play icon for videos
← Academy
Grant review course · Lesson 5 deep dive

Ask your whole grant round anything (Assistant + MCP)

Horizon's board chair, finance and the auditor all asked about R-2 on the same Monday. Ask the round in plain language, through the AI Assistant or through Claude or ChatGPT, and get answers a colleague can check.

Academy / Applications, awards & grants / Deep dive

Lesson 5 · Deep dive 1 of 3 · About 25 minutes with practice, plus a one-minute video

Ask your whole grant round anything (Assistant + MCP)

Horizon's board chair, finance and the auditor all asked about R-2 on the same Monday. Ask the round in plain language, through the AI Assistant or through Claude or ChatGPT, and get answers a colleague can check.

Slide titled Stop exporting. Start asking. Start with one workflow this cycle. A grant manager at a laptop asks, How many families did our nutrition grantees reach this quarter? The reply is a bar chart labeled By grantee, with sources. Footer: Unmesh Sheth, Founder, Sopact; sopact.com.
The answer on the slide is a chart by grantee with its sources, not a paragraph. That is the standard for every question on this page. From the video Rethinking Grant Management with AI.
Additional course links

You leave with: A saved question specification and a checked answer for R-2's overdue reports, with scope, sources, coverage and what is unknown.

Where this fits: Lesson 5 asks you to answer the Monday questions from the record. This page answers the question its exercise raises: how do you phrase a question across the whole round so the answer can be checked, not only believed? Bring back a saved question and a checked answer for step 5 of the workbook.

Watch · 2:42–3:51 · ask the pool, get a shareable report

Unmesh asks the pool of 80 applications what barriers each person faces, then "tell me which 10 are the best." The demo runs in Claude, connected to Sopact through MCP; ChatGPT works the same way. Watch for his stress on reliable answers: that is what the rest of this page makes testable. Watch on YouTube ↗

Jump to: 3:25 — "which 10 are the best" becomes a shareable report

To ask useful questions across a grant round, define the round, the as-of date, the records in scope and the rule, then require the answer to show its sources, its coverage and what is unknown. Counts and totals come from structured fields; explanations come from the text, with the passage cited. A conversational answer is useful when a colleague can check how it was reached.

Start with a decision, not an open question

"Tell me everything about R-2" gives the assistant little to work with. The people asking you have narrower needs: which applications still need clarification before the committee meets, which quarterly updates are overdue, what Eastgate's first quarter shows.

In a configured system, each question becomes an export and a spreadsheet. Asked of the record, the answer arrives with its evidence attached.

State the decision and the evidence it needs. For a committee meeting, that is application IDs, assigned reviewers and open eligibility questions. For a reporting review, it is due dates, approved extensions and accepted submissions.

Keep identifiers distinct. A-31 is an application; Eastgate Youth Works is an organization that may apply again in R-3; its award has its own reporting obligations. A question about one round should not quietly pull in another.

Set the boundaries before asking

Write down five details before the question: the round, the as-of date, the record unit, the definition and the audience. A saved question is reusable only when these are explicit.

BoundaryR-2 exampleWhy it matters
RoundYouth Pathways Fund, R-2 onlyAvoids mixing rounds and programs
As-of dateThe morning of the board meetingStatuses and deadlines change daily
Record unitOne quarterly-update obligationOne grantee may owe several reports
DefinitionOverdue: due date passed, no accepted update, no active extensionMakes the count repeatable
AudienceProgram team, not the boardControls which details belong in the answer

Use the right evidence for the type of question

Different questions need different evidence. A paragraph summary is not a count of distinct application IDs, and a count does not explain why a grantee is behind.

Question typeR-2 exampleEvidence to use
OperationalWhich quarterly updates are overdue?Due dates, extensions and acceptance status, counted under the stated rule
DescriptiveWhat barriers do grantees describe in Q1?The narrative text, with each theme tied to cited passages
ComparativeHow does Eastgate's attendance compare with other grantees?The same measure, period and definition for each grantee
ExplanatoryWhy is Eastgate's enrollment unclear?The records behind the gap: 30 registrations with no status

For a question about a reviewer's decision, retrieve the recorded rationale rather than asking the assistant to guess what the reviewer meant. And keep "what changed" apart from "what caused the change," however persuasive the narrative sounds.

