3×
faster portfolio risk analysis
Real-Time Portfolio Intelligence Platform for SAMCo
SAMCo
Real-time
Risk analysis (was 24hr lag)
3hr
Daily time saved per manager
$2B+
AUM on platform
8wks
Scoping to live
Context
The business context
Asset management is a business where timing is everything. SAMCo's analysts were skilled and experienced - but they were making portfolio decisions with information that was, at best, 24 hours old. Overnight batch jobs, Excel risk models maintained by a single analyst, and data silos across trading, compliance, and portfolio systems meant that by the time a risk report reached a portfolio manager's desk, the market had moved. In volatile conditions, a 24-hour lag isn't just inefficiency - it's exposure.
The problem
5 specific problems that needed solving
Overnight batch jobs meant risk analysis was always 24 hours stale - unacceptable during high-volatility market periods
A single analyst maintained the core Excel risk model, creating a critical dependency and a 3-hour update cycle for any model change
Risk data siloed across four separate systems: trading platform, Bloomberg terminal, compliance database, and internal analytics
Portfolio managers spent an average of 3 hours per day extracting, consolidating, and formatting data before they could begin analysis
No natural language interface - every query required technical SQL knowledge or waiting for the analytics team
Our approach
Real-time is a systems problem, not a UI problem.
The temptation in projects like this is to build a better dashboard. We spent the first sprint mapping exactly where the latency lived - and most of it was in the data pipeline, not the reporting layer. Overnight batch jobs were running because the previous architecture couldn't support live queries across four data sources simultaneously. We re-architected the data layer with a streaming pipeline before touching a single user-facing component. The natural language interface came last - built on top of a foundation that could actually support real-time responses.
Streaming data pipeline built before any UI work - real-time is a data architecture problem first
Natural language queries backed by traceable reasoning: every answer cites the specific data points it used
Alert system designed around portfolio manager workflows, not technical data events
Model architecture documented and explainable - compliance team can audit every AI-generated risk assessment
What we built
A live intelligence layer across SAMCo's entire data estate
The platform combines a real-time streaming pipeline with a GPT-4o powered query interface. WebSocket connections maintain live feeds from Bloomberg, the internal trading platform, and the compliance database. A custom risk model - co-designed with SAMCo's head of risk - runs continuously over the live data, updating exposure calculations every 60 seconds. Portfolio managers interact with the system through a natural language interface: they ask questions in plain English and get structured answers with the underlying data exposed for inspection. The system also runs a configurable alert engine that triggers on user-defined risk thresholds.
Streaming data pipeline
Real-time WebSocket connections to Bloomberg API, the internal trading platform, and the compliance database. Position and pricing data updates every 60 seconds. Historical data is preserved in PostgreSQL for trend analysis and backtesting.
AI risk model
A custom risk model trained on SAMCo's portfolio history, co-designed with the head of risk. Runs on live position data to produce VaR estimates, currency exposure summaries, and sector concentration metrics - updating continuously rather than nightly.
Natural language query interface
GPT-4o powered query interface grounded in live portfolio data. Queries like 'What is my USD exposure if the dollar moves 2% against INR?' return a structured answer with the calculation methodology, data sources, and confidence range.
Configurable alert engine
Portfolio managers define risk thresholds (e.g. 'alert me if tech sector exposure exceeds 30%') and receive push notifications the moment live data crosses the threshold - replacing the previous end-of-day email digest.
Compliance audit trail
Every AI-generated insight, alert trigger, and query response is logged with the underlying data snapshot, model version, and timestamp. SAMCo's compliance team can reconstruct the exact information state at any moment a decision was made.
Impact
What changed in production
The technical metrics tell one story. The operational shift - from reactive risk management to proactive, real-time intelligence - tells a bigger one.
24-hour batch lag eliminated. Portfolio managers save 3 hours per day. Platform handles $2B+ AUM with full audit trails on every AI-generated insight.
Real-time
Risk analysis (was 24hr lag)
3hr
Daily time saved per manager
$2B+
AUM on platform
8wks
Scoping to live
“We used to brief portfolio managers with yesterday's numbers. Now they get real-time answers to questions they didn't even know to ask. The natural language interface has changed how our entire team thinks about data.”
Chief Technology Officer
Chief Technology Officer - SAMCo
Learnings
What we took away from this project
Real-time financial data requires obsessive error handling
Live market data is messy. Bloomberg feeds drop out. Internal systems have maintenance windows. Position data can arrive out of sequence. We spent significant engineering time on fallback states, data staleness indicators, and graceful degradation - so the platform always communicates clearly when data is fresh versus cached, rather than silently serving stale information as if it were live.
Natural language queries need strong output structure
Free-form natural language responses in a financial context are a liability. Portfolio managers need structured, scannable answers - not prose. We designed a strict output schema with a direct answer, supporting data table, methodology note, and confidence indicator. This also made it easier to validate outputs programmatically before serving them.
The analytics team needs to trust the AI before the managers do
The biggest adoption barrier wasn't portfolio managers - it was the existing analytics team who feared the system made their role redundant. We repositioned their role explicitly as 'model owners and validators': they define the risk parameters, review model outputs weekly, and own the alert threshold configurations. This turned the team from sceptics into champions.
3×
faster portfolio risk analysis
At a glance
Tech stack
Capabilities
Build something similar?
We've solved this category of problem before. Let's scope yours.
Start a conversation View related serviceMore work
