Chew Ming Yau@Roycen

The problem Code reaches human reviewers with problems a machine could have caught: a crash on a missing field, new behaviour with no test, API docs that no longer match the code. Reviewers rebuild the context, leave routine comments, and the review loop starts again. Tests alone don't catch this: in our sample change all 22 existing tests pass while a request without one field crashes with an HTTP 500. And AI review tools that simply say "looks good" give opinions without evidence, so teams can't trust them with the decision. Our solution PRism AI checks code before it goes to review. One command, or one question in chat, snapshots the change and sends it to three AI specialists in parallel: code review, testing and documentation, each with its own instructions. The project's real test suite runs on a copy of the code, and pass/fail counts come from the test runner, never from the AI. Every AI answer is validated against a JSON schema; an invalid answer gets one automatic repair, then counts as an error, never as a pass. Finally, fixed rules in policy.json decide the verdict: READY FOR HUMAN REVIEW, ATTENTION REQUIRED or VERIFICATION FAILED. It never says "approved". A human always makes the merge. Who it is for and how they use it Developers who want a check before asking for review, reviewers who want evidence instead of opinions, and teams who want AI help without giving AI the final say. Type prismai in any project folder and ask "analyse this project and give me a report", then follow up with "explain the bug in shipping.py and show me the fix". It also runs as a single command on any folder, a git commit, before/after folders or a patch file, re-checks on every save in watch mode, and returns exit codes that a CI job can use. It works with any OpenAI- or Anthropic-compatible AI provider. What makes it different The AI finds the problems; deterministic code decides. Every finding carries a file, a line, quoted evidence and a fix. Large projects get a two-pass review, a free code map and then AI summaries with a risk score, so every AI call fits the model's limit. A memory re-checks unchanged code in about one second with zero AI calls, and before/after tracking shows exactly what a fix resolved. Results On a messy 117-file demo project with 10 planted bugs, one check found all 10 in 26 seconds, led by a critical SQL injection. On our sample app it found all 5 planted problems while every test passed, stayed at READY FOR HUMAN REVIEW on a clean control change, and caught a held-out bug that the prompts were never tuned on. About 458 automated tests cover the pipeline and run without any AI key.

I use 3 layer hybrid architecture to handle both structured and unstructured data: Layer 1: Data Acquisition (Custom Skills): We built OpenAPI integrations to simulate accessing Internal Ledger (ERP), Open Banking APIs, and Government Compliance (SSM/LHDN sim). Layer 2: Orchestration (Skill Flows): This layer utilizes an Agentic Workflow to automatically fetch, sequence, and map data from all three isolated sources, guaranteeing stability and efficiency. Layer 3: Intelligence: The AI Agent receives the unified data packet and uses foundation models to perform forensic logic reasoning Business Value: The solution provides immediate ROI by: Preventing Fines: Ensures 100% compliance with statutory contribution rates (KWSP/LHDN). Eliminating Fraud: Stops payments to shell companies instantly. Increasing Efficiency: Reduces manual audit time from days to seconds by using automation. I use a scenario that involves a high-value payment for services: Amount: RM 250,000 Stated Purpose: Consultancy Fees Claimed Vendor (ERP): GHOST TECH SDN BHD AI successfully detects three major red flags by cross-referencing the three microservices: Red Flag 1: Shell Company Risk (SSM Check) Finding: The vendor, GHOST TECH SDN BHD, is listed with an SSM Status of "DORMANT (No Activity)". A company with no activity cannot legitimately provide RM 250,000 worth of consulting services. This indicates a high probability of a Shell Company being used to generate a fake expense. Red Flag 2: Identity Mismatch (Bank Trace) Finding: Although the ERP ledger claims the money went to the company, the actual beneficiary of the RM 250,000 transfer was "TAN AH KOW ". Red Flag 3: Tax Non-Compliance (LHDN Check) Finding: The vendor's LHDN compliance status is False. This confirms a high risk of Tax Evasion, as the counterparty is likely hiding the income, exposing the purchasing company to LHDN scrutiny. issue a CRITICAL FREEZE based on this overwhelming evidence.

💻 Online Hackathon | ⏳ Build: 48 hours | 📅 September 25–27, 2026 The official IBM Bob 2.0 hackathon. Build what's next in AI-assisted development, alongside the developers and experts shaping it. ⭐ Get help from experts throughout the event 🤝 Join a team or build solo 💰 Prize pool: $12,000 🧑🏻‍💻 Register before the Kick-Off Stream to start building with Bob

Leverage Orchestrate’s digital skills to design solutions that automate repetitive tasks, orchestrate workflows across tools, and empower employees to focus on high-value work. ⏳ Complete your project in just 48 hours and showcase your innovation. 🚀 Gain hands-on experience building with IBM watsonx Orchestrate. 💡 Develop practical AI agents that reshape the way teams and organizations operate. ⭐ Learn directly from experts who will support you throughout the event. 🤝 Team up or work independently to bring your vision to life. 💰 Prizes: $10,000 🧑🏻‍💻 Sign up before the Kick-Off Stream and start shaping the future with IBM watsonx Orchestrate!