Reducto CEO on the Missing Document Layer for AI Agents, Now Processing 7 Billion Pages
a16z Podcast · rss · 2026-10-21
- On the a16z podcast, Reducto co-founder and CEO Adit Abraham explains why agents need a reliable "document layer": real-world work is trapped in PDFs, scans and spreadsheets, and traditional OCR breaks down on messy documents.
- Reducto combines vision-language models with specialized infrastructure to hit high accuracy without sacrificing cost or latency; it just processed its 7 billionth page and now handles billions monthly.
- Key topics: frontier models silently drop information on long extraction tasks; Reducto's R1 model lets agents review and correct their own extractions; the company is pushing beyond reading files toward agents reliably editing them.
- The stakes: when one misread word can affect a healthcare claim or financial decision, getting inputs right matters as much as smarter models.
More from coding & agent
- Decisions API hits GA as agents automate cloud video editing via feedback loops — dkundel · 2026-10-23
- Swarms API changelog: 8 months of streaming, multi-agent orchestration, and dynamic model pricing — KyeGomezB · 2026-10-23
- A curated library of 50+ free AI agent resources: videos, repos, one Google Doc — ifioknkem · 2026-10-23
- Vercel adds no-account deploys: drag and drop a file to get a live URL — steren · 2026-10-23
- Dev runs 5 Claude Code sessions that coordinate via MCP Agent Mail to root his network cameras — doodlestein · 2026-10-23
- Vercel ships 'vercel deploy --temporary' for ephemeral agent-built deployments — cramforce · 2026-10-23