Worked example: which reports are actually overdue?

Horizon example · fictional

Suppose R-2 closed with ten awards, each owing a Q1 update. As of the board-meeting morning, five updates are accepted. Eastgate's is submitted, with a clarification open on its 30 unresolved registrations. One grantee has an approved extension. One grant agreement was signed later, so its first update is not yet due. Two are past their due date with no accepted update and no extension.

StatusCountWhat it means
Accepted5Complete under the acceptance rule
Submitted, clarification open1Eastgate: received, one question outstanding; not overdue
Active extension1Use the approved revised date
Not yet due1Do not chase
Overdue2Needs focused follow-up
Total obligations10Categories reconcile to the register

The overdue count is two. It is not five, even though five updates are not yet accepted. If one of the two has an unclear due date, the answer should separate it rather than pretend the classification is certain.

Ask for the two record IDs with their due-date and submission evidence, and check both before any reminder goes out. Eastgate needs a different message altogether: a request for the status of 30 registrations, sent through its unique ID, not a late notice.

A question to reuse

Replace the bracketed details and run it against the authorized records:

For [round], as of [date], identify overdue report obligations using this rule: [rule, including extensions and accepted submissions]. State which records and sources are included. Count distinct obligations, not files or organizations. Return the count, record IDs, due dates, status evidence and unresolved fields. Reconcile the categories to the included register. Do not send reminders or change statuses; prepare the evidence for review.

For a narrative question, change the instruction: identify the relevant passages, keep the grantee's explanation apart from the assistant's interpretation, and include conflicting evidence where it exists.

What a useful answer includes

A short answer can still show its reasoning. Ask for the conclusion first, then what someone needs to check it.

Sample answer · fictional

Answer: 2 of 10 R-2 Q1 updates are overdue under the stated rule.

Scope: R-2 only, as of the board-meeting morning; all ten award records included; no exclusions.

Sources: each award's reporting schedule, the extension approval and the submission log, linked by record.

Calculation: 5 accepted + 1 submitted with clarification + 1 extension + 1 not yet due + 2 overdue = 10.

Unknown: none for this count. Eastgate's enrollment figure is open, which affects the board question but not this one.

Next action: program owner to confirm both overdue records before sending reminders.

A citation is only useful if it supports the statement beside it. Open a sample, and check every source behind a consequential finding. A link to the first page of a budget workbook is not enough when the answer relies on a table further in.

Where MCP fits

The Model Context Protocol, or MCP, is a standard way for AI applications to connect to exposed tools and data. It lets Claude or ChatGPT read the same governed records the AI Assistant reads.

Permissions travel with the person, not the tool. A program officer asking through Claude should see exactly what that officer sees on screen, and a volunteer reviewer should not reach committee notes by asking. Confirm which records and operations your deployment exposes before relying on it.

Start read-only. If a connected tool can change records or send messages, make that explicit and keep a person approving each action. The MCP tools documentation recommends that people can review and deny tool invocations.

In Sopact Sense, every applicant and grantee keeps one persistent unique ID, the Intelligence Cell has already read each answer and document, and the Intelligence Row summarizes each grantee. The AI Assistant, or Claude and ChatGPT through MCP, asks questions of that record and answers with sources, so the question starts from read evidence rather than raw files.

Make repeated answers reproducible

Save the question, definitions, as-of date and source versions. Rerun it with the same records and rules when you check a result. If a new update arrives or an extension changes, the answer should change, and the saved scope shows why.

Wording from a language model can vary between runs. Do not promise identical prose. Check instead that the counts reconcile, the citations support the claims and the rule is applied the same way each time.

When two answers disagree, inspect the records, filters, date and definitions before rewording the question, and keep the discrepancy and its resolution. Treat instructions found inside a grantee's document as evidence, never as a rule to follow.

One honest limit: "all grants" means all records the workflow can read and the asker may see. If the assistant reads only part of the round, the answer must say so; a partial view cannot support a portfolio-wide claim.

