Automation
KraftFlow
Evidence-grounded prospecting with deterministic control.


Why this needed to exist.
Traditional prospecting tools optimise for message volume rather than relevance. They often generate generic outreach that cannot be justified through real observations. KraftFlow was designed to determine whether a company is genuinely worth contacting, collect traceable evidence and stop unsupported AI claims before they reach a human reviewer.
- Context
- Internal Tool
- Platform
- Local Web Application · Background Worker
Complexity, given a direction.
- 1Lead Discovery
- 2Content Extraction
- 3Evidence Gate
- 4Browser Capture
- 5AI Audit
- 6Reference Validation
- 7Human Review
The work behind the interface.
Deterministic control around the LLM
Code manages orchestration, limits, state transitions, validation and safety rules. The LLM is limited to interpreting captured evidence and generating language.
Evidence-linked AI findings
Audit findings are rejected unless they reference an extracted evidence record, captured browser source or screenshot.
Staged evaluation funnel
Low-cost extraction and filtering run before browser capture and visual AI analysis.
Evidence, not theatre.
Completed a working local-first prototype covering lead discovery, evidence collection, AI-assisted auditing, scoring, draft validation and human review.
End-to-end workflow completed
Dedicated worker and controlled concurrency
Evidence-linked AI findings
No autonomous email-sending capability