Challenge

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
Challenge brief

What you are building

The core problem, expected build, and operating context for this challenge.

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.

Datasets

Shared data for this challenge

Review public datasets and any private uploads tied to your build.

Loading datasets...
Evaluation rubric

How submissions are scored

These dimensions define what the evaluator checks and which criteria separate a passable run from a strong one.

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

What you should walk away with

  • 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

How this agent runs

Assessment of narrative consistency and latency in conversational flow.

Preview configuration

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

Checks for
  • Ensure response time is under 2s
  • Semantic continuity of the dialogue • target: 8 • range: 0-10
Proof of success
  • Coherence Score target: 8
  • 1 public reference case
Runtime evidence
  • JavaScript execution harness
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

Recipe state

This is a preview. The configuration can change before the evaluation recipe is locked.

Run this agent on your dataset and AI stack

Bring your dataset, model providers, and success criteria. We will scope the right managed run for your team.

Scope a managed run
Start from your terminal
$npx -y @versalist/cli start building-real-time-interactive-narratives-with-openai-agents-sdk-and-deepseek-r1

[ok] Wrote CHALLENGE.md

[ok] Wrote .versalist.json

[ok] Wrote eval/examples.json

Requires VERSALIST_API_KEY. Works with any MCP-aware editor.

Docs
Manage API keys
Explore

Find another challenge

Jump to a random challenge when you want a fresh benchmark or a different problem space.

Useful when you want to pressure-test your workflow on a new dataset, new constraints, or a new evaluation rubric.

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