#Risk

Articles about Risk — exploring patterns, best practices, and real-world implementations in production systems.

13 posts tagged with risk. ← All posts

#A2A (5)#ADK (8)#AG-UI (7)#AI Agents (244)#AI Governance (7)#AML (3)#Accounting (9)#Agent Skills (3)#Agentic AI (23)#Agentic Commerce (12)#Agents (4)#Architecture (22)#Audit (3)#Azure (11)#Azure AI Foundry (10)#BigQuery (6)#Capital Markets (8)#Cards (13)#Checkpointing (5)#Cloud Architecture (3)#Compliance (30)#Concurrency (4)#Context Providers (3)#Conversation State (3)#Cost Optimisation (5)#Credit (14)#Crypto (12)#Custody (9)#Distributed Systems (3)#Engineering (7)#Evaluation (5)#FREE-AI (8)#FX (5)#FinOps (5)#FinTech (6)#Financial AI (14)#Fintech (116)#Fraud (10)#Function Tools (6)#GCP (5)#Go (168)#Google ADK (26)#Governance (5)#Guardrails (7)#HIPAA (3)#Harness Engineering (8)#Human-in-the-Loop (7)#KYC (11)#Kubernetes (6)#LLM (4)#LangGraph (11)#Ledger (12)#Lending (14)#MCP (5)#Machine Learning (12)#Markets (4)#Memory (5)#Microsoft Agent Framework (211)#Middleware (9)#Multi-Agent (8)#Multi-Agent AI (14)#Multimodal (4)#Observability (14)#Open Source (6)#OpenTelemetry (5)#Opinion (6)#Orchestration (15)#Payments (49)#Privacy Engineering (3)#Providers (3)#Python (127)#RAG (6)#RBI (3)#Rails (16)#Reconciliation (3)#Regulation (8)#Reliability (15)#Retrieval (3)#Risk (13)#SRE (3)#Security (24)#Sessions (4)#Settlement (9)#Spanner (4)#Streaming (4)#Structured Output (4)#Testing (6)#Trading (8)#Treasury (5)#Workflows (15)
Pratik Dhanave · ·6 min read

Why Machine Learning in Finance Is Different

Financial ML lives under regulators, adversaries, and money-denominated errors — so you design backward from a business metric, not forward from a model.

What sets financial ML apart from general ML: strict regulatory scrutiny and mandatory explainability, high-stakes and immediately quantifiable errors, messy multi-source data, non-stationarity, and adversarial actors.

#Financial AI#Machine Learning#Compliance#Risk
Pratik Dhanave · ·7 min read

Graph-Based Fraud Ring Detection

Why per-transaction scoring misses organized fraud, and how modeling accounts, devices, cards, addresses, and IPs as a graph catches the whole ring.

Modeling accounts/devices/payments as a graph, connected-component and community detection, shared-attribute linking, and analyst review.

#Fintech#Fraud#Risk#Data
Pratik Dhanave · ·6 min read

Rules and ML in One Fraud Decision Path

How to combine a deterministic rules engine with an ML risk model in a single decision: rule precedence, score bands, shadow mode, and champion/challenger evaluation with feedback labels.

Teaches how to combine a deterministic rules engine with an ML risk model in one decision path: rule-precedence and overrides, model score bands, shadow mode, and champion/challenger evaluation with feedback labels.

#Fintech#Fraud#Risk
Pratik Dhanave · ·6 min read

Building a Step-Up Authentication Orchestrator

How a risk-driven layer escalates from silent approval to OTP, biometric, or 3DS challenge — holding a pending-challenge state and resuming the original transaction once the customer clears it.

Teaches how to build risk-based step-up auth: an orchestration layer that escalates from silent to OTP/biometric/3DS challenge based on risk signals, with pending-challenge state and resumable transaction context.

#Fintech#Fraud#Risk
Pratik Dhanave · ·6 min read

Real-Time Velocity Checks and the Fraud Feature Store

Building low-latency sliding-window counters, entity-keyed aggregates, and an online feature store that stays consistent with its batch-computed twin.

Teaches how to build low-latency velocity checks: sliding-window counters and aggregates in an online feature store, entity keys (card/device/IP), and consistency between real-time and batch-computed features.

#Fintech#Fraud#Risk
Pratik Dhanave · ·7 min read

"My Agent Did It": Fraud, Disputes, and Liability in Agentic Commerce

When software holds the card and clicks "buy," the old questions — was this the cardholder, did they mean to, who pays if not — all get harder to answer.

The new fraud surface: prompt injection turning a shopping agent into an attacker's buyer, hijacked delegated credentials (Visa saw ~450% more dark-web 'AI Agent' chatter in H1 2026), and disputes when an agent acted on…

#Agentic Commerce#Fraud#Risk#Compliance

All posts on this site are written by Pratik Dhanave, an Agentic AI Architect with 7+ years building production distributed systems, multi-agent AI platforms, and cloud-native infrastructure. About the author → Each article includes working code, architecture diagrams, and references to the specific frameworks and standards discussed. Browse all posts or explore related topics using the tag cloud above.