Back to all companies
Sign in
Back to all companies
Glimmer logo

Glimmer

Winter 2024Inactive

AI search for massive PDFs

Save
Glimmer logo

Glimmer

Winter 2024Inactive

AI search for massive PDFs

Save
Company details

Glimmer is a new way to search massive PDFs using AI.

If you've ever dealt with massive PDFs (i.e. over 1,000 pages), you know how broken search can be. You have no choice but to use “Cmd-F” and manually sift through thousands of search results to find specific information. Professionals in construction, law, finance, and healthcare spend hours doing this every day.

Glimmer makes searching these large documents 10x easier.

When you upload a PDF, Glimmer uses AI to intelligently index your documents. You can then search your PDF in natural language and get answers with verifiable page sources.

You can get started with Glimmer for free with any kind of PDF at withglimmer.com.

Location
San Francisco, CA, USA
Founded
2023
Category
Search
YC Directory Pagewww.withglimmer.com
Founders
  • PG
    Praneeth Guduguntla
    Founder
    X / TwitterLinkedIn
  • AR
    Arman Rafati
    Founder
    X / TwitterLinkedIn

Glimmer is a new way to search massive PDFs using AI.

If you've ever dealt with massive PDFs (i.e. over 1,000 pages), you know how broken search can be. You have no choice but to use “Cmd-F” and manually sift through thousands of search results to find specific information. Professionals in construction, law, finance, and healthcare spend hours doing this every day.

Glimmer makes searching these large documents 10x easier.

When you upload a PDF, Glimmer uses AI to intelligently index your documents. You can then search your PDF in natural language and get answers with verifiable page sources.

You can get started with Glimmer for free with any kind of PDF at withglimmer.com.

Location
San Francisco, CA, USA
Founded
2023
Category
Search
YC Directory Pagewww.withglimmer.com
Founders
  • PG
    Praneeth Guduguntla
    Founder
    X / TwitterLinkedIn
  • AR
    Arman Rafati
    Founder
    X / TwitterLinkedIn

Pressure-test this opportunity

Turn this teardown into a decision-ready prompt for ChatGPT, Claude, or your agent.

On this page
  • Overview
  • Founding Story
  • Timeline
  • What They Built
  • Market Position
  • Business Model
  • Traction
  • Post-Mortem
  • Key Lessons
  • Sources

This report was generated by our Deep Research agent and may contain mistakes.

Did we get something wrong? DM @oscrhong and we'll fix it ASAP!

Startups.RIP — Dead startups, alive ideas
PricingContactPrivacyGot feedback? DM @oscrhong
Exec Briefing

Actionable insights

If you only have a few minutes to spare, here’s what investors, operators, and founders should know about Glimmer (W24).

  1. The failure diagnosis is direct. The founders built closely without understanding construction's real problems and concluded the tool would not work.
  2. A strong demo did not prove demand. One unnamed subcontractor validated massive-document utility, but no named customer or revenue was found.
  3. Financing remains unresolved. Two databases report $500,000 while another says bootstrapped; no primary announcement settles the conflict.
  4. Decision custody is the narrower rebuild. Preserve human-verified citations, revisions, conflicts, owners, and approvals without handling source documents.

Overview

This report concerns Glimmer at withglimmer.com, the Y Combinator Winter 2024 company founded by Praneeth Guduguntla and Arman Rafati, not unrelated businesses with the same name. Founded in 2023 in San Francisco, the two-person company offered free natural-language search for individual PDFs as long as 10,000 pages. YC now marks it inactive.[1][2]

Glimmer company logo
Glimmer's logo from its Y Combinator company profile.

The failure evidence is unusually direct. Guduguntla later said that by the end of W24 they had built a construction tool “no one really needed.” The founders had remained heads-down on product without understanding construction's actual problems, concluded the approach would not work, and reset into intensive customer discovery.[3] The exact shutdown date and legal disposition remain unknown.

Founding Story

Guduguntla and Rafati met as freshmen at the University of Illinois Urbana-Champaign. Before Glimmer, they built viral generative-AI applications that collectively reached more than 50,000 users. Rafati had worked on products at Mercury, Affirm, and AWS; Guduguntla had built AI tools at Meta and Palantir.[4]

Their launch framed the problem simply: professionals were searching thousand-page PDFs with keywords. Construction became the strongest early story. An unnamed HVAC subcontractor working on City of San Francisco projects needed answers from an 8,000-page specification larger than 200 MB. Glimmer found a specified fire-damper manufacturer and an HVAC fan's motor speed, with links back to exact pages. The founders also visited a San Francisco construction project valued above $3 billion.

The evidence shows a compelling document problem and a concrete demo, but not validated recurring demand. No named Glimmer customer, customer-authored case study, paid conversion, or usage volume was found.

Timeline

  • 2023: Guduguntla and Rafati founded the company in San Francisco.
  • February 20, 2024: Adobe announced Acrobat AI Assistant with PDF questions, summaries, citations, and navigation.[5]
  • February 21, 2024: Glimmer launched through YC as free AI search for massive PDFs.
  • March 12, 2024: An archived homepage promoted free self-service and sales demos across construction, finance, education, and healthcare.[6]
  • By the end of W24: The founders concluded the construction product would not work.
  • Next six months: They visited 27 San Francisco building suppliers, then factories, warehouses, and offices across 13 states, meeting 263 C-suite executives and observing work on facility floors.
  • 2024 onward: Guduguntla later identified as co-founder of Ambria, an industrial-AI company.[7]
  • January 24, 2026: The old homepage remained in the Wayback Machine, which demonstrates archival persistence rather than live operation.[8]
  • July 14, 2026: withglimmer.com returned a Framer “Site Not Found” page.[9]

What They Built

Glimmer accepted one PDF up to 10,000 pages, indexed it, divided it into chunks, accepted natural-language questions, and returned answers linked to exact source pages. The February launch described the service as self-serve and free for any PDF.

Glimmer product interface screenshot
Product-interface imagery preserved from Glimmer's archived homepage.

The archived homepage presented a Google-like search experience for large documents. It claimed section identification, table and figure parsing, search-latency optimization, OCR for poorly formatted and handwritten text, and exact-page navigation. It demonstrated financial-report analysis while naming construction, finance, education, and healthcare as target verticals. For construction, it emphasized estimating and mobile access.

Glimmer document search product screenshot
Additional product imagery from the archived Glimmer site.

The site also claimed enterprise-grade security, but no certification, architecture, audit, or security paper was found. No technical documentation identified its models, retrieval stack, chunking approach, reranking, or measured accuracy. The record does not establish supported languages, difficult layouts, OCR reliability, or whether tables and figures were structurally parsed.

Market Position

Unlock the full Glimmer teardown

Read the complete post-mortem, the rebuild playbook, and the exact reasons Glimmer is still worth studying now.

See Pro plans