​Hack the Video Agent Context Graph

​Video is one of the hardest data types to search: hours of footage where everything you care about—what is shown, said, and written on screen—is locked inside frames nobody has time to watch.

​Your challenge is to build a video agent that turns what it sees into a context graph it can reason over.

​In one full day, your agent will ingest raw video, understand it across vision, audio, and speech with TwelveLabs, and write what it finds into a Neo4j context graph: entities, scenes, tags, and the relationships between them. Strands Agents orchestrates the pipeline. OpenAI drives the reasoning.

​Go solo or form a team. No prior graph or video AI experience is required. The event operator expects to provide starter templates and the technical stack; final links and access instructions will be shared when confirmed. Prize categories and judging details are still to come.

​Build something that watches, tags, and connects.

​What You Will Build With

• ​Strands Agents to orchestrate the video-to-graph pipeline

• ​OpenAI to reason over extracted context

• ​TwelveLabs to understand vision, audio, speech, and on-screen content

• ​Neo4j to model entities, scenes, tags, and their connections

​Schedule

• ​9:30 AM - Doors, check-in, coffee, and setup

• ​10:00 AM - Orchestrating the Pipeline with Strands Agents - Elizabeth Fuentes

• ​10:15 AM - Reasoning over Video Context with OpenAI - Charlie Guo

• ​10:30 AM - Understanding Vision, Audio, and Speech with TwelveLabs - James Le

• ​10:45 AM - Modeling a Neo4j Context Graph: Entities, Scenes, Tags, and Connections - Jeremy Adams

• ​11:00 PM - Challenge briefing, starter templates, questions, and team formation - Hacking Begins

• ​12:00 PM - Lunch / setup buffer; food details TBD

• ​4:00 PM - Target submission window; final cutoff - Judges review submissions

• ​5:15 PM - Target demo and judging window

• ​7:00 PM - Target awards and closing remarks; prize details TBD

• ​7:30 PM - Doors close

​Who Should Join

• ​AI, ML, and software engineers

• ​Builders working with agents, video, search, retrieval, or knowledge graphs

• ​Technical founders and product engineers

• ​Developers curious about multimodal reasoning and graph-based context

• ​First-time video AI or graph builders who want a practical starting point

​Bring a laptop and come ready to build. You may participate solo or with a team.

​Event Ownership

​This event is organized and operated by the lead event team, whose final public name and contact are still to be confirmed. HackerSquad and The Builder Collective are providing promotional support only; they are not producing or operating the event. Venue operations, registration decisions, attendee support, speakers, food, AV, judging, prizes, safety, and day-of production belong to the lead event operator.

​When: Thursday, July 30, 2026 | 9:30 AM-8:00 PM PT; technical program begins at 10:00 AMWhere: AWS Builder Loft, 525 Market St, San Francisco, CA 94105