Resume RAG Chatbot

Resume RAG Chatbot

Overview

The AI assistant running on this portfolio. Try it on this site: open the chat widget on any page and ask about my experience. Every answer is grounded in my resume, not guesswork.

This portfolio answers questions about itself. The full resume ships as context for Gemini 2.5 Flash with every request, and answers stream back through the Vercel AI SDK. No vector store, no embeddings, just grounded answers. It is the smallest version of the AI features I build for clients.

Business Context: Turning Portfolio Content into a Searchable Product Surface

A traditional portfolio asks visitors to do too much interpretation work. Recruiters, hiring managers, founders, and collaborators often have very specific questions:

• ›Has he led full-stack projects?
• ›Does he have backend depth or mostly frontend experience?
• ›What kinds of systems has he built?
• ›How might this background help a product team right now?

When those answers are buried across a resume page, project pages, and blog posts, the portfolio becomes a discovery problem. The chatbot solves that by acting as a guided interface over the most important experience content.

The core product problem: Static portfolio content is informative, but not queryable. Visitors need a faster way to map Sadam's experience to their own team or product needs.

What success looks like:

• ›Visitors can ask direct, role-relevant questions in natural language.
• ›Responses stay grounded in documented experience instead of generic AI filler.
• ›Answers connect technical background to likely delivery outcomes for teams and products.
• ›The chatbot feels integrated into the portfolio UX, not bolted on as a novelty feature.

What I Built

1. Resume Context as the Grounding Layer

• ›MDX-Based Source of Truth: Reused the site's existing resume content (public/resume/resume.mdx) as the knowledge source instead of introducing a second content system.
• ›Full-Document Injection: The server loads the whole resume on each request and injects it into the system prompt as context. The document is small enough to fit comfortably in Gemini Flash context, so every answer draws from complete information rather than a retrieved slice.
• ›Caching and PII Handling: An in-memory cache keyed on file modification time avoids rereading the resume on every request, and contact details are redacted before the text ever reaches the model.

2. AI SDK Chat Pipeline

• ›Typed Chat Transport: Built the server route around the Vercel AI SDK's UIMessage[] contract, validating incoming chat history before converting messages for model execution.
• ›Bounded Working Set: Only the most recent messages travel with each request, with per-part text caps, so token usage stays predictable no matter how long the conversation runs.
• ›Retry and Rate Control: Disabled default SDK retries during provider failures to avoid duplicate calls, and rate-limited the endpoint per IP so one visitor cannot exhaust the shared quota.
• ›Guardrails: Added instruction design that keeps the assistant grounded in resume evidence while encouraging answers to explain both what Sadam has done and what that experience suggests for teams or products.

3. Chat Experience in the Portfolio UI

• ›Floating Widget Pattern: Implemented a bottom-corner widget that opens into a dedicated chat panel, making the assistant accessible without interrupting the rest of the portfolio browsing flow.
• ›Contained Scroll Behavior: Refined the panel layout so scrolling remains isolated to the chat window rather than leaking to the page underneath.
• ›Streaming Responses: The UI shows the response as it arrives, making the interaction feel responsive and alive.
• ›Markdown Rendering: Added markdown support in assistant messages so lists, emphasis, inline code, and formatted answers render cleanly instead of appearing as raw text.
• ›Starter Questions, Follow-Ups, and Error States: Included suggested prompts, contextual follow-up chips, loading affordances, and graceful error messaging to reduce friction for first-time users.

Architecture Highlights

Full Context as the Grounding Layer, Not a Sidecar

The chatbot is not just "an LLM on top of a prompt." The full resume ships with every request and anchors the response in documented experience. That design choice matters because it improves both accuracy and usefulness:

• ›Accuracy improves because responses are tied to real content rather than generic inference.
• ›Usefulness improves because the system can answer narrow, role-specific questions from complete experience context.

Content Reuse Through Existing MDX

Rather than creating a separate admin panel or knowledge base interface, the implementation reuses the existing resume MDX as the canonical source. That keeps the content workflow simple: update the resume and the assistant reflects the latest experience narrative on the next request, with no reindexing step.

