Serverless backend
Implement lightweight AWS Lambda processing with logging, error handling and frontend integration.
An AI-powered interactive portfolio assistant that helps visitors explore Ron's work experience, skills, certifications, education and projects using only information published on this website. RonBot is designed to stay grounded, avoid guessing and direct unanswered enquiries to the Contact page.
Project Delivery Board
Implement lightweight AWS Lambda processing with logging, error handling and frontend integration.
Select and integrate a suitable model with prompts and guardrails optimised for quality, latency and cost.
Support natural follow-up questions while preventing chat history from overriding grounding rules.
Add input validation, rate limiting, API protection and prompt-injection resistance.
Prevent external personal-data retrieval and define safe behaviour for personal or inappropriate questions.
Measure RonBot's production AWS and AI operating costs, maintain budget alerts, establish a monthly cost baseline and document optimisation opportunities, including cost-per-usage metrics where practical.
Create recruiter, technical, certification, work-history, unknown-answer and adversarial test cases.
Verify answers against the website and confirm unsupported questions trigger the Contact fallback.
Test desktop, mobile, browsers, accessibility, performance, error handling and live AWS integration.
Build out the repository with source, README, architecture, deployment, privacy, screenshots and cost notes.
Expand this page with architecture, stack, screenshots, technical challenges, security controls and outcomes.
Deploy the backend and frontend integration, configure production settings and complete end-to-end testing.
Complete final documentation, cost and portfolio reviews before marking Project 02 complete.
No task is currently marked in progress. RON-11 — RonBot API is complete; RON-12 — Serverless backend is next in the backlog.
Defined RonBot as a website-only assistant: no external searches about Ron, no unsupported guessing, and unanswered enquiries are directed to the Contact page.
Defined and documented the frontend, API, AI and website-knowledge architecture using low-cost serverless AWS services.
Defined RonBot's friendly, professional and recruiter-ready voice, adaptive technical depth, website-only grounding and Contact fallback behaviour.
Created and approved the production RonBot character artwork with AWS hoodie, Redpanda T-shirt, Azure beanie, Google-branded trousers and study material.
Built and validated the website knowledge ingestion and retrieval foundation, including structured JSONL generation, chunking with overlap, URL canonicalisation, same-site restrictions and grounded retrieval tests against live website content.
Added the interactive RonBot chat experience with hover feedback, animated open/close behaviour, user message bubbles, purposeful thinking animation, an animated thinking indicator, improved spacing and reduced-motion accessibility support.
Built and validated the website ingestion pipeline, indexing 12 live site pages into 39 clean, traceable knowledge chunks.
Enforced same-site-only crawling and validated that GitHub, LinkedIn, Credly and all other external domains are excluded from RonBot's knowledge source.
Improved natural-language retrieval and conversational answers while preserving the website-only knowledge boundary and Contact-page fallback. Validated with an 11 / 11 regression test covering supported and deliberately unsupported questions.
Added adaptive answer depth so general visitors receive concise portfolio answers while technical questions can surface deeper website-grounded implementation detail. Improved retrieval for RonBot implementation questions while preserving website-only grounding and the Contact-page fallback for unsupported questions.
Deployed the RonBot backend to AWS Lambda, exposed it through an Amazon API Gateway HTTP API using POST /ask, connected the browser frontend to the live endpoint, configured CORS for local and production origins, and validated grounded answers, fallback behaviour and frontend error handling.