Give Sopact Sense a program's page and it rebuilds the 4×4 logframe, grades every cell, and flags the unmeasurable indicators and risks-disguised-as-assumptions that get proposals sent back.
In short: To review a logframe, give the program's page (or its text) to an AI and ask it to rebuild the 4×4 matrix and grade every cell by evidence — green where an indicator is SMART and verifiable, amber where a baseline is missing, red where an indicator is unmeasurable or has no means of verification. Sopact Sense does this in minutes straight from a URL, so the two errors that get logframes sent back — unmeasurable indicators and risks disguised as assumptions — are flagged before a reviewer sees them.
A review starts from what the program actually publishes. Point the Assistant at the program or proposal page and tell it to use only what's stated there:
You are the Sopact Sense Assistant. Audit the program/proposal page at [URL] (or I will paste its content). Use only what is stated on the page. Wait for my task.
Ask Sense to reconstruct the 4×4 logframe from the page and grade every cell — flagging indicators you couldn't actually measure and assumptions that are really risks:
Read [URL] and rebuild its Logframe as a 4×4 matrix. Flag unmeasurable indicators and risks disguised as assumptions. Do not infer what the page doesn't say. Grade every cell green / amber / red.
Five elements make the review rigorous: the input (the live [URL] or its text); rebuild the matrix (four levels × four columns); unmeasurable indicators and risks-as-assumptions (the two errors that get logframes returned); no inference (it won't invent what the page doesn't say); and the grade (green / amber / red at a glance).
Sense returns the rebuilt matrix with each cell graded and the weak indicators called out. The demo reviews Bright Futures Initiative, engineered to grade one green, one amber, one red:
Bright Futures Initiative helps ~150 first-generation students each year. We run weekly tutoring, college-application workshops, and a summer bridge camp. Our goal is for students to enroll in college and persist to year two. Last year 128 of 150 students (85%) submitted at least one college application, tracked through our application portal. We believe consistent mentoring builds the confidence students need to persist. We have not yet measured year-two persistence, and we do not state a baseline college-enrollment rate.
GRADE: green | 85% submitted | tracked in the portal — a SMART indicator with a clear MoV; amber | enrollment rate | stated as a goal but with no baseline to measure against; red | year-2 persistence | unmeasurable as written, and no means of verification
The green cell is a verifiable indicator, the amber cell is an enrollment outcome with no baseline, and the red cell is a persistence indicator that isn't measurable and has no means of verification attached.
The review pays off when you fix the cell holding it back. Take the lowest-graded element and make it measurable with one realistic change:
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.
For Bright Futures, that's rewriting the persistence row as a SMART year-two indicator with a registrar record as its means of verification — turning a red cell green.
Generate a decision-first report in your own brand, then a shareable link:
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.
Every indicator needs a means of verification. The quickest tell of a weak logframe is an indicator with no way to verify it. Ask Sense which indicators have no means of verification — those are the cells a reviewer marks first.
Check the assumptions for hidden risks. Ask Sense to flag any assumption that's really an unmanaged risk. “We assume students stay enrolled” is a risk, not an assumption — and reviewers know the difference.
Re-review after each fix. Add the means of verification Sense suggests, then re-run the review next cycle and watch the grade climb.
Tighten the program page for accuracy. Once you've seen the grades, ask Sense to rewrite the page so its claims match the evidence:
Based on the grades above, suggest edits to the program page so its claims match the evidence. Flag every sentence that overstates what the program can show, and rewrite it to be accurate and specific.
A strong logframe has a SMART indicator and a matching means of verification at every level, a baseline for each outcome it claims, and an assumptions column that lists genuine preconditions rather than unmanaged risks. If any indicator can't be measured, or any assumption is really a risk, the logframe isn't ready — grading each cell green, amber or red makes those gaps obvious.
A logframe review rebuilds a program's 4×4 matrix and checks each cell: is the indicator SMART, is there a means of verification, is the assumption a real precondition or a hidden risk, and is there a baseline? It's the check a funder runs before approving — done in minutes with AI rather than by hand.
The two that show up most are unmeasurable indicators (vague, not time-bound, or with no means of verification) and risks disguised as assumptions. A third is a missing baseline, which makes an outcome indicator impossible to judge. Fixing those three is usually what turns a returned logframe into an approved one.
Open Sopact Sense, paste your program description, and put it to work.
Try in Sopact