When the answer feeds a decision the auditor will ask about, keep the question, evidence and reviewer decision together. The audit trail deep dive shows how.

Put it into practice

Test the answer before trusting the summary

  1. Using step 5 of the workbook, write the question specification for R-2's overdue Q1 updates: round, as-of date, record unit, definition and audience.
  2. Run the reusable question and check the answer against the ten-obligation table above.
  3. Add a duplicate file for one accepted update. The overdue count should not change.
  4. Change the active extension to an expired one, with the same as-of date. The count should rise to three.
  5. Remove the due date from one overdue record. The answer should name the missing date, not label the record overdue or on time.
  6. Write the board chair's question the same way, using eastgate-q1-update.csv, and note what the answer must say is unknown.

Download the workbook (PDF)
Practice data: horizon-r2-applications.csv · horizon-rubric.csv · calibration-scores.csv · eastgate-q1-update.csv

Check your reasoning before moving on

The duplicate file changes nothing, because the count is of distinct obligations. The expired extension moves one record from extension to overdue, so the answer becomes 3 of 10 and the categories still reconcile. The missing due date produces an unresolved record with a named gap, which leaves one confirmed overdue and one unresolved in that version of the table.

For the board question, a checked answer states 108 of 150 eligible participants attended at least 3 of the first 4 sessions (72%), cites Eastgate's Q1 report, and says that 30 registrations have no status and that placements at 90 days are not yet due. A colleague should reach the same numbers without relying on the assistant's confidence.

Questions grant teams ask

Can I ask questions across an entire grant round?

Yes, when the records are in one place, read and authorized for the person asking. Specify the round, the as-of date and the definitions, and require the answer to disclose what it included, what it excluded and what is missing.

Does MCP make answers accurate?

No. MCP connects an AI application such as Claude or ChatGPT to tools and data. Accuracy depends on the sources, the definitions, the calculation and a person checking the answer. What MCP adds is reach: the same governed records, with the same permissions, from the tool your team already uses.

How should overdue reports be counted?

Write the rule first, including accepted submissions and active extensions, then count distinct report obligations rather than files or organizations. Show unresolved records separately instead of guessing their status. A submitted report with an open clarification, like Eastgate's Q1 update, is not overdue; it needs a question, not a reminder.

Will the same prompt always produce the same answer?

Not word for word. Language-model wording varies, and the underlying records change as reports arrive. Save the scope, definitions, as-of date and source versions, then check that the counts reconcile and the cited evidence supports each claim. Reproducible means a colleague reaches the same result, not the same sentence.

Can the assistant send follow-ups automatically?

Only where that action is supported, configured and approved. Keep analysis apart from sending messages or changing records. Prepare the evidence and a draft request, then let the responsible person review it before anything reaches a grantee.

Put this guide into practice.

Bring one grant-round question and the records behind it. Explore how to prepare a checkable answer for your team.

