Helping internal teams understand high-level information from piles of documentation and search contextually using AI
Turning a fragmented, months-long due-diligence process into a transparent GenAI research workflow built on trust and visibility.
marsh.ratesense.com
My Dashboard
Back
Source Library
Report
Chapters
Sources(4)
Executive Summary
Key Findings
Summary
Takeaway
Researcherโs Findings
Summary
Key Takeaway
JPM Equity Strategy Research View
Draft
Last saved: 2:35 PM on October 11, 2025
Share
Export
16
Inspect
Research Report
JPM Equity Strategy Research View
Key takeaways
by AI
Doc
2 Sources
Score
20 Oct 2025
Pros:
The team of experienced investment professionals has worked together for many years and displays a high level of commitment to the approach.
by
18 Oct 2025
It is the methodical and detailed due diligence that differentiates the strategy with each step of the process reflecting a significant amount of thought.
by AI
1 Sources
Score
20 Oct 2025
The devilโs advocate process at the stock-selection stage of the process ensures robust challenge.
by AI
Doc
2 Sources
Score
20 Oct 2025
The team applies sensible screens in order to narrow the universe to a limited set of ideas warranting further due diligence. The requirement of specific reasons why ideas screening well are not progressed fosters objectivity.
by
18 Oct 2025
There is a strong desire for continuous improvement and refinement of the process, with regular off-site meetings and a willingness to improve the decision-making process.
by
18 Oct 2025
Cons:
The balance of power in investment decisions does seem to lie in Dalgasโ hands and we view him as the guardian of the approach. Although low, there is an element of key-man risk in the strategy. Similarly, we would review the rating if Ingemann left.
by AI
Doc
1 Sources
Score
20 Oct 2025
Add
AI Companion
Insights
Citations
Confidence Score
Version History
Search
Based on recent audit, 87% of the team are experienced investment professionals that has worked together for many years and displays a high level of commitment to the approach.
DOC
Financial Reports.docx
Page 14. Paragraph 3
The balance of power in investment decisions does seem to lie in Dalgasโ hands and we view him as the guardian of the approach. Although low, there is an element of key-man risk in the strategy. Similarly, we would review the rating if Ingemann left.
Portfolio Holdings.PDF
Uploaded: 20 Jan, 2026
Client
Project category
0-1, Internal Tool
Timeline
8 Months
Team
2 PMs
Design Lead
Product Designer (Thatโs me ๐)
GenAI Engineers
UI Developers
Business Analyst
TL;DR:
Marsh, a Fortune 500 asset and wealth management firm, relies on researchers to produce investment and operational due diligence reports on asset managers, structured, compliance grade documents that must clear legal and compliance review before a client ever sees them. Marsh wanted to accelerate due-diligence process using AI.
Existing AI workarounds were not built for this. Producing one of these reports meant working across three disconnected platforms with no shared source of truth, manually extracting and synthesizing factual information from dozens of documents, then adding researcher narration on top. Nobody could tell what was written by a person versus generated by AI, and citations could not be checked making it difficult to trust the output.
RateSense unifies that fragmented workflow into one AI-assisted platform, keeping a human in the loop. RateSense generates the report with clear attribution (written by AI or a researcher), citations tagged against every fact, and a confidence score that gives complete transparency. This meant researchers were able to easily generate and validate AI-generated reports, improving report turnaround from 6 to 8 weeks to 1 to 2 days.
My Contribution
Owned the 0-1 UX design for RateSense,
from discovery through shipped delivery.
Discovery workshops with 15 SMEs.
Synthesized findings into a future-state service map unifying 3 fragmented legacy platforms and where AI could take over.
Partnered with 3 Gen-AI Engineers
to design 5 human-in-the-loop features behind the AI-Report creation: Attribution, citations, and confidence scoring.
Design & Shipped 2 end-to-end flows
Demoed the platform to senior leadership, including global managers, to secure buy-in for broader rollout
A peak into my Design file: Hereโs what & how I shipped this project!
๐
A Sneak peak
The Problem
For a compliance-driven report, trust cannot be assumed.
Lack of Verifiability
Researchers had little to no trust because a single unverified A.I generated claim isnโt an inconvenience.
Itโs a compliance risk!
This is an example from a well-known app
Invisible authorship
Finished report reads as one voice, with nothing on the page showing weather something is written by A.I or human. Which matters most during an audit.
by AI?
by a Researcher??
Lack of control
ChatGPT, Claude etc. are general-purpose AI assistants, Not made for iterative workflows. Researchers were stuck switching between A.I and word just to improve content for a portion of the report
The Solution
Unifying 3 disconnected platforms into an AI-assisted workflow. Every source gets pulled into Source library, and a report can be generated directly into Marshโs standard template
Play
Play
Inspect Mode and Citations
Clicking into Inspect Mode surfaces all the meta-data behind a claim, along with a citation, confidence score covering language, tone, and how reliable that source actually is.
How this solves the problem
This gives a compliance reviewer exactly what the invisible authorship problem was missing: a clear, immediate answer to who wrote a given line.
Attribution
Hovering over any line shows whether AI wrote it or a person did. The distinction that used to be invisible across the whole report is now visible one hover at a time.
How this solves the problem
This adds a trust and transparency layer on top of the report. A claim is never just asserted, All the metadata is shown
Play
Inline editing and versioning
Iterate the AI-generated content without losing context generate multiple versions of the reports
Play
Select any part of the report, give it a quick instruction, and it updates in place. No full reprompt required.
Play
Lock a section and then regenerate the rest of the report from new documents without touching what is already approved.
Impact
RateSense turned a 6-to-8-week manual process
into a 1-to-2-day AI-assisted workflow
Pilot Adoption Rate (n=50)
Before company wide-roll out
Faster report generation
Compared to Industry standard AI tools
User satisfaction Metrics
20% Increase after iterations
This deep dive is classified.
Meet me for coffee and Iโll slide a briefcase full of secrets across the table!
Hereโs whatโs inside(Pun intented):
Business Goal
Develop a Minimum Viable Product (MVP) that provides hyper-personalized travel experiences, leading to higher user acquisition and potential monetization opportunities
My Personal Challenge
Unfortunately, We didnโt have direct access to end user until later in project!
My work around
No collaborative AI-powered trip planner that helps groups coordinate plans seamlessly.
Key Partnerships
Travel booking platforms: Hotels (Booking.com, Expedia, Agoda)
Flights (Skyscanner, Kayak API)
Tours (basic partnerships for experiences)
AI/ML tech providers (OpenAI, Llama for route personalization).
Influencers for early beta testing & launch push.
Key Activities
Travel booking platforms: Hotels (Booking.com, Expedia, Agoda)
Great for itinerary organization
Great for itinerary organization
Customer Relationships
Optional personalization adjustments to fine-tune profile over time.
"Smart match" system recommending trips based on user's evolving personality
Channels
Mobile App (Primary) โ iOS & Android (direct download).
Customer Segments
Frequent travelers (both leisure & business) looking for quick trip curation.
Millennials and Gen Z travelers who prefer personalized, plans.
First-time travelers seeking simple and fast itinerary solutions.
Small groups & solo travelers needing flexible planning.
Occasional travelers who want easy plug-and-play trips without research.
Great for itinerary organization
Great for itinerary organization
Timothy
Chandan
Business Model Canvas
Chandan Jonnavithula
2025ยฉ