Workshop

AI-powered data enrichment and analytics.

Workshop was built for two simple jobs: generate richer audience data to expand what teams can analyze, then turn the results into clean, structured intelligence for humans and AI systems alike.

Request a Demo

Workbook

Base query

Joins

Composites

Models

Q5 scoring model

Model file Audience propensity score

Summary Recipe Script

Predictive score for Q5

Estimates the likelihood that an audience member belongs in the target response group, using matched survey and consumer variables.

Training data

Matched survey rows and consumer variables.

3.7k

Outcome

Binary response class from Q5.

Ready

Validation

Best fold mean squared error.

0.076

Top predictors

10.18

20.14

30.11

Status Trained / Review Fold 3

Dora

Can we turn the new consumer variables into a Q5 audience propensity model?

Yes. I matched them to 3.7k survey rows, held out validation, and ranked the strongest predictors.

Audience propensity model is trained.

Output field: audience_propensity_q5. The recipe, MSE notes, and staged score are written to the workbook dossier.

Review model dossier

Audience intelligence that compounds with every question.

A workbook gives your team and AI systems a shared audience record. First, enrich the data layer. Then, turn that context into analysis people can inspect and agents can reuse.

01Data Enrichment Increase the surface area for intelligence. Bring more context into the workbook, then turn it into connected data, derived fields, and modeled fields that every analysis can reuse.

Enrichment categories

Workbook 1278 Audience build sequence

Workbook Project

Source Data

Full Dataset 121 / 1.8k

Market Survey 45 / 1.8k

Consumer Data 61 / 1.8k

Computed Fields 15 / 1.8k

Snapshots

Persuadables 121 / 480

Female 18-34 121 / 311

Joined Consumer Data

Dataset Tabulations Agent Dossier

Variable profiles Value profiles

Household Composition Family structure appended from consumer data.

SingleFamilyMulti

Children in Household Count of children in the home.

0123+

Veteran in Household Flag used for audience segmentation.

YesNo

Home Ownership Owner/renter field for household models.

OwnRent

Estimated Income Band Modeled household income range.

<50k50-100k100k+

Purchase Category Category affinity from acquired behavior.

HomeAutoRetail

Length of Residence Tenure field used in response models.

0-2y3-7y8+y

Respondent ID HH composition Children Income band Score

R-10482 Family 2 100-150k 0.74

R-10917 Single 0 50-75k 0.58

R-11306 Multi-gen 1 75-100k 0.81

R-11844 Couple 0 150k+ 0.66

R-12039 Family 3+ 75-100k 0.72

R-12671 Single 0 <50k 0.49

R-13128 Family 1 100-150k 0.69

R-13652 Couple 0 50-75k 0.52

R-14086 Family 2 150k+ 0.79

Join query Scrolled to fields 55-61 of 61

-- 54 selected fields above
  consumer.home_ownership_status,
  consumer.length_of_residence,
  consumer.household_composition,
  consumer.children_in_household,
  consumer.veteran_in_household,
  consumer.income_band,
  consumer.consumer_match_score
FROM market_survey AS survey
LEFT JOIN consumer_database AS consumer
  ON survey.respondent_unique_id = consumer.respondent_unique_id;

Search 121 vars

Dora

Children CHILDREN_IN_HH

Veteran VETERAN_HH

Income INCOME_BAND

Residence LENGTH_RESIDENCE

☝️ I found 61 consumer fields that can add context to your survey and support modeling downstream. Would you like me to join this data to your survey?

go ahead. JG

Done. Added 61 consumer fields, computed 15 modeling fields, and saved two audience snapshots.

The truth is in here... ↑

Workbook Project

Source Data

Full Dataset 121 / 1.8k

Market Survey 45 / 1.8k

Consumer Data 61 / 1.8k

Computed Fields 7 / 1.8k

Snapshots

Persuadables 121 / 480

Female 18-34 121 / 311

Computed Fields

Dataset Tabulations Agent Dossier

Variable profiles Value profiles

Persuadable Audience Likely movable based on issue priority, candidate openness, and confidence gap.

CoreLeanMoveable

High-Information Persuadable Persuadable respondents with enough stated context to support message testing.

HighMediumLow

Q5 Top 2 Box Composite flag for respondents who strongly agree or agree on Q5.

Top 2Other

Q5 Bottom 2 Box Composite flag for respondents who disagree or strongly disagree on Q5.

Bottom 2Other

Young Family Segment Age and household composition composite for younger households with children.

InOut

Suburban Owner Segment Geography and home ownership composite for suburban homeowners.

InOut

Senior Fixed-Income Segment Age and income composite for older respondents in fixed-income bands.

InOut

Search 7 vars

Dora

Dora, create a persuadable audience using the questions that show openness, concern, and room to move. Do not make it a single-question cut. JG

I can build that from multiple signals instead of one response.

Audience rule Combine Q5 agreement, candidate openness, issue priority, confidence gap, and turnout likelihood.

Guardrails Exclude fixed opponents and low-information cells where the read is too thin.

Good. Also create a stricter version for message testing. JG

Done. I created two persuadable audience fields and five supporting composites.

Ready for review persuadable_audience and high_information_persuadable are staged in computed fields.

Dossier context The rule logic, source questions, and caveats are ready to write into the agent dossier.

