See the future of research.
Build it now.
Foresight is an AI-powered research intelligence platform that synthesises academic papers into a visual timeline, predicts future research directions, and generates runnable implementations with live AI agents.
How It Works
Explore
We index papers from NeurIPS, ICLR, ICML, CVPR, and arXiv, building a knowledge graph of citations and semantic connections. Browse any field as an interactive, physics-driven timeline.
Predict
Our AI synthesises the collective future-work sections of hundreds of papers to project where the field is heading. Each future direction comes with confidence scores, compute estimates, and matched researchers.
Implement
Click any future direction and a live Claude agent generates a complete research scaffold: runnable Python code executed instantly in a sandboxed environment. From paper to prototype in seconds.
By the Numbers
Architecture
Bounty Tracks
Best Use of Agentic SDK
Live Claude agent streams code generation via SSE, with paper context injection from our knowledge graph. The agent reads methods sections from prerequisite papers and generates a targeted research scaffold.
Best UI
Academic journal aesthetic: serif typography, monochromatic palette, physics-driven D3-force timeline graph with zoom/pan, path highlighting, and smart labels. Every pixel designed for depth and sustained attention.
Team
Will Rowan
- PhD Computer Science, University of York. Thesis on 3D face reconstruction
- Co-founder of PXLD, an AI video relighting startup (featured in Variety, Screen Daily)
- Published at ICLR, ECCV. Best Poster Award, ECCV 2024
- Research Fellow working on AI-powered virtual production tools
Simon Luo
- BA Computer Science, Churchill College, Cambridge - thesis on applying ML models to financial market prediction
- Former Technical Lead and FDE at Palantir
- Former SWE at DRW
- Currently exploring startup ideas worth building