The 'why' behind a metric lives in the open-text of the same people who moved it. Join quant and qual on the stakeholder ID to explain the number, not just report it.
In short: A metric that moved tells you what happened, not why. The 'why' lives in the open-text of the same people the number describes — so join quant and qual on the stakeholder ID, separate improver themes from non-improver themes, and back each with a count and a quote. One prompt does it and grades the result green, amber, or red.
Point the Sopact Sense Assistant at your dataset so it works from clean records with persistent contact IDs, then have it load your Decision Brief first. The persistent ID is what lets you connect a person's score to that same person's words — which is the whole point of mixed-method analysis.
You are the Sopact Sense Assistant working over the DEMO-03 · Workforce Cohort dataset (clean data + persistent contact IDs). Load my Decision Brief (decision, audience, outcomes, indicators, evidence standard) first, then wait for my task.
The workforce cohort's confidence metric moved up. Using open-text from the same IDs, explain: improver vs non-improver themes, quantified + quoted. Grade green/amber/red.
Five elements make this prompt work: it runs over your dataset; it pairs quant + qual on the same IDs so the words belong to the people who moved the number; it surfaces themes split by improver and non-improver; it flags missing open-text where a number has no comment; and it ends with a grade of green, amber, or red.
Run on the Workforce Cohort dataset (DEMO-03) already loaded in Sopact Sense.
GRADE: green | Improver theme | counted + quoted; amber | Non-improver barrier | thin; red | No open-text | can't explain
A green improver theme is named, counted across IDs, and quoted. An amber non-improver barrier exists but is thin — mentioned but not yet quantified. A red ID has a number but no open-text, so its 'why' is simply unknown.
Take the lowest-graded element above and fix it using only what the program could realistically measure. Show the before → after grade and the single indicator/edit that moves it to green.
Create a 'missing & incomplete' report from this analysis in Sopact branding [or paste your website URL / brand guideline to apply your own]. List every element graded amber or red, what is missing, and the one input that fixes each. Lead with the decision this report informs.
Create a shareable link for this report and open it in a new tab.
Split improvers from non-improvers first. Pooling all comments together blurs the signal. The interesting contrast is between what movers say and what non-movers say.
Quantify every theme. 'Several participants mentioned childcare' is an anecdote; '9 of 14 non-improvers named childcare' is a finding. Always reconcile theme counts to the number of people.
Quote in the person's words. A count tells the funder how many; a verbatim quote tells them what it felt like. Pair both per theme.
Treat numbers without open-text as a gap. An ID that moved but left no comment is the most common red — you cannot explain a change you never asked about.
List the IDs that improved but left no open-text, and suggest the single open-text question I should add so next cycle every mover can explain their why.
Join them on a persistent stakeholder ID so each person's score sits next to their own words, then explain the metric by contrasting improver themes against non-improver themes, with a count and a quote for each. Flag any ID that has a number but no open-text.
Because the explanation you need is comparative: what did the people who moved say that the people who did not move did not? Pooling all responses together hides exactly that contrast.
Flag them as a gap rather than guessing their reason. The one-fix prompt will name the single open-text question that, added next cycle, lets every mover explain their why.
Open Sopact Sense, paste your program description, and put it to work.
Try in Sopact