Explore Applications & Grants →
Prepare Data Governance Before Using AI
Prepare your data governance
nonprofit-data-governance-before-ai
Feedback
Foundation
Prepare an evidence register and a tested governance baseline before applying AI to program data.
How to Turn Findings into Action and Check What Changes
The Loop — the method in one read
the-loop
Loop
The method
0
One continuous method for reliable, traceable AI reporting across case, application, grant, and program workflows: collect clean, analyze on arrival, and improve in time.
For growing data collection, connected analysis and recurring reporting
What Is Case Intelligence?
What Is Case Intelligence?
what-is-case-intelligence
Case
Foundation
1
One current, traceable record for each person—connecting intake, services, notes, surveys, documents, outcomes, decisions, and follow-up.
Workforce and training · Youth and mentoring · Case management · Scholarships · Accelerators · Education · Nonprofit programs
What is grant intelligence?
What Is Grant Intelligence?
what-is-grant-intelligence
Grant
Foundation
1
One connected evidence record from application and committee review through the awarded grant, grantee reporting, renewal, and board accountability.
Foundations and grantmakers · Public grant programs · Scholarships and fellowships · Accelerators
Connected Data Intelligence
Understand the approach
connected-data-intelligence
Feedback
Foundation
1
Connect recurring collection, relevant history, AI analysis, and governance in a workflow your team can maintain.
Growing organizations managing recurring data collection without a dedicated data team.
Measurement and Reporting: From Agreement to Evidence-Based Report
Measurement and reporting: from agreement to report
embedded-impact-measurement
Reporting
Start here
1
Turn the onboarding call into a reporting agreement, share one data dictionary, and write reports funders can compare and check.
For funders and the organizations they fund
Connect company context before collecting another return
Connect context
track-investees-impact-agreement-variance
Portfolio
Portfolio intelligence tools
1
Build a repeatable collect, review and improve cycle
Methodology — continuous, not annual
loop-methodology
Loop
The method
1
The continuous collect–analyze–improve cycle, adopted as an experiment: start with the step that already pays and add one data-collection step at a time.
Teams tired of rebuilding spreadsheets and forms who want a measurement system that compounds instead of resetting.
Agree the theory of change and core metrics on the onboarding call
Agree measures
onboard-portfolio-lock-impact-agreement-track-results
Portfolio
Portfolio intelligence tools
2
Test whether an AI-assisted result is repeatable and correct
Reliability — test repeatability and accuracy
loop-reliability
Loop
The method
2
Test repeatability and accuracy using versioned data, defined calculations, known-answer checks and human review of qualitative interpretation.
Teams that need to check recurring AI-assisted analysis before using it in decisions or reports.
Design an application process around the decision, not the form
Design an Application Process
how-to-design-an-application-process
Grant
Foundation
2
How to Structure Stakeholder Data: Four Common Patterns
Choose your record structure
which-shape-is-your-data
Feedback
Foundation
2
Map the people, observations and relationships your workflow needs before collecting data.
Turn the onboarding call into a reporting agreement
Turn the onboarding call into a reporting agreement
onboarding-call-to-reporting-agreement
Reporting
Agree together
2
How to build a theory of change, then show it as a logic model, logframe or results framework
How to build a theory of change, then show it as a logic model, logframe or results framework
how-to-build-a-theory-of-change
Reporting
Agree together
3
How to Build a Logic Model: Steps, Example and AI Prompt
Build a Logic Model You Can Use
how-to-build-a-logic-model
Reporting
Align
3
How do you onboard a grant or RFP program?
Onboard a Grant or RFP Program
how-to-onboard-a-grant-rfp-program
Grant
Foundation
3
Turn your theory of change into a data-collection plan
Turn a Theory of Change into a Data-Collection Workflow
theory-of-change-to-data-collection-workflow
Case
Foundation
3
Run quarterly collection around each company's dictionary
Collect quarterly
collect-investee-reporting-without-burden
Portfolio
Portfolio intelligence tools
3
Keep a clear trail from a finding to its evidence
Traceability & Transparency
loop-traceability
Loop
The method
3
