AI Agent Use Cases
Views —

AI Agent Use Cases

Added today

11All 202

Trying Codex Automated QA for a Flutter App

The author reports that after integrating Codex automated QA into a Flutter app under development, slow tests and unintended changes to features became problems.

Codex
Dev

Making a 3D Cube Net App for Children's Math Study

Grok Bot reportedly created a 3D app where children can fold all 11 cube nets from their textbooks, which are usually shown only as flat diagrams, using their fingers.

Grok Bot
Learning & Careers

1–20 of 202

Work & Research

Agent for Early Detection and Scenario Analysis of National Crisis in Indonesia

The author reports monitoring Indonesia's macroeconomic risk signals using 13 modules and automatically analyzing the impact of different crisis scenarios.

Claude Code

How it works

  1. The author installs the agent framework and downloads code forked specifically for Indonesia.
  2. They run 13 macroeconomic modules in parallel (including trade balance, foreign exchange defense, banking/market/fiscal stress, and political/social risks).
  3. For each module, they collect real-time data (such as exchange rates, CDS, government bond yields, foreign capital flows, commodity prices, and political news).
  4. They aggregate risk signals from each module to calculate the Silent Crisis Probability (0–100%) and Synthetic Stability Score.
  5. The system automatically displays early crisis warnings (RED/ORANGE/YELLOW/GREEN) and indicates when key thresholds are breached.
  6. It incorporates risk assessment indicators based on international macroeconomic theories such as KLR EWS, IMF FSAP, and R&R.
  7. The author simulates crisis scenarios (e.g., sharp exchange rate fluctuations, interest rate hikes, foreign capital outflows) via command line or agent skills.
  8. For each scenario, the system compares changes in risk scores, transmission paths, and major alerts across modules.

Results

The author reports that the output summarizes the overall crisis probability, risk scores by module, key threshold breaches, and crisis transmission details in tables and narrative form. For example, after an MSCI market downgrade announcement, the foreign exchange, fiscal, and political modules simultaneously switched to RED, and the crisis probability surged from 24% to 85%.

Notes

The author notes that actual data collection and scenario execution can be checked via command line scripts or agent skills. Additional configuration may be required for linking external APIs, real-time data, or manual input of policy variables, depending on the environment. The system's crisis thresholds and signal interpretation criteria are reportedly based on international macroeconomic theory.

Source

uradn/dex_indonesia (GitHub) Original post ↗

Example prompt · Claude Code

[Goal] Automate early detection of Indonesia's national macroeconomic crisis and impact analysis by crisis scenario.

[Input] Enter real-time or latest public data (exchange rates, CDS, government bond yields, foreign exchange reserves, trade balance, foreign capital flows, commodity prices, banking soundness indicators, political/social news) or connect via API. Crisis scenarios (e.g., sharp exchange rate fluctuations, interest rate hikes, foreign capital outflows, commodity price spikes) can be selected from predefined presets or specified directly.

[Environment] Use a Claude Code-based agent framework and fork the dex_indonesia repository to activate Indonesia-specific modules. Prepare an environment that supports external data integration, command line execution, and agent skill invocation.

[Implementation Steps]
1. Fork the dex_indonesia repository and install dependencies.
2. Activate 13 macroeconomic modules (trade balance, foreign exchange defense, banking/market/fiscal stress, political/social risks, etc.).
3. Collect and integrate real-time or latest data for each module (configure API keys, manual input, etc. as appropriate).
4. Set up automatic calculation of overall risk indicators such as Silent Crisis Probability and Synthetic Stability Score.
5. Enable automatic alerts for crisis thresholds (RED/ORANGE/YELLOW/GREEN) and major warning events.
6. Incorporate risk assessment indicators based on international macroeconomic theories such as KLR EWS, IMF FSAP, and R&R.
7. Run stress tests for each crisis scenario (e.g., 'crisis', 'idr-freefall', 'china-slowdown') via command line or agent skills.
8. For each scenario, output a summary table and narrative of changes in module risk scores, Silent Crisis Probability, and key threshold breaches.
9. Provide key signals, transmission paths, and policy implications for human review.

[Deliverable] Generate a report summarizing overall crisis probability, risk scores by module, threshold breaches, and crisis transmission details in tables and narrative. For example, after an MSCI market downgrade announcement, the system should be able to reproduce a scenario where the foreign exchange, fiscal, and political modules simultaneously switch to RED and the crisis probability jumps from 24% to 85%.

[Verification Criteria] Check that actual data and scenario results are consistently reflected, that key threshold breaches and alerts are accurately displayed, and that policy implications are easy for humans to interpret.