Workflows

Business work

Create a repeatable business report

Turn a recurring business question into a validated, rerunnable report with clear data boundaries.

CodexClaude CodeCursor

What you will work toward.

A repeatable report pipeline with validated inputs, explicit metrics, and a reviewable artifact before distribution.

Prepare my brief

Make this workflow yours.

Choose your AI tool, describe your task, and copy one complete project brief. Your inputs stay in this tab.

Includes your prompt, selected references, skill instructions, setup steps, and checks. Use your own AI account; Pristren does not run a model here.

Describe your project or task to prepare your brief.

Read the complete brief
Create a repeatable business report for [Describe the project, audience, and useful result.] within Use existing project conventions. State assumptions and verify the result..

Define the audience, decision, reporting period, data sources, and metric formulas. Inspect an approved schema or synthetic sample before connecting live data. Identify required fields, time zones, currency treatment, duplicate rules, and how missing or stale data should appear. Keep personal and confidential data out of prompts and fixtures unless explicitly approved.

Implement a rerunnable report generator with separate ingestion, validation, calculation, and presentation steps. Use a small fixture with known totals to verify calculations and edge cases. Make failures visible instead of silently producing an empty success report. Include the data period, source freshness, definitions, and limitations in the output.

Generate a reviewable local artifact first. If scheduling is in scope, prepare a manual trigger before a timed schedule and make repeated runs safe. Keep external delivery, publication, and live account writes as separately authorized steps. Report the commands run, verified fixture results, output location, and any credentials or account configuration still needed.

Execution environment: Codex. Follow applicable project instructions and verify the requested result.

Workflow
https://pristren.com/workflows/automate-business-report/

Expected result
A repeatable report pipeline with validated inputs, explicit metrics, and a reviewable artifact before distribution.

Before you begin
- A business question, report audience, and reporting period.
- An approved data source and a synthetic sample with known totals.
- Metric definitions, output format, and a decision about scheduling versus manual execution.

Setup for Codex
- Start Codex in the repository and read applicable AGENTS.md guidance. Include only the files this task needs.
- Use a synthetic fixture with known totals, validate inputs, and generate an artifact before enabling any delivery or schedule.
- Use the acceptance checks below to assess the result; an agent completion message is not evidence that the task passed.

Selected resources
- Build reports from evidence: https://pristren.com/resources/evidence-led-report/
  Use the published resource’s Download SKILL.md action, or copy its complete original SKILL.md text. Draft resources are not publicly downloadable.
  Save the supplied SKILL.md as .agents/skills/evidence-led-report/SKILL.md in the project. Review it before use.
  Open the project in your tool and select evidence-led-report by name; check that it resolves to this project-local version.
  Read the resource below and apply only the parts relevant to the current task.
  Inspect the loaded skill before using it on a representative task. This page documents setup; it has not performed the installation for you.
  mkdir -p .agents/skills/evidence-led-report

Skill instructions (Build reports from evidence)
---
name: evidence-led-report
description: Produce a sourced research or business report from supplied data while keeping observations, calculations, and recommendations distinct.
---

# Evidence-led report

Define the question, audience, time range, and unit of analysis before drawing conclusions. Identify the source of each input and whether it is current enough for the question. Ask only for missing information that would materially change the result.

Keep a working evidence record: source URL or artifact, checked date, claim supported, scope or plan qualifier, and uncertainty. Missing documentation means unverified; it does not establish that a capability is absent. A vendor claim is not a hands-on benchmark.

For calculations, state units, denominators, exclusions, and transformations. Check that totals reconcile and distinguish zero from missing values. Do not turn views into unique people, a download into a successful implementation, or an enquiry into a paying client.

Write the report around the answer and the evidence needed to assess it. Separate observed facts, interpretations, and proposed actions. Cite close to the supported statement. Include material limitations and make recommendations proportional to the evidence.

For a repeatable report, describe the expected inputs and validation checks so a later run can reject stale or malformed data. Drafting a report does not authorize sending it, publishing it, or modifying the source system.

- Create a repeatable business report — master prompt: https://pristren.com/resources/automate-business-report-prompt/
  Use the task-specific master prompt above.

Execution
1. Define the business question, metrics, time zone, and approved data boundary.
2. Build a synthetic fixture with known totals and missing/duplicate cases.
3. Implement ingestion, validation, calculations, and an inspectable report artifact.
4. Verify repeat runs; prepare scheduling or delivery only within explicit authorization.

Acceptance checks
- Known fixture totals match the documented metric formulas.
- Missing, stale, and malformed inputs produce visible warnings or failures.
- The report identifies its period, source freshness, and limitations.
- Repeated execution avoids duplicate external actions.

If something fails
- Totals differ from the source dashboard: Compare filters, time zones, duplicate handling, and metric definitions before changing the formula.
- A scheduled run produces an empty report: Reject missing or stale inputs and inspect credentials, source availability, and reporting-period boundaries.

Inspect the project first. Report the changes, the checks actually run, and anything still unresolved. Ask before any deployment or external publication.
Tool setup and prerequisites
Documentation reviewedChecked 2026-11-17

Tool setup checked against official documentation. Pristren has not executed this workflow through this tool.

  1. Start Codex in the repository and read applicable AGENTS.md guidance. Include only the files this task needs.
  2. Use a synthetic fixture with known totals, validate inputs, and generate an artifact before enabling any delivery or schedule.
  3. Use the acceptance checks below to assess the result; an agent completion message is not evidence that the task passed.
Official setup documentation

Before you begin

  • A business question, report audience, and reporting period.
  • An approved data source and a synthetic sample with known totals.
  • Metric definitions, output format, and a decision about scheduling versus manual execution.
Skills and tools included in your brief

Required resources are included. Add optional ones when your task needs them.

Create a repeatable business report — master prompt

Required

Start with this workflow’s original task-specific master prompt.

Review instructions
Build reports from evidence

Required

Carry source dates, definitions, and uncertainty into the report.

Review instructions
GitHub Actions

Optional

Add a reviewed manual trigger or schedule after local generation works.

Review instructions

What your AI will work through.

  1. Define the business question, metrics, time zone, and approved data boundary.
  2. Build a synthetic fixture with known totals and missing/duplicate cases.
  3. Implement ingestion, validation, calculations, and an inspectable report artifact.
  4. Verify repeat runs; prepare scheduling or delivery only within explicit authorization.

Check the result before calling it done.

  • Known fixture totals match the documented metric formulas.
  • Missing, stale, and malformed inputs produce visible warnings or failures.
  • The report identifies its period, source freshness, and limitations.
  • Repeated execution avoids duplicate external actions.

When something gets in the way.

Totals differ from the source dashboard

Compare filters, time zones, duplicate handling, and metric definitions before changing the formula.

A scheduled run produces an empty report

Reject missing or stale inputs and inspect credentials, source availability, and reporting-period boundaries.

How did your attempt go?

Try the brief in your AI tool first. Your feedback helps us find workflows that need attention.

Go a little deeper.

Sources and review notes