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

> Source: <https://dev.to/inushathathsara/multi-agent-gift-recommendation-engine-powered-by-google-adk-gemini-3669>
> Published: 2026-08-21 15:27:55+00:00

*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:

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

**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:

`LlmAgent`

, `SequentialAgent`

, and `InMemorySessionService`

.`min-instances=0`

(scales to zero when idle for $0.00 base cost).`.md`

), JSON (`.json`

), Clipboard, or Print / Save as PDF.`ProfileAnalyzerAgent`

)
`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",
)
```

`IdeaFinderAgent`

)
`{recipient_profile}`

from the session state and ideates 6–10 candidate ideas across diverse categories (e.g., `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",
)
```

`BudgetFilterAgent`

)
`{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 `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",
)
```

`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,
    ],
)
```

`google-adk`

(Agent Development Kit v2.7.0)`gemini-3.1-flash-lite`

(via `google-genai`

)To keep running costs near $0.00 while maintaining rapid startup times:

`min-instances = 0`

`memory = 512MiB`

& `cpu = 1 vCPU`

`gemini-3.1-flash-lite`

**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**:

Using `InMemorySessionService`

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.

Building **GiftAdvisor** with Google ADK demonstrated how accessible and clean multi-agent orchestration has become in Python.