Document Processing · IT Operations Automation
Users wanted outcomes, not just search results, and Genspark needed a no-code way to automate complex multimodal tasks such as calls, presentations, videos, and report generation through simple prompts.
Reported impact
Genspark turned a search product into a viral no-code agent platform, shipped features rapidly with a tiny team, and proved strong demand for outcome-driven multimodal automation rather than purely informational AI experiences.
Genspark pivoted from AI search into agentic execution by launching Super Agent, a no-code assistant that can make phone calls, assemble decks, create videos, and automate other real-world tasks. Under the hood, the platform orchestrates nine specialized language models and more than 80 tools, with OpenAI models at the center. GPT-4.1 handles research and structured outputs across very long contexts, GPT-image-1 generates visuals, and the OpenAI Realtime API powers Call For Me, a voice experience that can conduct live conversations with people. A dual-layer voice architecture combines the Realtime API for live dialogue with a shadow model that monitors and guides the interaction through queues, allowing the system to handle ambiguity, hold music, and real-time back-and-forth. Users never see that complexity; they simply request an outcome in natural language and the agent executes the workflow. This architecture, plus close collaboration with OpenAI’s startup team, let a 20-person company scale to remarkable ARR without paid marketing.
A user prompt enters Super Agent, which routes research, document generation, image creation, or phone calls to the appropriate OpenAI-backed components. For voice calls, the Realtime API manages live dialogue while a shadow model monitors and guides the interaction before the final artifact or completed task is returned to the user.
"Grown to $36M ARR in just 45 days"
"Super Agent uses OpenAI multimodal models and Realtime API to enable tasks across text, image, and voice"
"The OpenAI API design helped us move quickly, shipping, debugging, and scaling without bottlenecks."
"a fully autonomous, no-code assistant that can make phone calls, design slides, generate videos, and more"
Review how this reference was scored and trace each normalized claim back to its documented source.
Scoring methodology
Customer Reference Value measures usefulness as a customer reference. Evidence Confidence measures the quality and traceability of available evidence, not independent verification.
Traceability
Field coverage shows which facts each source supports. Dates are shown only when documented by the source.
Related
OpenAI Sample May 7, 2026 Oracle The talent acquisition team used ChatGPT Work to build a talent market intelligence tool that takes a job description, researches comparable roles, benchmarks compensation, and assesses the talent pool across relevant… "We’ve gone from zero to a hundred," says Jan Ackerman, Senior Vice President and Global Head of Talent… ChatGPT Work · Codex OpenAI Sample Aug 12, 2025 Basis "We’ve worked with OpenAI from day one," says Mitchell Troyanovsky, co-founder of Basis. "Each model improvement broadens what our agents can take on. Built with OpenAI o3, o3‑Pro, GPT‑4.1, and GPT‑5, Basis’ AI agents help accounting firms save up to 30% of… GPT-4.1 · GPT-5 · o3 
Google Cloud Sample Modified · Oct 9, 2026 Anthropic During large-scale training runs, traffic is highly variable—dropping to near zero during model checkpointing before bursting to millions of events per minute. Anthropic needed a serverless messaging queue that scaled… Handles peak throughput of over 1M events per second BigQuery · Bigtable · Cloud Pub/Sub 