Give Sopact Sense a program's page and it reconstructs the results framework — strategic objective to intermediate results to sub-IRs — grading each and flagging the unlinked results and missing baselines where most go wrong.
In short: To audit a results framework, give the program's page (or its text) to an AI and ask it to reconstruct the hierarchy — Strategic Objective → Intermediate Results → Sub-IRs — and grade each by evidence: green where the result ladders up and has a baselined indicator, amber where a baseline is missing, red where a result has no indicator or doesn't link to the objective. Sopact Sense does this in minutes straight from a URL, so the place most results frameworks go wrong — the unlinked result — is flagged before a reviewer finds it.
An audit 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 rebuild the results framework from the page and grade each level — flagging results that don't ladder up and indicators with no baseline:
Read [URL] and reconstruct its Results Framework: Strategic Objective → Intermediate Results → Sub-IRs, each with its indicator. Flag unlinked results and missing baselines. Do not infer what the page doesn't say. Grade every element green / amber / red.
Five elements make the audit rigorous: the input (the live [URL] or its text); reconstruct SO → IR → Sub-IR; unlinked results and missing baselines (where most results frameworks go wrong); no inference (it won't invent what the page doesn't say); and the grade (green / amber / red at a glance).
Sense returns the reconstructed hierarchy with each result graded and the orphan results and gaps called out. The demo audits 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 | applications IR | 85% submitted, tracked — ladders to the objective; amber | enrollment IR | stated but with no baseline to measure against; red | persistence IR | no indicator at all, and an orphan sub-IR that doesn't link up
The green result is an intermediate result carried by a tracked indicator, the amber result is an enrollment IR with no baseline, and the red result is a persistence IR with no indicator — plus a sub-IR that doesn't ladder up to any objective.
The audit pays off when you fix the result 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 adding a year-two persistence indicator and re-linking the orphan sub-IR to the enrollment objective — turning a red result 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.
Hunt the unlinked result. The signature failure of a results framework is a result that doesn't roll up to anything. Ask Sense to trace every sub-IR to its IR and every IR to the objective, and to name any that don't connect.
An IR with no baseline can't be judged. Ask Sense which intermediate results state a target but no baseline — those read as aspirational, not measurable, to a reviewer.
Re-audit after each fix. Add the indicator or baseline Sense suggests, then re-run the audit 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.
Trace the logic in both directions: every sub-IR should roll up into an intermediate result, every IR into the strategic objective, and every level should carry a baseline-and-target indicator. A review flags unlinked results, IRs with no baseline, and results with no indicator — the three things that make a framework read as incoherent. AI does this in minutes from the program's page.
An unlinked (or orphan) result is an intermediate result or sub-IR that doesn't ladder up to anything above it — it sits in the framework but doesn't contribute to the strategic objective. It's the most common reason a results framework looks busy but doesn't actually show how the program achieves its aim.
Yes — give Sopact Sense the program's page URL and it reconstructs the SO → IR → Sub-IR hierarchy from what's published, grades every result, and flags unlinked results and missing baselines, without inventing indicators the page doesn't state. It takes minutes instead of a manual review.
Open Sopact Sense, paste your program description, and put it to work.
Try in Sopact
