[ AI ]

Create AI research columns

Add AI columns that summarize, classify, or extract research from existing row data and web-agent outputs.

Use this playbook

Overview

Add AI columns that summarize, classify, or extract research from existing row data and web-agent outputs. This workflow is useful when you want structured notes that live beside the source rows instead of in a separate doc. Cockpit keeps the source fields and AI output together so the team can review and reuse the results.

Add AI columns that summarize, classify, or extract research from existing row data and web-agent outputs.

How it works

1

Import or select rows

Start with imported or enriched account rows

2

Generate structured AI research fields

AI Research Fields

3

Review and filter results

Approved rows ready

4

Export or hand off rows

Clean dataset prepared

Step-by-step process

  1. 1

    Start with spreadsheet rows

    Start with imported or enriched account rows. Keep the original input columns visible so the team can check where each result came from and which source data the AI should read.

  2. 2

    Generate structured AI research fields

    Add AI columns for the research fields you need, then use mentions to reference the right source columns. Cockpit writes the research fields back into the sheet as separate, reviewable columns.

  3. 3

    Review the output

    Filter by status, confidence, missing values, fit, or approval state before moving the data downstream. This is where you catch vague answers and tighten the prompt if needed.

  4. 4

    Prepare the handoff

    Keep only the useful fields, then use CSV export or another destination that matches the next workflow. The output should read like a structured research sheet, not a block of raw notes.

Key outputs

AI Research Fields

AI

The main output of this workflow. It gives each row structured AI research fields that can be reviewed, filtered, and exported.

  • Research summary
  • ICP fit
  • Suggested angle

Review Status

Workflow

A simple status field for deciding whether the row is ready, needs review, or should be skipped.

  • Ready
  • Needs review
  • Skip

AI research columns work best when each row has a clear job

AI columns are easiest to use when they are not trying to do too much at once. Instead of asking one prompt to produce a giant summary, this workflow breaks research into smaller row-level fields. That makes the output easier to review, easier to trust, and easier to reuse later.

The setup matters because the quality of the result depends on what the model can see. If you attach the right source columns, the AI can work from company context, contact context, or earlier research without guessing. The sheet stays readable because each answer lands in its own column rather than replacing the row with one long paragraph.

  • Use separate columns for separate questions.
  • Attach source data that supports the answer directly.
  • Review vague or inconsistent outputs before exporting.

This workflow is especially useful for sales and research teams that need consistent notes across many rows. Common outputs include ICP fit, summary notes, buying committee clues, objection risk, or a suggested next action. Because the answers live in the spreadsheet, you can sort, filter, and compare them without rebuilding the research each time.

AI columnTypical use
ICP fitQuickly scores whether the row looks relevant.
Buying committee noteCaptures who matters and why.
Objection riskSurfaces likely pushback before outreach.
Suggested actionHelps decide whether to enrich, email, sequence, or skip.

When the research columns are working well, the spreadsheet becomes a shared operating view. Everyone can see the inputs, the AI output, and the review state in one place, which makes the process easier to repeat for the next account list.

To get started

  • Start with imported or enriched account rows
  • Add AI columns for the research fields you need
  • Use mentions to reference the right source columns

When to use this

  • Research needs to be standardized across rows
  • You want AI output in separate reviewable fields
  • Sales or ops needs consistent qualification notes

Integrations

AI columns
AI web-agent columns
Company enrichment
CSV export

What you can swap

This playbook follows the workflow shown in the video, but the exact source, enrichment, prompt, and handoff can be changed to match your team.

  • Input source
  • Column configuration
  • Provider or AI prompt
  • Export destination

Common questions

Can I run this on an existing spreadsheet?

Yes. Import or open existing rows, add the relevant Cockpit columns, then run the workflow on selected rows or the full sheet.

Can I review results before exporting?

Yes. Results stay visible in the spreadsheet so you can filter, edit, rerun, or approve rows before handoff.

Can I reuse the workflow later?

Yes. Treat the columns and prompts as a repeatable playbook for the next list, campaign, or account segment.

More AI playbooks