Python · Streamlit · Claude Code

The analyst's
co-pilot.

Demand-planning analysts were spending 5–6 hours every single day manually pulling, matching, and reconciling data across five sources and three platforms. I built an internal app — in 3 days — that does it for them.

200+
man-hours reclaimed every month
01 — THE PROBLEM

Five sources. Three platforms.
Five to six hours. Every day.

The demand-planning team at Accenture was the last mile between raw data and decisions — but they were spending the bulk of their day not planning, but plumbing. Every morning meant opening five different data sources, manually cross-referencing them across three separate platforms, reconciling mismatches by hand, and then assembling outputs for reports and system uploads.

Five to six hours. Daily. For a task that was entirely deterministic — the same steps, the same logic, the same pain — just with different data each time. There was no single source of truth. No automation. No tooling. Just analysts, spreadsheets, and a growing backlog of ad-hoc requests on top.

5
data sources to pull from manually
3
platforms to match and reconcile across
5–6 hrs
lost to reconciliation every single day
02 — THE APPROACH

One app. Every step
of the workflow.

Rather than a single script, I built a small suite of connected tools inside one internal app — each owning a step of the workflow, so the analyst drives the whole process from one place instead of stitching steps together manually.

Built end-to-end with Claude Code, which let me move from problem to working tool in days, not sprints, and iterate directly against real analyst feedback.

01
Ingest
Pull & normalise from all sources
02
Reconcile
Clean & match across formats
03
Transform
Run business logic
04
Output
Downstream-ready files & reports
03 — WHAT IT DOES

From raw data to ready output —
automatically.

Pulls and normalises data automatically
Ingests from multiple sources such as ERP system, Inhouse platforms, manual excel files, and normalises to a single format — no manual copy-paste.
Runs reconciliation and transformation logic
The matching, cross-referencing, and calculation steps that used to be done by hand in spreadsheets now run in seconds.
Produces downstream-ready output
Reports and upload-ready files formatted exactly as downstream teams need them — no reformatting before handoff.
👤
Built so a non-technical analyst can run it unassisted
Zero learning curve. The team adopted it without a rollout deck or change-management session — they just switched.
04 — THE OUTCOME

200+ hours back.
Team adopted it without being asked.

200+
man-hours reclaimed per month
Days

Clicks
manual cycle compressed
0
change-management sessions needed for adoption

The clearest signal that it worked wasn't a metric — it was behaviour. The team started using the app without being told to. No rollout deck, no change-management session. They just switched.

A multi-day manual cycle compressed to a few clicks. Fewer hand-off errors, and analysts back on analysis instead of data prep.

STACK
PythonStreamlitClaude APIClaude Code
The point wasn't the automation. It was giving skilled people their judgment time back.