BUSINESS INTELLIGENCE / REVIEW ARCHITECTURE
Lead Audit Review
A research pipeline that discovers suitable businesses, audits public website signals, develops evidence-backed opportunity hypotheses and keeps a person in control of every outreach decision.
01 / LEAD GENERATORCurrent
Current
architecture.
From search terms and manually supplied URLs through crawling, evidence, scoring and human-reviewed outreach. The branches show where sources split, combine and become the next system record.
Discovery candidates
OPTIONAL Related-company expansion
HOMEPAGE DISCOVERY
Page classification and sampling
Combined commercial assessment
JSON state files
02 / TOOLS BEHIND THE SYSTEMWhat powers
What powers
each part.
Each tool has a narrow job. Together they move the work from public research to a decision a person can understand and control.
01DISCOVER
Find and reach the right websites
The first group discovers businesses, checks their addresses and visits public pages without letting one slow website hold up the full run.
- PythonRuns the research pipeline and keeps each business isolated.
- DuckDuckGo + BingProvide the first set of public discovery results.
- RequestsFetches pages with timeouts, rate limits and safe retries.
- PlaywrightOptional fallback for websites that need a real browser to appear.
02UNDERSTAND
Read pages and form evidence
The page code is reduced to useful content, then checked in the same consistent way for every business.
- Beautiful SoupSeparates useful text, links and page structure from the HTML.
- Python rulesApplies visible, repeatable checks instead of hidden AI judgement.
- Evidence recordsKeep the source page and supporting words beside every finding.
03PRESERVE
Preserve each research run
The completed audit is written into ordinary, inspectable formats before it reaches the review interface.
- PandasShapes results into consistent rows for comparison and export.
- OpenPyXLCreates the Excel workbook used for wider review.
- JSON + CSVKeep a timestamped source record that can be reopened later.
04REVIEW
Review and manage the next action
The final group makes the research understandable to a person and records what happens after they make a decision.
- Next.js + ReactPower the local workspace where evidence and live websites meet.
- SMTPSends a message only after it has been reviewed and approved.
- IMAPChecks for replies and connects them to the original business.
- Local JSON stateStores notes, rejections and follow-up reminders.
03 / WHY THESE CHOICESWhy these choices
Why these choices
matter.
Evidence before messaging
Every recommendation is tied back to observable public pages so a reviewer can challenge the conclusion before contacting anyone.
One bad site cannot stop a run
Audits are isolated per company. Failures are logged while successful businesses continue into the output artifacts.
Human-controlled outreach
Scoring prioritises attention; it does not grant permission to send. The review UI keeps drafts, notes, replies and follow-ups visible.
MORE WORK