SaaS
AI/ML
Platform Design
CISO Auto-Trace
Automates fund tracing, detects suspicious patterns, and generates reports in one click.
Year
2021-2024
Role

At a Glance
Auto-Trace automatically traces crypto funds from source to destination across multiple wallets and hops, helping financial crime investigators follow the money trail and flag suspicious entities in minutes instead of hours.
As the founding designer, I led the 0→1 design of Auto-Trace, owning the end-to-end UX, collaborating with data scientists and engineers to to design the tracing logic within heavy-data constraints. I validated the workflow with investigators using real case data and iterated the product through multiple development phases.
Impact
85%
faster investigations
30%
customer growth
Problem
As crypto-related financial crimes surged in 2021 , investigators manually traced hundreds of wallet hops to follow laundering paths and fund destinations, an error-prone, repetitive process that was slow and hard to scale.
Solution
An automated tracing tool that follows funds across blockchains, prioritizes key flows, and highlights suspicious entities, turning complex financial crime investigations into a fast, report-ready process.
Context
Before Auto-Trace, CISO’s Transaction Graph helped visualize flows, but still required manual wallet expansion. Investigators spent hours digging through noise, often exporting results into spreadsheets for evidence collecting.
Investigation process and live case example of manual expansion, filtering,
Challenge
We discovered the deeper issue wasn’t just volume, it was the inability to prioritize which transactions truly mattered. Analysts lacked a structured way to surface key flows, leading to wasted time and missed insights.
Funds Jumped Through Too Many Wallets
The graph relied on manual expansion. Money often flowed through dozens of wallets, forcing investigators to click each step, which was slow and time‑consuming.
Hard to Follow the Story of the Money
After expansion, analysts often faced overwhelming number of transactions per node. They had to sort by time and amount to figure out what mattered.
High-Risk Paths Hard to Spot Quickly
Analysts wanted the system to flag or rank risky paths automatically, so they didn’t have to dig through everything manually.
Analysts Created Workarounds
Noise forced analysts to document key paths in spreadsheets to build cleaner investigation reports, which made the process slower and harder to maintain.
Goal
From Manual to Automated Tracing
Introducing Auto-Trace
One-Click Tracing, Instant Results
Enter a wallet or transaction hash, and Auto-Trace follows the funds, highlights the most relevant flows, and identifies liquidation points.
No Risk Left Outside the Trace
Auto-Trace pulls in historical suspicious activity back in the graph, letting investigators review risky behavior alongside the flow.
Actionable Insights
Auto-Trace provides a clear next step for every address at the last hop, offers one-click export, monitoring for inactive wallets, or Continue Tracing for active ones.
Clearer Graphs to Reduce Noise
Large graphs stay readable with clustering, filters, and dimming of low-risk nodes, keeping focus on what matters most.
Approach and Iteration
1. Workflow Observation
To understand how investigators decide which paths to expand, I held working sessions with clients, observing live cases in CISO and reviewing the manual investigation reports. I focused on how analysts decided to expand, stop, or follow a path. By mapping out the full decision flow, I found analysts relied on four key patterns guiding their decisions.
How analysts make decisions on which path they want to follow.
✅ Outcome
By observing live cases and reports, I identified four key patterns guiding analysts’ decisions.
2. Designing and Testing the First Auto-Trace Flow
I partnered with data scientists and engineers to build the first tracing API, automating fund flow analysis using four key patterns and AI-powered risk scoring. For the first time, investigators could set parameters and have the system automatically trace fund flows along the most critical paths.
At the same time, I created the first Auto-Trace wireframes to show how setup and results would integrate into the investigation tool. With these mockups, we tested the feature on staging with clients using real case data, validating that tracing depth worked in live conditions and setting the foundation for future iterations.
✅ Outcome
Auto-Trace flow prototyped and tested on real cases
User testing validated depth but exposed performance and setup issue: long loading times, failed returns, and uncertainty about hop depth