Small-System, Production-Minded Architecture

The architecture is intentionally compact:

• ›Resume content in MDX
• ›Full-context injection per request
• ›Gemini generation with grounded prompt design
• ›AI SDK route for orchestration
• ›React chat UI for delivery

This keeps the system easy to understand and maintain while still showcasing applied AI engineering in a real product environment.

Technical Deep Dive: Portfolio-Native Grounded Chat Flow

The request lifecycle is straightforward but purposeful:

1. ›A visitor submits a question in the chat panel.
2. ›The latest user message is extracted from the AI SDK UIMessage[] payload after validation.
3. ›The server loads the full resume MDX (from the in-memory cache when fresh) and composes a system prompt that instructs the model to answer only from that context and to connect the documented experience to potential team or product outcomes.
4. ›Gemini generates the response and the AI SDK streams it back to the client.
5. ›The client renders the answer with markdown support inside the chat panel.

The important product insight is that the chatbot is not only answering factual questions. It is also helping visitors interpret relevance. A static resume says what happened. This assistant helps explain why it matters.

Key Challenges & Solutions

• ›

  Challenge: Static portfolio content is difficult to query conversationally. Approach: Built a grounded assistant over resume content so visitors can ask direct questions in natural language. Why: This reduces the cognitive load of navigating a portfolio and increases the chances that the right strengths are discovered quickly.

• ›

  Challenge: LLM answers can become generic or drift beyond the source material. Approach: Ship the whole resume as context and add strict prompt instructions to stay grounded in documented experience. Why: A portfolio assistant needs credibility more than creativity. Grounding matters more than flourish.

• ›

  Challenge: Chat UI quality often breaks the illusion of product polish. Approach: Added streaming states, starter prompts, markdown rendering, contained scrolling, and tighter panel behavior. Why: If the assistant feels clunky, users treat it like a demo. If it feels polished, they use it as part of the portfolio experience.

• ›

  Challenge: AI integrations can introduce unnecessary infrastructure complexity. Approach: Used full-context injection over the existing resume MDX rather than adding a vector database and embeddings pipeline. Why: The goal was to demonstrate product-quality AI integration, not accumulate avoidable system overhead. The resume fits comfortably in Flash context, so retrieval would add cost and staleness without benefit.

Outcomes

• ›Queryable portfolio: Visitors ask direct, role-relevant questions instead of assembling context from scattered pages.
• ›Experience-to-outcome translation: Answers explain not just what I built, but what that background means for a team or product.
• ›Live proof: The site demonstrates the AI integration skill it advertises, running in production on this page.
• ›Grounded responses: Resume-based context keeps the system anchored to documented experience rather than generic model output.

Engineering Takeaways

This project reinforced a useful product principle: AI features are most convincing when they sit directly inside a real workflow. A standalone demo is easy to dismiss. An assistant embedded in a portfolio that improves discovery, interpretation, and engagement is much more compelling.

Patterns I'd reuse:

• ›Full-context grounding over existing content sources rather than creating redundant admin workflows
• ›Skipping the vector layer entirely when the corpus comfortably fits the model context
• ›AI SDK chat abstractions for building typed, streaming UI experiences quickly
• ›Guardrail prompts that combine evidence grounding with user-centered interpretation

What I'd improve next:

• ›Expand the grounding corpus beyond the resume to include selected projects and case studies
• ›Add source citations or linked references in responses so visitors can jump directly to supporting content
• ›Introduce evaluation prompts or test fixtures to benchmark answer quality across common visitor questions

Trade-offs acknowledged:

• ›Chose a small, focused knowledge base (resume only) to keep grounding strong, accepting that some broader portfolio questions may not yet have enough context
• ›Chose full-context injection over a retrieval stack to keep architecture simple and always fresh, accepting that a much larger corpus would eventually need retrieval
• ›Chose prompt-level outcome framing rather than explicit scoring/ranking heuristics, which keeps the system flexible but makes response style more dependent on prompt quality