Every figure links back to the exact response, note, or document it came from — a full audit trail from headline result to raw evidence.
Teams whose numbers get scrutinized — by funders, boards, auditors, or standards — and who need to answer where did this come from on the spot.
Build Context: What Your AI Needs to Know
Build context
build-organization-evidence-model
Feedback
Foundation
3
How to Change Survey Questions Without Losing Comparability
Change questions with a clear history
change-questions-without-breaking-the-record
Feedback
Control
3
Create a question-change log and decide how old and new versions should appear in reports.
Programme & MEL leads · Teams whose questionnaire has ossified · Anyone evaluating a platform where configuration is a purchased service
Five Dimensions of Impact: How to Review Your Evidence
Use the Five Dimensions to Test the Evidence
five-dimensions-of-impact
Reporting
Align
4
How do you design a grant rubric and eligibility rules?
Design Your Rubric & Eligibility Rules
grant-rubric-eligibility-rules
Grant
Foundation
4
Review impact and financial evidence before it reaches the dashboard
Review and approve
read-investee-reports-multi-signal
Portfolio
Portfolio intelligence tools
4
Adapt the learning cycle to your workflow
Flexibility — one method, four workflows
loop-flexibility
Loop
The method
4
The same collect–analyze–improve cycle, shaped to four kinds of impact work — case, grant, portfolio, and feedback — each shown end to end.
Anyone deciding where the Loop fits their work, who wants to see the full path from messy input to a report they can defend.
How to Collect Feedback Offline and Track the Same People Over Time
Collect offline and reconcile the batch
collect-feedback-offline
Feedback
Connect
4
Build a field protocol and reconcile a test batch across devices, visits and delayed uploads.
Field & multi-site programs · Low-connectivity contexts · Teams collecting in person
How Do You Design an Intake Form for a Baseline?
Design an Intake Form That Captures a Usable Baseline
intake-form-usable-baseline
Case
Nonprofit Track
5
Turn a proposed outcome into a reporting definition
Outcomes vs Outputs
frame-outcomes-over-outputs
Grant
Foundation
5
Plan and review your first workflow pilot
Plan and review your first workflow pilot
loop-guarantee
Loop
The method
5
How to Analyze Documents as Evidence: Sources, Context and Review
Read documents as traceable evidence
read-documents-as-evidence
Feedback
Connect
5
Create a document register and reviewed findings with source locations, context and explicit exceptions.
Check each partner report against the agreement
Check each partner report against the agreement
check-partner-reports-against-agreement
Reporting
Funder road
5
Combine compatible metrics and explain every portfolio total
Build rollups
portfolio-impact-rollups
Portfolio
Portfolio intelligence tools
5
How to Clean Open-Ended Survey Responses Without Losing Meaning
Clean responses and define the denominator
clean-open-ended-survey-responses
Feedback
Clean
6
Create a cleaning log, response-status table and reproducible report statement.
How to Review Participant Support Needs Mid-Program
Spot At-Risk Participants Mid-Program
spot-at-risk-participants-mid-program
Case
Nonprofit Track
6
How to Write a Nonprofit Grant Application: Template and Example
Grant Application for Nonprofits
grant-application-for-nonprofit-organizations
Grant
Foundation
6
Personalize quarterly donor and annual LP reports
Report with evidence
portfolio-lp-board-impact-report
Portfolio
Portfolio intelligence tools
6
How to Build a Funder Context Profile: Research to Reporting
Build a Sourced Funder Context Profile
build-funder-context-profile
Reporting
Align
6
Roll up and benchmark portfolio results
Roll up and benchmark portfolio results
roll-up-and-benchmark-portfolio-results
Reporting
Funder road
6
How Do You Measure Change at Exit?
Measure Change at Exit (Not Just Completion)
measure-change-at-exit
Case
Nonprofit Track
7
How do you collect applications clean at the source?
Collect Applications Clean at the Source
collect-applications-clean-at-source
Grant
Collect
7
Turn portfolio findings into action and test the next cycle
Act and improve
portfolio-risk-monitoring-alerts
Portfolio
Portfolio intelligence tools
7
How to Analyze Multilingual Feedback Without Losing Meaning
Analyze and review multilingual feedback
analyze-multilingual-feedback
Feedback
Clean
7
Build a language review sheet and test software on original responses, translations, codes and reporting bases.
