BACKGROUND
Hyprbots is a fintech startup focused on reducing manual work across invoices, accruals, and procurement to improve efficiency for accountants and CFOs.
01
Procurement Feature
PROBLEM
Procurement workflows in small and mid-sized businesses are slow, error-prone, and heavily manual; this requires accountants to reconcile multiple financial documents before taking action.
DESIGN BRIEF
How might we facilitate procurement reviews to help accountants identify and reconcile errors in the review process efficiently?
RESEARCH
Hyprbots' approach to improving the review process: surfacing AI-parsed data to indicate errors/ discrepancies
As the firm created AI co-pilots to automate procurement workflows, accountants still needed to review and validate AI-generated data. Existing Enterprise Resource Planning (ERP) interfaces surfaced this information in dense layouts, making errors difficult to detect quickly and increasing review time.
SCOPE
Introducing the human review layer within the workflow (human-in-the-loop approach)
I focused on designing the human review layer within an automated three-way matching workflow — specifically how accountants scan, validate, and correct procurement data before taking action.
IDEATION
Supporting scanability through surfacing the most relevant extracted information while also allowing access to original finance documents for helping accountants tally details.

Error states used to surface errors
Grouping key fields based on relevance to improve users' ability to scan information

Responsiveness to scale information across screens while preserving information hierarchy and review flow
OUTCOME
Two-pane layout which includes a document drawer as well as key finance information with error indicators to help accountants scan and take action to rectify procurement errors
I worked within an existing product strategy and interaction pattern, refining the layout, information hierarchy, and error surfacing to support efficient financial review.
IMPACT
$2M+
raised through the seed funding round supported by MVP demos including this key feature, which was shipped in early 2025.



























