From Data Flow to Calibrated Intelligence
This is not a market prediction exercise. It is a Scrum exercise. The market is the environment your sprint operates in. The prediction is your sprint increment. The delta is your Sprint Review. The prescription is your Retrospective action item. Every stage maps to a Scrum ceremony — watch for the label at the top of the canvas as you advance.
Click Next ▶ to step through each stage at your own pace. Audio narrates when you advance. Stages 1–8 are core. Stage 9 is a bonus extension for advanced teams.
Use Next ▶ to advance. ◀ Back to review. Click any stage dot to jump directly. 🔊 Audio plays when you advance a stage.
Four Models — One Identical Prompt — What Divergence Reveals
Querying four LLMs with identical inputs is not redundant. Divergence is signal. Agreement is confidence. Understanding why they differ is what separates an intelligent system from a chatbot wrapper.
Strong on narrative synthesis and macro framing. Watch for confident-sounding hallucinations on specific data. Best used for reasoning through scenarios.
Strong on nuanced reasoning, uncertainty acknowledgement, and structured analysis. More likely to flag caveats. Good calibration signal for confidence scoring.
Strong on recency and web-grounded data. May surface recent news others miss. Check for factual grounding and source quality in outputs.
Different training distribution. Useful as a divergence check. When DeepSeek alone disagrees with the other three, investigate why — it may be picking up something different.
What Each Step Looks Like When Automated
| Manual Now (Sprint W3) | Automated in Prism (Future) | Human Role Remaining |
|---|---|---|
| Screenshot Finviz sector map | API call fetches sector data on schedule | Review anomalies flagged by system |
| Write Almanac analysis by hand | Calendar parser + historical pattern DB | Approve or override seasonal weight |
| Run 4 LLM prompts manually | Parallel API calls, auto-saved responses | Review comparison and set weight |
| Build comparison table in Word | Auto-generated agreement matrix | Interpret divergence, apply scepticism |
| R7 lead writes Human Score | Structured input form with guided fields | Wild Card insight — irreplaceable |
| Create GitHub release manually | CI/CD pipeline auto-tags on approval | Final approval click |
| Post Discord submission by hand | Bot posts from template on release trigger | Verify accuracy before send |
Where This Is Heading — The Prism Architecture
Prism (Predictive Reasoning and Intelligence Synthesis for Markets) is Professor Dr. Tan's deployed AI market intelligence platform. It embodies the exact architecture you are learning to specify manually this sprint.
Python Flask serving a FinBERT sentiment model. Market text → structured sentiment signal. This is your "Macro Agent R4" as code.
Interactive candlestick rendering for SPX, NDX, IWM. Visual layer on top of the Technical Agent R5 output.
ChatGPT and DeepSeek panels running identical prompts. The comparison table your R8 operator builds manually — automated.
Architecture Guiding Questions — Sprint Retrospective Prompts
That is your first automation candidate. Define the input, output, and frequency. Write it as a system requirement.
Disagreement zones reveal where human judgement is most valuable and where the system should request escalation.
Current processes that rely on one person knowing something informally are not scalable. Document and systematise them.
Every Almanac, Macro, and Technical output implies a data source. Which ones are missing from your current pipeline?