Multi-country programs · Multilingual survey data · Global networks & chapters
How to Define Impact Metrics Your Team and Funder Can Use
Define Measures the Organization and Funder Can Both Use
define-impact-metrics-funders-want
Reporting
Align
7
Write the portfolio report for your board or donors
Write the portfolio report for your board or donors
write-the-portfolio-report
Reporting
Funder road
7
Survey Attrition: How to Track Missing Waves in Longitudinal Studies
Track missing waves and matched outcomes
survey-attrition-longitudinal-studies
Feedback
Read
8
Build a wave-status register, compare response groups and report paired change with coverage and limitations.
How to Use Mentor Notes to Review Participant Support
Use mentor notes for support review
mentor-notes-early-warning
Case
Nonprofit Track
8
How do you reduce applicant burden?
Reduce Applicant Burden
reduce-applicant-burden-auto-clarification
Grant
Collect
8
Impact Metric Definitions: A Practical Worksheet and Example
Give Every Number One Definition
one-definition-for-every-number
Reporting
Define
8
Map every funder's ask to one evidence base
Map every funder's ask to one evidence base
turn-reporting-requirements-into-evidence
Reporting
Funded partner road
8
How to Connect Quantitative and Qualitative Survey Data
Connect scores and comments
connect-quantitative-qualitative-survey-data
Feedback
Read
9
Build a linked analysis view and joint display, with clear groups, reporting bases and evidence limits.
How to Calculate SROI as New Evidence Arrives
Calculate SROI — Live, Sourced, and Honest
calculate-sroi-live
Case
Nonprofit Track
9
How to Collect Grantee Reports with Less Burden
Collect Grantee Reports Without Burden
collect-grantee-reporting-without-burden
Grant
Collect
9
Capture each funder's taste, and your own
Capture each funder's taste, and your own
capture-funder-taste
Reporting
Funded partner road
9
How to Analyze Pre, Mid and Post Survey Data
Analyze pre, mid and post surveys
analyze-pre-mid-post-survey-data
Feedback
Read
10
Build a matched pre/mid/post analysis, interpret score movement and retain clear rules for missing waves.
How to Report a Job-Training Program to Grant Funders
Turn a Cohort into a Funder Impact Report
job-training-grant-impact-report
Case
Nonprofit Track
10
How to Follow Up on Missing Grantee Data
Chase Missing Grantee Data
chase-missing-grantee-data
Grant
Collect
10
How to Collect Clean Data Inside Your Workflow
Collect Clean Evidence Inside the Workflow
collect-clean-data-at-the-source
Reporting
Embed
10
Write each funder's report with AI, then check it
Write each funder's report with AI, then check it
assistant-writes-the-funder-report
Reporting
Funded partner road
10
Draft from approved sources, check the claims, and save an accountable report version. Bring the brief from the previous lesson.
Program managers, grant leads and reporting teams
How to Analyze Longitudinal Survey Data
Analyze longitudinal survey data
analyze-longitudinal-survey-data
Feedback
Read
11
Build a continuing analysis record with clear time scales, observed trajectories and limits.
How to Turn a Job Description into a Requirements Checklist
Clarify employer requirements
job-description-requirements-checklist
Case
Social Enterprise Track
11
Review applications without reviewer bias: one rubric, read on arrival, people decide
Review Without Reviewer Bias
review-applications-without-reviewer-bias
Grant
Analyze
11
How to Keep Impact Reporting Numbers Consistent
Get Stable Results From Governed Data
same-numbers-every-time
Reporting
Read
11
Compare your results with outside data: live queries and public datasets
Compare your results with outside data: live queries and public datasets
compare-with-outside-data
Reporting
Toolkit
11
How do you analyze a batch of grant applications?
Analyze a Whole Round
how-to-analyze-a-batch-of-grant-applications
Grant
Analyze
12
How to Measure Outcome Duration and Drop-Off
Measure outcome duration and drop-off
measure-outcome-duration-drop-off
Feedback
Read
12
Build a dated outcome claim, distinguish missingness from outcome loss and test forecast assumptions.
How to Score Candidate–Role Matches with a Clear Rubric
Review candidate–role evidence
score-candidate-role-matches-without-bias
Case
Social Enterprise Track
12
Make every number in your report match its source
Make every number in your report match its source
where-every-number-came-from
Reporting
Toolkit
12
How to Report Job Placements to Impact Investors
Turn a Cohort into a Social-Enterprise Investor Report
job-placement-investor-impact-report
Case
Social Enterprise Track
13
