Hire an AI grant spending and evidence report preparer

Everything it can hand back

Your task sets the actual outputs. The specialist picks the methods that cover them.

• A reconciled grant spending table, variance brief and evidence gaps.
• Step files with evidence, unresolved facts and actual checks completed.
• A hand-back summary and one practical next step.

How it does the job well

• Agree the question and the decision it supports before analysing.
• Check the data first: date range, grain, missing values, duplicates and definitions.
• Compare like with like: same period length, definitions and segments.
• Separate what the data shows from what it might mean, and give confidence levels.

Mistakes it avoids

• Inventing facts, metrics, dates, permissions, quotes or completed actions.
• Applying a prior step's output without checking its meaning and source.
• Re-running successful steps with unchanged inputs or hiding a failed check.
• Treating these portable instructions as a connected service or an installed schedule.
• Reporting a change without checking whether tracking or definitions changed.
• Treating correlation as cause.

How the work is checked

• Restricted spending follows the supplied award rules; unknown eligibility is a question for the fund owner.
• Every factual claim, figure and date traces to a source or is clearly labeled as an assumption.
• The original source files stay intact, and revised files have distinct names or versions.
• Each required component check ran, or the run stopped and says which check could not pass.
• States which checks passed, failed or could not run, and names missing inputs.

These checks have not been run against a model yet. Your AI uses them to check its own work.

Capabilities

• Spreadsheet checker. Reconcile transactions and receipts to the grant period, budget categories and restricted fund ledger without changing source records.
• Budget variance explainer. Bridge the actual grant spending to the approved phased budget, keeping timing differences and unapproved reallocations explicit.
• Stakeholder update writer. Draft the fund owner update with source totals, unresolved eligibility questions and requested decisions, without submitting a funder return.

How the role works

1. Checks your task, context and available tools.
2. Picks the methods needed and prepares a work plan.
3. Carries out supported tasks, with each method's limits and review gates.
4. Checks the real deliverables and corrects supported faults.
5. Hands back files, evidence and unresolved gaps.

Your specialist's working setup

Download the base specialist without a task form or account. README.md and SETUP.md explain how to use the folder. SOUL.md defines its scope. INTAKE.md asks missing questions inside your AI. PLAYBOOK.md, SKILLS.md, BEST_PRACTICES.md, CHECKS.md and HANDOFF.md guide the work and its checked deliverables.

Complete associated skills, supporting files and licences are included. Choose only the methods needed for the actual task. Keep context, working files and accepted feedback in your AI project.

Use this specialist through MCP or the API

Call prepare_specialist with role_id prepare-a-grant-spending-evidence-pack only. No task is required to load it. Your AI asks what job you need done, what you want back and which relevant context it can use.

For task-led hiring, call find_specialist, explain the suggested specialists and let the user accept or change the team.

Complete ZIP: Download base specialist. API: GET /api/v1/specialists/prepare-a-grant-spending-evidence-pack/pack. The host AI supplies its own model, tools and execution; a pack does not connect accounts or run a task.

Inputs and helpful context

The specialist starts from the task brief. Only active methods require their inputs.

For the primary method, when used

• Start here: the award agreement and your transaction records for the reporting period.
• The approved budget, the fund restrictions and the actual receipts.
• The reporting period as start and end dates, the currency, and the fund or award identifier that appears on each transaction row.
• The intended reader, deadline and limits on what may be changed (optional).
• Earlier work and approved examples (optional).
• Available tools for the finished output: A compatible spreadsheet engine.

Helpful context (optional)

• Approved examples of a good result.
• A named reviewer and their acceptance rules.

Tools and access

• A compatible spreadsheet engine: Formula recalculation and workbook inspection need an actual compatible engine; static table checks can use supported scripts.
• Any good chat AI: It only needs your notes pasted in. A tracker connection is a bonus, not a need.

Functions and deliverables

• Grant spending and evidence report preparer: Share grant rules, budget, transactions and receipts. Get a spending table, budget differences and missing evidence for the fund owner.
  • A reconciled grant spending table, variance brief and evidence gaps.
  • Step files with evidence, unresolved facts and actual checks completed.
  • A hand-back summary and one practical next step.
• Spreadsheet checker: Check a spreadsheet for odd totals, broken formulas and messy data. Your original stays safe, and you get findings with proof and a new file.
  • A sheet inventory and scope
  • Findings with evidence locations
  • Data quality and formula issues
  • A new output file with your edits
  • Reconciliation results
  Source: Burhan Sebin.
• Budget variance explainer: Find out why your actuals missed budget. Give it actual and budget numbers and get each gap split by cause, plus short notes for leadership.
  • A breakdown of each variance by cause
  • Volume, price and mix amounts
  • Short written commentary
  • A waterfall chart outline
  • A list of gaps worth action
  Source: Anthropic.
• Stakeholder update writer: Turn your rough progress notes into a weekly, monthly or launch update for leaders, engineers, partners or customers, sized to the reader.
  • A draft update sized to your reader, ready to paste
  • A status colour with a one-line reason
  • Each risk with a plan or an owner
  • Each decision with options and a recommendation
  • A list of facts you still need to add
  • A version for a second reader (optional)
  Source: Anthropic.
• Metric definition writer: Share a metric, calculation and business use. Get a YAML definition, validation results and questions for the data owner.
  • A filled metric, dimension or entity YAML
  • A validation report
  • dbt-ready field names
  • Notes on edge cases
  Source: Nimrod Fisher.

Tasks you can use it for

• You need a reconciled grant spending table, variance brief and evidence gaps.
• The relevant facts are spread across files or notes and need one consistent review.
• You want the work and its checks saved so another person can review it.

Limits to check before starting

• You want to hand over a recurring process, not report on grant spending: use Process handover guide writer.
• You need an audit opinion or the funder's sign-off on the spending: ask your auditor or grant officer, because this prepares the table and marks the gaps.
• You have no transaction records for the reporting period: pull them from your accounts first, because the table cannot be reconciled without them.

Best way to use this role

Give it one clear outcome, the actual files and a definition of done. Keep the work in one AI project so it can reuse checked context and earlier files.

• Download the complete pack and add its governing file and component skills to your AI.
• Share the sources listed above and say which result you need.
• Ask the AI to follow the governing file, save each result and stop on a failed required check.
• Review the files, missing facts and proposed actions before using the result.

Read it as data

Read the complete role setup as JSON. Connect your AI to the AI Blocks MCP library and read aiblocks://roles/prepare-a-grant-spending-evidence-pack for its role instructions and pinned sources.

This is a prepared AI role. No task has run. Your AI carries out authorized work using its available tools and reports the actual deliverables and checks.