cleopatra douglas

Build Fintech AI Systems That Actually Ship

Goldman Sachs

Flutterwave

GUARANTY Trust Bank

Cleopatra Douglas

CEO & Co-Founder, Recital Finance | ex @ Goldman Sachs, Flutterwave (YC Unicorn)

Identify the 3 architectural mistakes that kill fintech AI projects, and the decision patterns that prevent them.

Why fintech AI projects fail before production

You'll see a real reconciliation agent in action and understand how to structure autonomous workflows around messy data

How to design an agentic workflow for financial data

Leave with a checklist covering observability, ML lifecycle, and the guardrails that separate demos from shipped systems

The production checklist nobody teaches you

Lead AI initiatives with clear goals, defensible evaluation, explicit risk decisions, and exec updates that drive alignment and investment.

CPO, GM xBraintrust, Nextdoor, OpenTable

Braintrust 🧠

Nextdoor

LiquidSpace I Work from where it works.

OpenTable

BlackRock

Elena Luneva

f-CPO. Product executive (Braintrust, Nextdoor, OpenTable, LiquidSpace)

Ex-Alexa AI Principal PM

Amazon

Elsevier

Schneider Electric

Polly Allen

Ex-Alexa AI PM turned founder at AI Career Boost

Magic

Juggernauts

AI increases what your ICs can do. It also breaks the management systems most teams rely on.Prototypes multiply. Quality becomes subjective. Risk ships quietly. You end up in every review because no one is sure what "good" looks like — or who's accountable for evals, failure modes, and rollout decisions.If you're a Director, Head of Product, or VP with multiple AI initiatives in flight: you're managing something you didn't build a system for yet. Execs keep asking "How do we know it's good?" and "What's the ROI?" — and you're the one fielding it.This two-day workshop gives you the operating system. Not theory. Not frameworks. The actual playbooks, artifacts, and rituals high-performing, AI-native teams use — built during the workshop so you leave with real deliverables, not homework.Leave with:1. A 90-day AI portfolio — clear bets, owners, and decision gates so nothing gets orphaned2. A repeatable risk review process your team can run without pulling you in3. A shared quality bar — examples, acceptance criteria, and review gates so "is this good enough?" stops being a judgment call4. Reusable operating artifacts built during the workshop — actual deliverables, not slides

Get the operating system used by high-performing AI-native teams

Install an AI-native operating cadence that keeps speed and alignment

Run AI risk reviews that drive decisions and confidence

Own and drive evaluation metrics and process, before and after launch

Implement playbooks that let your team move with you, not wait for you

Director/Head of Product: Leads AI initiatives; turns prototypes into production with clear quality, gates, and exec updates.

Eng leader (Sr Mgr/Dir/VP): Ships AI fast while managing reliability, security, and cost with consistent eval + risk reviews.

Data/ML leader (Dir/Head): Owns evals and performance; aligns product and execs with shared language and decision-ready tradeoffs.

Your AI agent works in demos. But Production isn't one.

Principal Consultant. MD @ Datawhistl

Tata Consultancy Services

Wipro

Serco Group

Dheeraj Saxena

Ex-IBM, TCS, Wipro Consultant. | 25+ Years Scaling Data, AI & MarTech Solutions

Cohort 4

📉 Most production deployments underperform or fail — <a target="_blank" rel="noopener noreferrer nofollow" href="https://www.gartner.com/en/newsroom/press-releases/2025-06-25-gartner-predicts-over-40-percent-of-agentic-ai-projects-will-be-canceled-by-end-of-2027">Gartner expects over 40% of agentic AI projects to be cancelled by 2027</a>. The velocity that Claude Code and Cursor give developers in the sandbox quietly hides architectural debt that production exposes the moment the agent meets real customers, real data, and real regulators. The cause is rarely the LLM call — it's the workflow architecture around it.🏛️ Frameworks like <a target="_blank" rel="noopener noreferrer nofollow" href="https://docs.aws.amazon.com/wellarchitected/latest/generative-ai-lens/generative-ai-lens.html">AWS's Well-Architected Generative AI Lens</a> stop at defining best practices but completely lack the specificity required to prevent production failures.⚖️ Governance standards like <a target="_blank" rel="noopener noreferrer nofollow" href="https://iapp.org/certify/aigp">AIGP</a> focus on control rather than engineering patterns and lack practical actionability for the engineering team.This workshop closes that gap.Using real case studies, you'll learn how to identify and apply AI architecture principles to design agents that survive contact with reality — real customers, real data, and real regulators. And do so in a repeatable, auditable manner across your entire Agentic AI project portfolio.

From flaky sandbox demos to consistent business value. Proven, structured techniques to architect agentic AI systems in production.

What AI architecture principles are

What happens if you do not use architecture principles

Alignment with AWS Well-architected-framework/GenAI Lens

How to enforce principles through governance and CI/CD pipelines

Step-by-step framework to help you decide which principles you need

what they automate, what they decide, what's being deployed where. You don't need to code them; you do need to understand them.

Business understanding of AI agents and what they do in enterprises

Senior Developers who are responsible for building production-grade Agentic AI workflows.

AI Governance &amp; Risk Professionals translating governance policy into architecture decisions that engineers can actually build against.

Business Heads/Project Managers accountable for AI initiatives and who need to understand architecture challenges without getting into code.

Go from building agent demos to shipping production-grade agent systems with the eval rigor, guardrails, and judgment real teams rely on.

