World Business StrategiesServing the Global Financial Community since 2000

The half day workshop on Wednesday 24th September is complimentary to all delegates: 13.45 – 17.15

13.45 - 17.15
Using Behavioural Psychology to Design Reliable AI Workflows

Like humans, AI produces results that vary from one attempt to the next and sometimes makes mistakes. This does not stop us from relying on humans, and it should not stop us from relying on AI.

The key to successful AI-based workflows is setting them up in a way that would help a human succeed at the same task. During this workshop, we will leverage this insight to build reliable AI-based workflows for several important use cases in trading and risk management.

Session 1 – Theory

  • Getting AI to Think Slow
    • Activating Kahneman’s System 2 and Suppressing System 1 in AI
    • The Role of Response Sequencing and Verbosity
    • Chain of Thought (CoT) and Tree of Thought (ToT) Prompting
    • Using Reasoning Models Effectively
  • Avoiding Psychological Effects and Cognitive Biases
    • Reference Point Framing and Informational Anchoring
    • Priming-Induced Anchoring
    • Associative Coherence and Halo Effect
    • Acquiescence Bias and Sycophancy
  • Reducing Noise in Scoring and Other Subjective Measures
    • Confirmation Bias
    • Availability Bias and Intensity Matching
    • Crowdsourcing
    • From Scoring to Ranking

Session 2 – Practice

We will use insights from behavioral psychology to improve the reliability of AI for several important use cases in the financial industry.

  • Credit analysis
  • Security prospectus compliance analysis

Session 1: 13.45 – 15.15
Coffee Break: 15.15 – 15.30
Session 2: 15.30 – 17.00
Q&A: 17.00 – 17.15

Alexander Sokol:

Executive Chairman and Head of Quant Research, CompatibL

13.45 - 17.15
LLM Finance Agents: From Core Concepts to Advanced LangGraph Workflows

Part Duration Focus Topics & Activities

  1. Foundations 0 h – 1 h Basics • Why use coding agents in finance (use-cases & constraints)
  • E2B architecture essentials: sandboxed runtimes, tool wrapping, API keys
  • Live demo: building a single-step “quote-fetch” agent with E2B + OpenAI
  • Hands-on exercise: add logging & basic error handling
  1. Building Capability 1 h – 2 h Intermediate
  • Agent loops: planning → execute → reflect Persisting state: lightweight memory stores for trade context
  • Integrating a vector DB (FAISS/Chroma) for research recall
  • Workshop lab: create a portfolio-rebalancing agent with risk checks
  1. Advanced Showcase 2 h – 3 h Advanced Example
  • Intro to LangGraph for multi-step orchestration
  • Designing a compliance gate graph around the rebalancing agent
  • Multi-agent pattern: Data Gatherer → Risk Analyst → Trader
  • End-to-end walkthrough & performance discussion

Session 1: 13.45 – 15.15
Coffee Break: 15.15 – 15.30
Session 2: 15.30 – 17.00
Q&A: 17.00 – 17.15

David Pacheco Aznar:

Founding Partner & Chief of AI Research and Development, Raven Risk AI

  • Discount Structure
  • Special Offer
    When two colleagues attend the 3rd goes free!

  • 70% Academic Discount
    (FULL-TIME Students Only)

Download Event PDF

Please enter your details to download this PDF

Error

Event Email Reminder

Error