Grafo: an agentic AI platform at 5K requests a minute
Grafo is an AI writing product that generates outreach messages from scraped content. I was the platform architect and full-stack engineer on it from March to December 2023.
The problem
A new product that had to run agentic AI workflows against two model providers at high concurrency, with pipelines that scraped, processed and generated in stages.
What I did
- Designed and built the platform architecture from scratch.
- Integrated agentic workflows using the OpenAI and Anthropic APIs.
- Built a model switcher so a pipeline could run on different models.
- Built the asynchronous processing and orchestration for multi-stage data pipelines.
- Optimised the pipelines to sustain 5,000+ parallel requests a minute.
- Integrated HubSpot and Reply.io.
Result
5K+ parallel AI requests a minute in production.
Stack
Konstantin has been an invaluable leader to our team at GrafoAI. He possesses a remarkable depth of technical knowledge and expertise and has consistently delivered high-quality code. Konstantin has a remarkable ability to analyze and solve complex problems, often seeing them before they appear. His ability to meet deadlines and manage tasks efficiently is second to none. K is extremely forward-thinking; always suggesting and implementing innovative ideas and showing his commitment to our mission and goals. He's absolutely invaluable and an all-around great person to work with. I look forward to continuing our partnership with Konstantin well into the future
Related: AI and LLM integration
Add a production AI feature, retrieval over your data, or model routing to a Rails app that already works. How it works →
Full overlap with European business hours, and 9am–6pm US Eastern.
43 clients, 21,500+ hours, 100% Job Success — the reviews are on Upwork.