a16z podcast: Reducto CEO on why AI agents need a document layer
a16z · x · 2026-10-21
- a16z GP Jennifer Li interviews Reducto co-founder and CEO Adit Abraham on the document layer problem for AI agents.
- Much of the world's work is trapped in PDFs, spreadsheets, and scans that models can't reliably parse; traditional OCR breaks down on messy real-world documents.
- Reducto combines vision-language models with specialized infrastructure for high accuracy without sacrificing cost or latency; frontier models can silently drop information on long extraction tasks.
- Target verticals: healthcare, legal, finance, insurance.
- Reducto now processes billions of pages monthly, crossing 7 billion pages the morning of the recording.
More from coding & agent
- 90% of big-company knowledge lives in heads, and "company brain" startups are in for pain — gabriel1 · 2026-10-21
- EAU: Co-evolving user simulator, environment, and RL setup for training LLM agents — UAlberta · 2026-10-21
- Meta's Self-Credit: Dense Rewards from Sparse RLVR via Intra-group Rescaling — meta · 2026-10-21
- Notion details its Auto model router: Elo-based evals, 62-93% cheaper than flagship models — ivanhzhao · 2026-10-21
- Dev sets up automation so agents proactively pick up stale issues and PRs — vikvang1 · 2026-10-21
- Tamper-proof agent logs still can't prove the agent did the job: who reads the record back? — ZealousidealAct9661 · 2026-10-21