Skip to main content
Loading navigation
Back to challenges

Building Real-Time Interactive Narratives with OpenAI Agents SDK and DeepSeek R1

Create an immersive, interactive agent system designed to generate dynamic microdramas. Using the OpenAI Agents SDK, you will develop a multi-turn conversation orchestrator that manages character persona state and narrative flow. This challenge leverages the DeepSeek R1 reasoning model to ensure that plot development remains coherent and follows complex character arcs defined by the user. Integration with Sarvam AI enables voice-native interaction, while Browserbase provides the infrastructure for agents to perform live-web actions, such as fetching real-time context to enrich the story. All traffic and model routing is managed through Vercel AI Gateway, providing enterprise-grade analytics on token usage and model performance. Google Jules serves as the core development assistant for debugging the logic flows within your agentic stack.

Special Purpose AgentsHosted by Vera
Sign in free to start

What you are building

Utilize OpenAI Agents SDK and DeepSeek R1 to power an interactive narrative engine with voice and browser capabilities.

How work is evaluated

Evaluation

Assessment of narrative consistency and latency in conversational flow.

Datasets

Public datasets, plus the private datasets you have access to.

How submissions are scored

Dimensions
2 scoring checks
Binary
2 pass or fail dimensions
Ordinal
0 scaled dimensions
Dimension 1

latency_check

Ensure response time is under 2s

Binary check

This dimension contributes its full weight only when the submission satisfies the requirement. Partial credit is not awarded.

Dimension 2

coherence_score

Semantic continuity of the dialogue • target: 8 • range: 0-10

Binary check

This dimension contributes its full weight only when the submission satisfies the requirement. Partial credit is not awarded.

Learning goals

  • Master the OpenAI Agents SDK for stateful, multi-turn dialogue management in narrative contexts

  • Deploy DeepSeek R1 via API for high-reasoning narrative construction

  • Build browser-based agents using Browserbase to pull real-world headlines for story enrichment

  • Configure Vercel AI Gateway to monitor agentic token consumption and implement fallback routing

  • Integrate Sarvam AI for real-time voice synthesis and speech-to-intent mapping

  • Use Google Jules to assist in diagnosing and refining agent-call sequences during complex story branches

Resources

Dataset notes

Sample data for 1 tasks

Challenge setup

Assessment of narrative consistency and latency in conversational flow.

Challenge input

Initial narrative prompt

OpenAI

OpenAI AI model provider

Browserbase

Headless browser for AI agents

DeepSeek R1

Policy Serving in the agent workflow.

Evaluated output

Character dialogue chain

Evaluation checks
  • Ensure response time is under 2s
  • Semantic continuity of the dialogue • target: 8 • range: 0-10
Configured evaluation evidence
  • Coherence Score target: 8
  • 1 public reference case
Configured runtime
  • JavaScript execution harness

Shows the first task, up to three tools, and up to three evidence items.

View technical recipe

Configured tools

Action Space
  • OpenAI · Required
  • Browserbase · Optional
Policy Serving
  • DeepSeek R1 · Optional

Evaluation contract

  • latency_check · Weight 1
  • coherence_score · Weight 1

Metrics

  • coherence_score · Target 8

Reference cases

  • 1 public reference case

Workflow tasks

  1. Task 1

    Input: Initial narrative prompt

    Output: Character dialogue chain

    Execution harness: JavaScript

Recipe freeze marker

No recipe freeze time is recorded.

Frequently Asked Questions about Building Real-Time Interactive Narratives with OpenAI Agents SDK and DeepSeek R1