Early Auto-Trace design for quick testing and delivery
3. Iterating on Tracing Limits
To address pain points from user testing, I worked with engineers to redesign the tracing setup, removing fixed hop limits and introducing Continue Tracing so analysts could extend flows step by step while getting faster results. Together, we brought backend thresholds upfront, giving investigators options to prioritize by amount or time when limits were reached, keeping traces focused and performance stable. I also built an Auto-Detect API to catch invalid time ranges and token selections early to reduce failed traces.
Address or Transaction
Time Range
Sending or Receiving Limits
Depth and Breath
Hops
Address expanded
Tracing Direction
Address or Transaction
INITIAL SETUP
Address or Transaction
Time Range
Tracing Direction
TRACE LIMITS
Expanded Addresses Limit
Hop Depth
+ Sort Transaction By
Date (Newest/ Oldest)
Value (High/ Low)
+ Amount Cap
TRACE RESULTS
+ Continue Tracing
Refining setup settings through multiple iterations
✅ Outcome
One-Click Auto-Trace simplified setup to just an address or transaction, making adoption faster
Less hops by default reduce long loading times
Reduced failed returns through Auto-Detect API
Gave investigators more flexibility with Continue Tracing



Setup page simplified with essentials only, auto-detect prevents failed traces
4. Improving Results and Graph Clarity
The early layout squeezed setup, results, and fund distribution into the same view, making the graph cramped and hard to interpret.
I redesigned the page to dedicate space to results and graph exploration, then added clarity features: clustering addresses by category, dimming low-risk nodes, and highlighting risky entities and exchanges. These changes kept large traces readable and helped analysts focus on what mattered most.
✅ Outcome
Cleaner layout with more space for results
Noise reduced through clustering and filtering
High-risk entities and exchanges highlighted to stand out
Suspicious activity pulled directly into traces for side-by-side analysis
Customization options to hide or filter less relevant nodes


Results page iterations improved clarity by freeing space for the graph
5. Designing Clear Next Steps
At the last hop, investigators needed clear guidance on what to do next. If funds flowed to an exchange, Auto-Trace offered a one-click export for compliance reports. If a wallet was inactive, it could be added to monitoring with alerts. And if a wallet was active, investigators could Continue Tracing directly from that address. This ensured every end point had a clear, actionable next step.
✅ Outcome
Faster compliance reporting with one-click export
Easier monitoring of inactive wallets with alerts
Clear, actionable paths at every investigation endpoint

The Impact
Since launching Auto-Trace, we’ve seen a significant shift in how our clients approach investigations. Auto-Trace evolved through multiple phases of prototyping and iteration, tested with investigators at every step. The feature quickly became the go-to starting point for both new and experienced analysts, saving hours of manual work and helping teams focus on what matters most.
Investigation Time Reduced by 85%
Auto-Trace provides us with real time-saving functionality. I have compared this to some live jobs here. It recreated investigations in 10 minutes when it took the investigating officer hours to complete using other tracing software.
Senior Investigator, UK Law Enforcement Agency
Strong enforcement of forward and backward Auto-Trace helped us to create a better analytical framework for blockchain tracing.
Analyst, Federal Financial Enforcement Agency
2. Customer Growth Increased by 30%

3. Adopted as a Screening API
For some of our largest clients in high-security and defense, being able to trace the flow of funds at scale is critical. We delivered Auto-Trace as an API, allowing quickly screen batches of addresses to see where funds came from and where they ended up, especially if they reached the liquidation points.
Future Vision
The story isn’t finished. One of the toughest challenges is still cross-chain tracing, where tokens move across different blockchains. This requires manual handoffs and separate data sources, and building a seamless multi-chain solution is our next frontier.
For me, Auto-Trace shifted how I design complex tools: not just making them faster, but keeping them manageable while ensuring decisions stay clear. As we continue to improve, our vision is to bring Auto-Trace directly into the manual graph experience, so analysts can blend automation with hands-on review in a single workflow.