The truth is in here... ↑

Workbook Project

Trained Models

Q5 Propensity 0.076

Persuadable Likelihood 0.081

High-Intent Likelihood 0.092

Response Lift Model 0.104

Activation Readiness 0.118

Segment Expansion draft

Q5 Propensity Model

0.076 Good best MSE

Q5 propensity model

Ranks audience members by likelihood of landing in the Q5 target group. MSE measures prediction error, so lower is better; this run is good for a 0-1 target, with one fold flagged for review.

Trained Review fold 3 Score field: audience_propensity_q5

How to read it Two folds are good; one fold needs inspection.

0.081 fold 10.076 best0.149 review

Model build Trained on a locked audience snapshot.

Training rows3.7k OutcomeQ5 class Avg. error~0.28

Predictors Strongest predictors remain inspectable.

Engagement0.18

Household0.14

Consumer0.11

Deployment path The model becomes a reusable audience variable.

Workbook score fieldready

Model dossier + recipeupdated

Gateway packageafter review

Dora

Dora, use the Persuadables snapshot to build a Q5 propensity model we can understand and deploy. JG

I can do that. I’ll train against the Q5 target class, compare MSE across folds, and keep the deployment path visible.

Run it. JG

Done. The best fold is in a good range, but one validation fold is higher and should be reviewed before activation.

Score field created audience_propensity_q5 has been written back to the workbook.

Deployment staged The score and model dossier are ready; Gateway deployment waits on fold review.

The truth is in here... ↑

02Data Analytics Generate Intelligence for Humans and Agents. Turn workbook data into weighted tabulations, readable findings, and structured dossier artifacts that people can inspect and agents can reuse downstream.

Intelligence mode

Workbook Project

Source Data

Full Dataset 121 / 1.8k

Market Survey 45 / 1.8k

Consumer Data 61 / 1.8k

Computed Fields 15 / 1.8k

Snapshots

Persuadables 121 / 480

Female 18-34 121 / 311

Persuadables

Dataset

Not at all 15% (72)

Not very 25% (118)

Somewhat 36% (176)

Very likely 24% (114)

Yes 63% (302)

No 37% (178)

Strongly agree 20% (96)

Agree 35% (168)

Disagree 30% (142)

Strongly disagree 15% (74)

Low 21% (101)

Medium 39% (187)

High 40% (192)

Strongly agree 17% (82)

Agree 33% (158)

Disagree 30% (144)

Strongly disagree 20% (96)

Total 480

Gender

Male 235

Female 245

Age

18-34 160

35-54 170

55+ 150

HH Composition

Single 150

Family 230

Multi-gen 100

Gender nested within age n480

18-34

Female n42

Male n38

35-54

Female n56

Male n51

55+

Female n28

Male low n

Single Family n96

Female n31

Male n29

Dora

Dora, I want to understand gender differences across segments like age and household composition, but I’m worried some cells may be too small for a reliable read. JG

Yes. Some three-way cells will get thin if we keep the raw response scales.

Create composites Convert bipolar questions into Top 2 / Bottom 2 box variables.

Run nested tabs Compare gender inside age and household-composition segments, with low-n cells flagged.

That sounds great. Go ahead. JG

Done. The nested tables and charts are ready for review.

Review output Two-way views are available in the workbook.

Agent dossier updated three-way-tabs.md now includes JSON plus the mechanical readout for future agent access.

The truth is in here... ↑

Workbook Project

Source Data

Full Dataset 121 / 1.8k

Market Survey 45 / 1.8k

Consumer Data 61 / 1.8k

Computed Fields 15 / 1.8k

Snapshots

Persuadables 121 / 480

Female 18-34 121 / 311

Persuadables

Dataset

manifest.md dataset-context.md variables.md one-way-tabs.md two-way-tabs.md three-way-tabs.md

three-way-tabs.md updated

# Three-way tabulations snapshot: Persuadables population_n: 480 weight: market_survey_weight composite: Q5 Top 2 / Bottom 2

## table: gender_nested_within_age outcome_variable: q5_top2_bottom2 nesting: age_group > gender low_n_rule: flag cells below threshold

{
  "table_id": "three_way_q5_age_gender",
  "snapshot": "persuadables",
  "rows": ["18-34", "35-54", "55+"],
  "nested_by": "gender",
  "readout": "female 18-34 indexes highest on top-box response"
}

## mechanical readout Top/bottom box composites were generated before nesting. Small-cell warnings are preserved for agent use.

Dora

Dora, I want to understand gender differences across segments like age and household composition, but I’m worried some cells may be too small for a reliable read. JG

Yes. Some three-way cells will get thin if we keep the raw response scales.

Create composites Convert bipolar questions into Top 2 / Bottom 2 box variables.

Run nested tabs Compare gender inside age and household-composition segments, with low-n cells flagged.

That sounds great. Go ahead. JG

Done. The nested tables and charts are ready for review.

Review output Three-way views are available in the workbook.

Agent dossier updated three-way-tabs.md now includes JSON plus the mechanical readout for future agent access.

The truth is in here... ↑

03Intelligence Gateway Put audience intelligence to work everywhere. Workshop turns the evidence behind your audience into a dossier Gateway can deliver to agents, apps, tools, and workflows. AI starts from your fields, models, and findings instead of a generic public-web answer.

Build intelligence that keeps getting smarter.

Bring sources, models, and questions into Workshop so every analysis becomes reusable knowledge for your team and your AI systems.

Request a Demo