A single-metric check-in misses the person. Here is how to synthesise a whole-person status across every life domain — at-risk, stabilising, or thriving, with evidence and a date — using Sopact Sense.
In short: A single-metric check-in misses the person. Point the Sopact Sense Assistant at the full record and synthesise a status across every life domain — at-risk, stabilising, or thriving — each backed by evidence and a date, with the most pressing need named. You get a whole-person read that tells you where to focus and which evidence is too stale to trust.
Tell the Assistant which dataset it is working over and load your Decision Brief first, so the status read ties back to the decision, audience, outcomes, indicators, and evidence standard you already set.
You are the Sopact Sense Assistant working over the DEMO-08 · Caseload dataset (clean data + persistent contact IDs). Load my Decision Brief (decision, audience, outcomes, indicators, evidence standard) first, then wait for my task.
For client [ID], synthesise status across [LIFE_DOMAINS]: at-risk/stabilising/thriving with evidence + date; name most pressing need. Grade green/amber/red.
The prompt carries five elements. Dataset: the client's full record. Status per domain: at-risk, stabilising, or thriving for each life domain. Evidence plus date: every status backed by a quote and when it was recorded. Most pressing need: the one thing to act on first. Grade: a green / amber / red call per domain.
Run on the Caseload dataset (DEMO-08) already loaded in Sopact Sense.
GRADE: green | Thriving | domain · amber | At-risk | housing · red | Stale | education
The Assistant synthesises each domain and grades it. Green is a thriving domain with fresh, clear evidence. Amber is an at-risk domain — here, housing instability flagged in a recent note. Red is stale data: the education evidence is too old to trust as a current status.
Take the lowest-graded element and fix it with something the program could realistically capture.
Take the stale-education element above and fix it: set a freshness window that flags any domain whose evidence is older than the review cycle. Show the before → after grade and the single edit that moves it to green.
Create a 'missing & incomplete' report from this analysis in Sopact branding. 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 & open it in a new tab.
Demand a date with every status. A status without a date is a guess. Requiring evidence-plus-date is what lets the Assistant grade a stale domain red instead of quietly carrying old data forward as current.
Name one pressing need, not five. A whole-person read can list everything that is wrong. Forcing a single most-pressing need turns the synthesis into a next action a caseworker can take today.
List your life domains explicitly. Housing, health, education, employment — spell out the domains you track so no part of the person is silently dropped from the read.
Re-run after each major update. Status changes; the read should too.
Re-run this prompt after any significant note so the status reflects the latest evidence, not last quarter's.
Synthesise a status across every life domain — housing, health, education, employment, and more — labelling each at-risk, stabilising, or thriving with supporting evidence and a date, then name the single most pressing need. The Sopact Sense Assistant does this from the full record and grades each domain green, amber, or red, giving a whole-person view a single metric can't.
Because a domain can look fine on old evidence that no longer holds. Requiring a date lets the Assistant flag stale data as red, so you know which parts of the picture need refreshing before you rely on them.
Have the Assistant name one most-pressing need rather than listing every issue. That converts a full status read into a clear next action for the caseworker.
Open Sopact Sense, paste your program description, and put it to work.
Try in Sopact
