FlagshipInternal analytics practiceResponsible AI adoption

"How do we get real productivity from AI without losing control of the analysis?"

A governed AI workflow for analytics teams

I designed and piloted an AI-assisted analytics workflow that pairs natural-language prompts with Markdown SOPs and version-controlled Power BI templates. Human-in-the-loop validation is required throughout.

SectorInternal analytics practice, applied across sectors
RoleDesigned the target workflow and SOP structures
ToolsPower BI (PBIP), DAX, VS Code, GitHub / Copilot, Markdown
SignalEst. 60–80% less time on repetitive tasks
The challenge

Repetition, fragile templates and knowledge trapped in chat history

Power BI template updates, report customization and recurring data reviews depended on repetitive manual steps. Each edit inside Power BI was slow and hard to govern, and English and French versions were maintained separately.

Troubleshooting lessons and business rules often stayed in individual project histories. The team kept re-explaining the same definitions, and AI prompts written ad hoc produced uneven results. Generated outputs could also look right without having been validated.

My role

Designer of the target workflow

I designed the target workflow, created the natural-language instruction patterns, developed the Markdown SOP structures, supported the move toward version-controlled Power BI project files, and built validation into the automation design from the start.

Approach

How it was done

  1. Reverse-engineer proven work

    Start from completed, validated projects and extract the ideal workflow, instead of inventing a new process.

  2. Generate the SOP before execution

    The method is written in plain-language Markdown with clear inputs, checks and deliverables.

  3. Raise missing inputs up front

    Dependencies and open questions go to stakeholders before anything runs.

  4. Build in prevention, not debug history

    Lessons from earlier errors become safeguards in the SOP.

  5. Version-control the product

    VS Code, Git-based practices and Power BI project files replace risky manual edits.

  6. Validate independently

    Outputs are recreated in Excel or Power BI before the generated workflow is trusted more.

Signature visual

The workflow, running

sop/donor-profile-build.md · synthetic demo
    Manual vs AI-assisted effort

    Choose a repetitive task to see what the AI does and what stays with a person.

    Bilingual Power BI

    One model, two languages

    A related implementation redesigned an internal Power BI product so that English and French behaviour comes from model-first changes, dynamic measures and language-aware bindings, instead of from duplicate templates. English stays as the baseline.

    The work reached an ~85% visual-update checkpoint with six translated source fields. Manual and AI-supported workflows were compared side by side for a team demonstration.

    01Translate at source

    Translated fields live in the model, not in visuals.

    02Dynamic measures

    Titles and labels switch with a language selection.

    03Schema-safe queries

    Power Query logic protects against missing columns when sources change.

    04One template

    Less duplicate maintenance and fewer drift errors.

    Evidence

    What the numbers say

    est. 60–80%

    Less time on selected repetitive tasks such as template updates, label maintenance, SOP drafting and data-review outputs.

    Owner estimate
    ~85%

    Of visuals updated at the documented checkpoint of the bilingual redesign, using dynamic language logic.

    Verified
    6

    Translated source fields supporting language switching, with English kept as the baseline.

    Verified
    1

    Reusable operating model: request → SOP → clarification → execution → validation → documented output.

    Owner-confirmed

    Figures use approved public wording: rounded, generalized or indexed so no client can be identified. Evidence standard

    Outcome

    The value created

    The result is a reusable model for governed AI assistance. The value is repeatability and controlled adoption, not automation for its own sake. Knowledge now lives in SOPs and prompts that the next analyst can pick up, and validation is a required step.

    The 60–80% figure is an owner estimate for specific repetitive tasks, not total project time and not a formal time study. Automated location-level report production and Python-supported data review are still being explored and are not presented as results.

    For your organization

    What this means for you

    Want AI productivity your auditors and executives can trust?

    I can map which of your analytics workflows suit AI assistance, write the SOP and prompt library, build the validation checks, and train your team to run it. Your knowledge stays with you after the engagement ends.

    Confidentiality note: this case study is anonymized. The sector label is generalized and there are no client names, proprietary templates or source screenshots. All visuals are rebuilt with synthetic data that keeps the analytical concept but none of the original values. Contribution is described with specific verbs (owned, designed, developed) because this was delivered within a wider team.

    Next case · A

    National membership data framework

    Read next →