CP3405 DT3 · System Intelligence Platform
Prof. Dr. Tan · TR2 '26
SPRINT W3 ACTIVE  ·  Submit by Sunday 7 June 2026, 23:59 SGT  ·  Presentations Monday 8 June  ·  Release tag required: vW23  ·  Manual → Structured → Automated → Intelligent
SPRINT W3 · WEEK 23

Weekend Sprint W3 Instructions

No ambiguity: lock the W3 prediction, commit evidence to GitHub, create the correct release tag, and post the submission in Discord before Sunday midnight Singapore time.

What to Submit System Architecture Team Status
PlatformLIVE
SprintW3 / Week 23
Tag RequiredvW23
Teams Active5
LLMs RequiredChatGPT · Claude · Gemini · DeepSeek
DeadlineSun 7 Jun · 23:59 SGT
System Thinking

You Are Building an Intelligence System — Not Completing a Task

"This week, you are doing manually what your future Prism tool should eventually help automate."

Every step you take this weekend — gathering market evidence, comparing four AI models, applying the Human Score, locking predictions, tagging a release — is not busywork. It is a system specification written in human actions. When you feel the friction of manual work, ask yourself:

Why are we doing this manually? What can be automated? What breaks if we scale to 10 teams? Where does human judgement add irreplaceable value?
System Maturity Model — Where Is Your Team?
🛠️
Level 1
Manual
Everything done by hand. No system. High effort, low scale.
📋
Level 2
Structured
Templates, roles, GitHub evidence trail. Repeatable process.
⚙️
Level 3
Automated
Scripts, APIs, scheduled jobs. Human reviews output, not inputs.
🧠
Level 4
Intelligent
AI synthesis, anomaly detection, self-improving predictions. PRISM.
Explore Full System Architecture →

Weekend Sprint Wisdom

Scrum exposes disorder early enough to fix it.
If your team feels confused, that is not necessarily failure. It is information.
Done means evidence exists.
If the work cannot be inspected in GitHub, Discord, FigJam, or the deck, it is not truly visible.
The release tag is your timestamped promise.
A prediction that can be edited after the result is known is not a prediction.
Retrospective is not blame.
It is the disciplined habit of turning frustration into the next process improvement.
Open Scrum Wisdom Archive

The Intelligence Pipeline — W3 Sprint Flow

Every agent and every role maps to a stage in this pipeline. Manual execution this sprint = system design specification for Prism.

📡Data Sources
Finviz · Yahoo
TradingEcon · Charts
→
🔬Agent Analysis
Almanac R3
Macro R4 · Tech R5
→
🤖LLM Synthesis
ChatGPT · Claude
Gemini · DeepSeek
→
🧠Human Score
R7 Override
Wild Card Insight
→
🔒Locked Decision
GitHub vW23
Discord + Deck

Non-negotiable Deadline

Submit by Sunday 7 June 2026, 23:59 Singapore time. This is the work that will be discussed in lecture/practical on Monday 8 June.

1
GitHub evidence committed
Prediction file, evidence folder, model responses, screenshots, and README updated.
2
Release tag created
Required tag: vW23. Not vW22. Not v1.0.0. Not missing.
3
Discord submission posted
Use the exact template below in your team channel before the deadline.
Open Team Status Board

Weekend Workflow — Do This in Order

WhenWhat to doEvidence required
Friday night / Saturday SGTAfter US market close, pull the latest market evidence.Timestamped screenshots or saved links for Finviz 1W, Yahoo sectors 5D, TradingEconomics calendar, and chart evidence.
SaturdayEach agent writes its own output before the team asks the LLMs for synthesis.Separate files/sections for Almanac, Macro, Technical, and Data/Actuals.
Saturday night / SundayRun ChatGPT, Claude, Gemini, and DeepSeek. Compare agreement and disagreement.Raw model responses saved, plus comparison table.
SundayHuman Score lead finalises the team prediction and explains what AI may have missed.Final W3 prediction file with direction/range, confidence, invalidation condition, and reasoning.
Before Sunday 23:59 SGTCommit everything, create release tag vW23, and post Discord submission.GitHub URL, release URL/tag, and Discord post.

Monday 8 June Presentation — Every Role Speaks

RoleWeekend responsibilityMonday speaking point
Product OwnerConfirm sprint goal and Definition of Done.State sprint goal, DoD status, and final W3 call.
Scrum MasterCoordinate deadlines, blockers, and team participation.Retrospective: what failed, improved, and changes next.
Agent LeadsPrepare Almanac, Macro, Technical, Data/Actuals evidence.Explain key evidence and confidence.
LLM OperatorQuery 4 AI models and create comparison table.Explain agreement, disagreement, and credibility.
Human Score LeadLead final judgement and override/confirmation decision.Present Human Score and final prediction.
GitHub LeadCommit evidence and create vW23.Open GitHub live and show release tag.
Full Roles & Responsibilities →

Discord Submission Template

TEAM: Team __ / Practical __
W3 RELEASE TAG: vW23
GITHUB REPO:
RELEASE LINK:
FINAL W3 PREDICTION FILE:
EVIDENCE FOLDER:
POWERPOINT / PRESENTATION FILE:
SPX prediction:
NDX prediction:
IWM prediction:
Confidence level:
Main reason:
Main invalidation condition:
Four AI models used: ChatGPT / Claude / Gemini / DeepSeek
Human Score lead:
Every role ready to speak Monday? Yes / No
Known gaps or blockers:

Current Risk Reminders

All teams: W3 release tag must be vW23. A tag from W2 is not sufficient.
Team 3: Discord activity is strong, but FigJam audit shows the board is effectively unfilled. Fix the thinking wall before Monday.
Team 5: Low Discord, no release tag, and mostly unfilled FigJam. Urgent intervention needed.
Team 4: Strong FigJam, but wrong release tag was previously observed. Correct to vW23.