GP, Musa Capital · ex-Microsoft operator

Microsoft

LinkedIn

Productiv

Musa Venture Collective

Allen Smith

General Partner, Musa Capital (ex-Microsoft, NFL, Stanford)

Cohort 1 — Summer 2026

There's a canyon between an agent that works in your notebook and one that survives real users, real edge cases, and real money on the line. You've felt it: the demo lands, everyone's excited — then it breaks the moment it hits production, and nobody quite knows why.Crossing that canyon is the single most valuable skill in AI right now. And almost nobody teaches it, because almost nobody has shipped it.Over six weeks, you'll build a production-grade agent system end to end — architecture, tool orchestration, memory, evaluation harnesses, guardrails, deployment. Not a toy. Your own real project, the kind you can demo to a hiring manager, a CTO, or an investor.What makes this different: you're learning from an active investor and former big-tech operator who builds agentic systems as part of how Musa Capital develops its thesis. Not theory from someone who read the papers — the patterns that separate funded companies from prototypes.You'll leave with a system that ships, an eval discipline most teams never build, and the judgment to know what's actually production-ready.

Go from AI demos that impress to agent systems that survive production

Design agent architectures that survive real-world complexity

Build reliable tool use and orchestration

Implement memory and state for long-horizon tasks

Build eval harnesses that catch failures before users do

Add guardrails, governance, and human-in-the-loop control

Deploy, monitor, and position agentic products

Technical Founders — shipping agentic features and need production patterns that scale beyond the demo.

Engineers &amp; Eng Leads — building with LLMs at companies and need governance, eval, and deployment rigor.

Technical PMs — scoping production-grade agents and need to speak the language of what's actually possible.

You leave with deployable systems and documented architecture — not slide decks.

AI & DeepTech Leader & Entrepreneur

Hike

Yatra

Apparel Group

Oracle

Bytelearn

Dr Ankur Narang

Three decades building HPC and AI systems processing billions of transactions

Enterprise AI Agent Architect

Adda247

Mobileum

Kush Khurana

AI product and deep-tech builder, Visiting Professor at Ashoka University

AI Systems Architect & Leader

Stryker

Samsung

Dr Aveek Brahmachari

Stryker Senior Staff Engineer; IIT-ISM, USF PhD; ex-DRDO, Samsung

Founding Cohort

A 4-week intensive for engineers mastering autonomous cognitive workflows — from cost compression and self-correcting loops to revenue-scaling agents that turn AI from a cost center into a profit driver.<a target="_blank" rel="noopener noreferrer nofollow" href="https://deepcorexlabs.com/courses/production-ai-agents">Course Webpage</a>Build The Economic Engine of Agents: This goes beyond the technical deep-dive. We focus exclusively on production-grade impact—engineering the measurable business outcomes that deliver exponential ROI.20x ROI via Cost CompressionAchieve 20x return on investment by reducing operational overhead — replacing manual human-in-the-loop processes with self-correcting agentic loops.100x ROI via Revenue ScalingUnlock up to 100x return on investment by deploying agents that solve high-intent, real-time use cases — turning AI from a cost center into a primary profit driver.Achieve 5–10x lower AI infrastructure costsToken routing, caching, and cost modeling that saves six figures at scale.Systematic evaluation capabilityInternal eval infrastructure — catch regressions before users do.De-risked architecture decisionsBuild-vs-buy calls backed by production data, not vendor pitch decks.Reusable patterns across teamsOne cohort creates blueprints your entire engineering org can adopt.

Deploy Agentic systems that deliver 20x–100x return on investment.

Ship a functioning agent with structured tool use and state management.

Ship a retrieval pipeline that's grounded, verified, and citation-backed.

Ship cost controls and failure recovery into your agent.

Ship your capstone with full eval harness and deployment pipeline.

<h3>Engineering &amp; Product Leaders</h3>Responsible for shipping AI features. Need production patterns beyond prompt engineering and API wrappers.

<h3>Technical Founders &amp; CTOs</h3>Built the prototype yourself. Need it reliable enough for paying customers and investor due diligence.

<h3>Lead Developers</h3>You're the person who makes the AI system actually work — and keeps it working when inputs get messy.

Agentic AI

Coding with AI

AI Workflows

Claude Code

OpenClaw

Vibe Coding

AI Evals

AI Transformation

RAG & Search

AI for PMs

AI for Engineers

AI for Designers

AI for Marketers

AI for Founders

Product Sense

Product Discovery

User Research

Prototyping

Growth

Analytics

Tech Foundations

Strategy

Influence

Leadership

Career Growth

Machine Learning

LLM Ops

Context Eng

Security

System Design

Figma

Design Systems

Visual Design

Design Strategy

Automation

Content Marketing

Demand Gen

Go-to-Market

Product Marketing

Positioning

Social Media

Brand

B2B Marketing

SEO & AEO

AI for Leaders

AI Governance

Communication

Management

People Operations

Exec Presence

Storytelling

Goal-setting

Personal Brand

Fundraising

Everyone

Operators

Data Scientists

Business Analysts

User Researchers

Customer Success

Project Managers

HR Professionals

Sales People

Lawyers

Finance

Investors

Real Estate

Educators

Creators

Engineers and engineering leaders who build, deploy, and scale software systems.

Applying AI tools and techniques to professional workflows — assign alongside more specific AI topics.

Build Fintech AI Systems That Actually Ship

What you'll learn

Why this topic matters

You'll learn from

Cleopatra Douglas