How do you track reviewer conflicts of interest?
Track Reviewer Conflicts of Interest
track-conflicts-of-interest-audit
Grant
Analyze
13
How to Write a Donor Report: Format, Evidence and Example
Design a Report for a Real Funding Decision
donor-report-funders-trust
Reporting
Decide
13
Build a report brief and claim-and-evidence table before drafting. Explain delivery, outcomes, spending, limitations and next actions.
Program managers, grant leads and reporting teams
How to put a credible dollar value on your results
How to put a credible dollar value on your results
credible-dollar-value-on-impact
Reporting
Toolkit
13
Prepare a valuation brief. Decide what the evidence supports, what needs more work, and when an outcome account is enough.
Program, evaluation and investment teams considering social-value estimates
AI Data Access Controls: What Your Assistant May See
Control what the assistant can access
what-the-assistant-may-see
Feedback
Prove
13
Define task-specific access, test synthetic records and verify report-sharing boundaries.
How to calculate the SROI ratio, step by step: value map, financial proxies and adjustments
How to calculate the SROI ratio, step by step: value map, financial proxies and adjustments
how-to-calculate-the-sroi-ratio
Reporting
Toolkit
14
Build a reproducible SROI calculation, test its assumptions and explain the result in a reviewed report.
Evaluation and reporting teams reviewing an SROI calculation
How to Write an Evidence-Based Impact Narrative for a Funder Report
Write a cited impact narrative
impact-narrative-funder-report-cited
Feedback
Prove
14
Build and check a report paragraph using a claim-and-source table, appropriate quotations and clear limitations.
How Do You Read a Grantee Report?
Read a Grantee Report
read-grantee-report-multi-signal
Grant
Analyze
14
How Do You Compute Grantee Variance?
Compute Grantee Variance
how-to-compute-grantee-variance
Grant
Analyze
15
Keep a person’s history connected across programs and staff changes
Follow one person over time
one-person-followed-for-years
Feedback
Shapes
15
Build a participant record that preserves episodes, dates, versions and missingness across repeated collection.
How Do You Build an SROI Value Map?
Build an SROI Value Map
how-to-build-an-sroi-value-map
Reporting
Optional method
16
Build a first value map, keep missing evidence visible, and give each unresolved outcome a next action.
Evaluation, program and investment teams preparing an SROI analysis
How do you track budget, invoices and actual spend for a grant?
Track Budget vs Actual Spend
how-to-track-budget-invoices-actual-spend
Grant
Analyze
16
Multi-Rater Feedback: Connect Perspectives and Protect Context
Connect several perspectives on one person
several-people-describing-one-person
Feedback
Shapes
16
Design subject-rater relationships, reporting rules and a tested multi-perspective feedback record.
How Do You Pick a Financial Proxy for SROI?
Pick a Defensible Financial Proxy
how-to-pick-a-financial-proxy-for-sroi
Reporting
Optional method
17
Compare candidate valuation sources and document why one fits your outcome, stakeholder and reporting period.
Evaluation and reporting teams selecting financial proxies
How Do You Analyze Grantee Reporting Longitudinally?
Analyze Grantee Reporting Over Time
analyze-grantee-reporting-longitudinal
Grant
Analyze
17
Cross-Program Reporting: Combine Results Without Losing Meaning
Combine evidence across programs
many-programs-one-picture
Feedback
Shapes
17
Build a defensible cross-program result with comparable measures, correct denominators and documented exclusions.
How to read Form 990 for a grant review
Read a 990 for Compliance
how-to-read-a-990-for-compliance
Grant
Analyze
18
Pick One Question. Keep Every System You Have.
Run a member-network survey
member-network-survey
Feedback
Shapes
18
Design and test a member reporting cycle with continuing records, coverage checks and authorized results.
Ask your whole grant round anything (Assistant + MCP)
Ask Your Whole Grant Round Anything
ask-your-grant-round-anything
Grant
Analyze
19
How do you build a grant audit trail?
Build a Grant Audit Trail
grant-audit-compliance-trail
Grant
Communicate
20
How do you produce grant compliance and regulatory reports?
Produce Compliance Reports
grant-compliance-regulatory-reports
Grant
Communicate
21
How Do You Roll Grantees Into a Board Report?
Roll Grantees Into a Board Report
roll-grantees-funder-board-report
Grant
Communicate
22
How Do You Build Grant Dashboards and Maps?
Grant Dashboards & Maps
grant-dashboards-geographic-mapping
Grant
Communicate
23