nowfound

Work · May 28, 2026

Intake

Documents in, structured data out — zero templates

Intake launched on May 28, 2026 with 2 votes, #6,288 of 20,538 launches that month.

What it does

Intake reads your PDFs and images, pulls out exactly the fields you define — in plain English, no templates — flags anything it's unsure about for a quick human check, then writes the clean record straight into Google Sheets, your database, or any webhook. It's the data-entry robot that actually lands the data where you need it. Free to start: 25 docs/month.

Does a similar job

all alternatives →
  • Docparser2016 · docparser.com · ▲194

    Convert PDFs and scanned documents into structured data

  • Paperworks2016 · paperworks.io · ▲412

    All your receipts, invoices, and payments in one place.

  • Docsumo2019 · docsumo.com · ▲99

    Automate data entry while processing documents ✌️

  • Convert PDF files into structured data2016 · docparser.com · ▲107

    Docparser helps you extract important data from Word, PDF, CSV, XLS, TXT, XML, and image files. Send to Excel, Google Sheets, and 100s of apps.

  • IntakeApr 2026 · intakerequest.com · ▲6

    Intake is secure client document collection for accounting, legal, and compliance firms. One portal, encrypted uploads, 120 templates, and a 14-day trial.

  • Sensible Instruct2023 · app.sensible.so · ▲117

    GPT-4 document extraction

More work this month

the category →

Source: Product Hunt launch ↗

Launched alongside, May 2026

the whole month →
  • Brew ▲900

    Like Claude design for email marketing

    AI · May 2026 · brew.new

  • Parallel agents, diff reviewer, and multi-model comparisons

    Dev tools · May 2026 · kilo.ai

  • StoreClaw▲806

    Grow your store profits with agents that know how to sell

    AI · May 2026 · storeclaw.ai

  • Give your agent a real number and voice to make calls.

    AI · May 2026 · pollyreach.ai

  • Hey HN, Henry here from Cactus. We open-sourced Needle, a 26M parameter function-calling (tool use) model. It runs at 6000 tok/s prefill and 1200 tok/s decode on consumer devices. We were always frustrated by the little effort made towards building agentic models that run on budget phones, so we conducted investigations that led to an observation: agentic experiences are built upon tool calling, and massive models are overkill for it. Tool calling is fundamentally retrieval-and-assembly (match query to tool name, extract argument values, emit JSON), not reasoning. Cross-attention…

    Life & fun · May 2026 · github.com

  • 🌱 Private, quiet space for thinking. Simple app for .md files. - zakirullin/files.md

    Dev tools · May 2026 · github.com