.Operations teammates can use the result without asking for extra background.

Troubleshooting

MCP server is not available in the client

Cause

The server config was not saved, the client was not restarted, or Node.js cannot run npx.

Solution

Run HubSpot MCP manually with its install command, then restart your MCP client.

The assistant cannot find the expected records

Cause

The connected account lacks access to the workspace, channel, repo, database, or page.

Solution

Grant the missing read scope and test with one known record before running the full recipe.

The result is too broad or includes stale context

Cause

The prompt did not limit the date range, source, account, or project clearly enough.

Solution

Add the relevant team, date range, channel, repo, account, or page name to the prompt.