Multi-Agent Gift Recommendation Engine Powered by Google ADK & Gemini

This post is my submission for DEV Education Track: Build Multi-Agent Systems with ADK. Finding the perfect, thoughtful gift shouldn't feel like a chore. Whether it's for a birthday, anniversary, or holiday, we all experience gift-buying paralysis: - Generic suggestions: "Just buy them a mug or a generic gift card." - Budget anxiety: Falling in love with an idea only to find out it costs 3x what you planned to spend. - Missing the subtle nuances: Forgetting that someone dislikes clutter, lives in a tiny apartment, or prefers practical experiences over physical objects. To solve this, I built GiftAdvisor. It is an intelligent, consumer-friendly gift recommendation system built with Google Agent Development Kit (ADK), Gemini (gemini-3.1-flash-lite ), and deployed seamlessly to Google Cloud Run. Live Demo & Links - Live Cloud Run App: https://gift-advisor-1008832068452.us-central1.run.app - GitHub Repository: https://github.com/inusha-thathsara/Multi-Agent-Gift-Idea-Generator-with-Google-ADK What I Built GiftAdvisor transforms unstructured descriptions of a person into tailored, ranked, and strictly budget-compliant gift recommendations. Instead of dumping everything into a single monolithic prompt, GiftAdvisor splits the cognitive load across three specialized AI agents orchestrated via Google ADK: - Profile Analyzer Agent: Understands the human behind the prompt (lifestyle, hobbies, aesthetic preferences, and explicit anti-preferences). - Idea Finder Agent: Brainstorms creative, thoughtful candidate gifts across multiple categories with estimated market prices. - Budget Filter Agent: Audits estimated prices, filters out anything exceeding the user's hard budget limit, swaps in budget-friendly alternatives, and delivers a ranked curation. Key Highlights & Features - Pure Multi-Agent Pipeline: Built using Google ADK's LlmAgent ,SequentialAgent , andInMemorySessionService . - Zero-Overhead Scale-to-Zero: Deployed to Google Cloud Run with min-instances=0 (scales to zero when idle for $0.00 base cost). - Modern Glassmorphism UI: Intuitive dark-mode consumer interface with 1-click preset profiles, interactive budget slider, and live pipeline stage tracking. - Comprehensive Export System: Export recommendations with 1 click to Markdown ( .md ), JSON (.json ), Clipboard, or Print / Save as PDF. Cloud Run Embed 1. Profile Analyzer Agent (ProfileAnalyzerAgent ) - Role: Empathy & Persona Architect. - What it does: Ingests raw user inputs (e.g., "My 29yo sister loves specialty pour-over coffee and houseplants, but lives in a small apartment"). It extracts core interests, lifestyle dimensions, emotional tone, and most importantly, anti-preferences (e.g., no large items, avoid generic mugs). - ADK Output Key: recipient_profile profile_analyzer_agent = LlmAgent( name="ProfileAnalyzerAgent", model=model_name, instruction=""" You are an expert gift persona analyzer. Analyze the recipient's description, occasion, and relationship. Extract key traits, hobbies, lifestyle context, and explicit anti-preferences (what to avoid). Save your structured analysis to session state key 'recipient_profile'. """, output_key="recipient_profile", ) 2. Idea Finder Agent (IdeaFinderAgent ) - Role: Creative Ideation Specialist. - What it does: Reads {recipient_profile} from the session state and ideates 6-10 candidate ideas across diverse categories (e.g., Experiential, Practical Everyday, Consumable / Artisan, Sentimental). It attaches realistic estimated market prices to every item. - ADK Output Key: candidate_gift_ideas idea_finder_agent = LlmAgent( name="IdeaFinderAgent", model=model_name, instruction=""" You are a creative gift brainstormer. Given the recipient profile: {recipient_profile} Brainstorm 6 to 10 distinct, creative gift ideas across multiple categories. For each idea, provide a realistic estimated market price. Save your candidate ideas to session state key 'candidate_gift_ideas'. """, output_key="candidate_gift_ideas", ) 3. Budget Filter Agent (BudgetFilterAgent ) - Role: Financial Auditor & Final Curator. - What it does: Reads {candidate_gift_ideas} ,{budget_limit} , and{currency} . It validates each candidate against the budget ceiling. Any item that exceeds the budget is logged in an Elimination Audit and replaced with a budget-friendly alternative. The agent then organizes recommendations into budget tiers (Splurge, Sweet Spot, Budget Friendly) with specific buying advice. - ADK Output Key: final_gift_recommendations budget_filter_agent = LlmAgent( name="BudgetFilterAgent", model=model_name, instruction=""" You are a meticulous gift budget auditor and curator. Budget Limit: {budget_limit} {currency} Candidate Ideas: {candidate_gift_ideas} 1. Audit each idea against the budget ceiling. 2. Eliminate items that exceed the limit and suggest budget-friendly alternatives. 3. Present the Top 3-5 Recommended Gifts formatted into budget tiers with rationale. Save the final report to session state key 'final_gift_recommendations'. """, output_key="final_gift_recommendations", ) 4. Orchestration with SequentialAgent Google ADK makes chaining agents intuitive using SequentialAgent . State flows from one agent's output_key directly into the next agent's prompt template variables: gift_advisor_pipeline = SequentialAgent( name="GiftAdvisorPipeline", sub_agents=[ profile_analyzer_agent, idea_finder_agent, budget_filter_agent, ], ) Implementation & Architecture Backend Tech Stack - Framework: Python 3.12, FastAPI, Uvicorn - Agent Framework: google-adk (Agent Development Kit v2.7.0) - Model: gemini-3.1-flash-lite (viagoogle-genai ) - Deployment: Google Cloud Run (Containerized via Docker) Cloud Run Production Optimization To keep running costs near $0.00 while maintaining rapid startup times: - min-instances = 0 : Cloud Run spins down to zero instances when no traffic is being served. - memory = 512MiB &cpu = 1 vCPU : Lightweight footprint optimized for async FastAPI and Google ADK orchestration. - gemini-3.1-flash-lite : Ultra-fast latency with minimal token consumption. Key Learnings Separation of Concerns Prevents Hallucination: When asking a single LLM prompt to analyze personality, brainstorm 10 items, and filter by budget simultaneously, it often ignores budget limits or produces bland suggestions. By decoupling Analysis -> Ideation -> Budget Auditing into separate ADK agents, each agent performs its task with significantly higher precision.Session State is the Superpower of ADK: UsingInMemorySessionService and prompt variable injection ({recipient_profile} ,{candidate_gift_ideas} ) made passing structured context between agents clean, traceable, and modular.Cloud Run + Gemini is a Perfect Match: Deploying containerized Python agent applications to Cloud Run gives you an instant HTTPS public API with scale-to-zero economics. No idle server bills, automatic TLS certificates, and global scaling out of the box. Conclusion & What's Next Building GiftAdvisor with Google ADK demonstrated how accessible and clean multi-agent orchestration has become in Python. Future Ideas - Live Search Tool Integration: Connecting Google Search grounding or SerpAPI to pull real-time e-commerce links and stock availability. - Group Gift Mode: Splitting a high-ticket budget across multiple contributors with automated per-person share calculations. Top comments (0)