Skip to main content
ZyngaConference talks

Dina Matveev (Data Engineer, Zynga) at AI Builders: Agentic AI.

What happened

Session: Code, Don’t Admin: Building a Multi-agent System to Automate our Sprint

Source

aibuildersday.comSep 8, 2026

AI Builders: Agentic AI

Code, Don’t Admin: Building a Multi-agent System to Automate our Sprint

Session

Moving a team from a unstructured workflow to structured sprints usually results in massive administrative overhead and developer background noise. When our team made the transition, we decided not to force engineers to become project managers, instead, we built a multi-agent system using LangGraph and LangChain, orchestrated via Google Vertex AI, to handle the sprint overhead for us. In this talk, we will show you the exact architecture we used to automate our workflow: real-time risk triaging,

aibuildersday.comRead the full source

Extracted by Autobound

From the Signal API record
Signal
Conference talks
Conference
AI Builders: Agentic AI
Date
Sep 8, 2026
Location
Tel Aviv, Israel
Topics
4

More conference speaker signals at other companies

The full record

From the Signal API record

People

  • Dina MatveevData Engineer, Zynga · Speaker

Topics and mentions

Conference topics

  • agentic AI
  • AI engineering
  • LLMs
  • developer tools
  • multi-agent systems
  • devops

Extraction

Confidence
High
Relevance
76%
Detected
Sep 30, 2026
signal_type
conference-speaker
signal_subtype
conferenceSpeaker

Use this data

Get every conference speaker signal for Zynga and the companies you sell to, in the tools you already use.

  1. Ask Claude about it

    Connect Autobound to Claude, Claude Code or Cursor with MCP. Then ask: “What changed at Zynga this week?”

  2. Send it to your own tools

    The Signal API returns conference speaker signals for any list of companies as JSON, for your CRM, warehouse or app.

  3. Try it free

    Sign up and spend your free credits on the companies you sell to.

    Start Free1,000 free credits

The API returns more than this page shows

This page shows a preview. The full conference-speaker record in the Signal API and MCP can also have these 19 fields. Some fields are empty for some signals.

Contact

  • full_nameValue in the API
  • job_titleValue in the API
  • linkedin_urlValue in the API
  • emailValue in the API
  • first_nameValue in the API
  • last_nameValue in the API
  • cityValue in the API
  • stateValue in the API
  • countryValue in the API
  • seniorityValue in the API

Company

  • linkedin_urlValue in the API
  • industriesValue in the API
  • employee_count_lowValue in the API
  • employee_count_highValue in the API
  • revenueValue in the API
  • descriptionValue in the API

Signal

  • signal_nameValue in the API
  • associationValue in the API

And 1 more fields.

Show the full JSONThe record on this page and the API request

GET /v1/signals/79a154d1-426b-58eb-bdcb-3c0cc5d42159 returns this record as JSON. POST /v1/companies/enrich returns every signal for zynga.com.

{
  "signal_id": "79a154d1-426b-58eb-bdcb-3c0cc5d42159",
  "signal_type": "conference-speaker",
  "signal_subtype": "conferenceSpeaker",
  "detected_at": "2026-09-30T08:36:28+00:00",
  "company": {
    "name": "Zynga",
    "domain": "zynga.com"
  },
  "data": {
    "summary": "Dina Matveev (Data Engineer, Zynga) at AI Builders: Agentic AI.",
    "relevance": 0.76,
    "confidence": "high",
    "speaker_bio": "Dina is a software engineer, she builds large-scale ingestion pipelines, distributed workflows, and production-ready AI features. Her background spans full-stack engineering and data engineering, and she’s drawn to problems that start out messy and unpredictable - she likes breaking them down into clear, maintainable systems and sharing the lessons that come from scaling and debugging them. When she’s not building pipelines, she’s usually at the piano or chasing the perfect cup of coffee.",
    "session_type": "talk",
    "session_title": "Code, Don’t Admin: Building a Multi-agent System to Automate our Sprint",
    "conference_url": "https://www.aibuildersday.com/",
    "conference_date": "2026-09-08",
    "conference_name": "AI Builders: Agentic AI",
    "is_future_event": false,
    "contact_resolved": true,
    "conference_topics": [
      "agentic AI",
      "AI engineering",
      "LLMs",
      "developer tools",
      "multi-agent systems",
      "devops"
    ],
    "extraction_method": "llm-speakers_list+bio",
    "domain_match_score": 10,
    "conference_end_date": "2026-09-08",
    "conference_location": "Tel Aviv, Israel",
    "session_description": "Moving a team from a unstructured workflow to structured sprints usually results in massive administrative overhead and developer background noise. When our team made the transition, we decided not to force engineers to become project managers, instead, we built a multi-agent system using LangGraph and LangChain, orchestrated via Google Vertex AI, to handle the sprint overhead for us. In this talk, we will show you the exact architecture we used to automate our workflow: real-time risk triaging,",
    "conference_description": "AI Builders is a practical, production-focused AI engineering conference for developers and tech leaders building real-world AI systems. It emphasizes agentic AI, SDLC integration, hands-on workshops, code labs, case studies, and architectural lessons from deploying AI reliably at scale.",
    "domain_match_confidence": "high",
    "conference_estimated_size": "450-600"
  }
}

Long text fields are shortened on this page.

Looking up one signal by its id is free. Enrich costs 2 credits per signal returned; a call with no results is free.