Visual-first video documents

The visuals of a video —
not just the transcript.

Every other tool hands your AI a transcript and loses the screen — the diagrams, slides, and code where the meaning actually lives. VidLens reads the screen and builds a persistent timeline you can search and question.

One moment, two readings

[04:32]“…the request flows from the API gateway through the message queue — as you can see in this diagram.

Transcript onlywords, no screen
“…as you can see in this diagram.”
on-screen diagram — never captured
The referent is lost. Your AI reads a pronoun pointing at nothing.
VidLenswords + what’s on screen
“…as you can see in this diagram.”
On screen [04:32] · architecture diagram
ClientAPI GatewayKafkaWorkerPostgreSQL
The screen, in words your AI can read — cited to the second.
Who it’s for

Made for the people transcripts leave behind.

The same visual layer, delivered three ways — to your agent, to your notes, and to your channel.

Researchers & developers

Query what was shown on screen, not just what was said.

Every analyzed video becomes a reusable multimodal timeline: speech, visual state, and on-screen text, all cited to the second.

ask · cached timeline
› Where is the architecture explained?

## On screen [04:32]
Architecture diagram:
Client → API Gateway → Kafka
  → Worker → PostgreSQL
Students & learners

Notes that show the whiteboard, not just the words.

Formulas, diagrams, and slides captured as real text and linked to the second they appeared — so you can skim the lecture instead of scrubbing through it again.

lecture-08-bayes.md
## Key moments
- [12:04] Bayes' rule on the whiteboard

<!-- on screen @ 12:04 -->
P(A|B) = P(B|A)·P(A) / P(B)
Creators

An llms.txt for your channel — make your videos readable by AI search.

Publish clean, structured documents of your own videos at stable URLs, so answer engines and agents can find, read, and cite what you made.

/c/maya-chen/llms.txt
# Maya Chen — video documents

- /v/vector-search   Vector Search in Production
- /v/rag-eval        Evaluating RAG, honestly
- /v/chunking        Chunking is the real model
How it works

Analyze once. Ask forever.

Paste a public YouTube link. Gemini reads the video natively, and VidLens keeps the resulting timeline for future questions.

01

Paste a YouTube URL

Submit a public video link. No browser extension, local SDK, or frame upload is required.

02

Gemini builds the timeline

Native video understanding fuses speech, visuals, and OCR into timestamped segments.

03

Ask from the cached index

Stream grounded answers with citations that jump directly to the relevant moment.

VidLens does not fetch or store video bytes. The public URL is passed to Gemini’s native video input.

Anatomy of a VidLens

One recording in. A document your AI can read out.

Summary

A two-sentence TL;DR of the whole recording.

Chapters

The recording split into sections, each with a one-line gist and a timestamp.

On-screen visuals

Diagrams, slides, and charts described in language your AI can read and search.

Timestamped transcript

Every line, speaker-labeled, linked to the second it was said.

On-screen text & code

Slides and code captured as markdown — copy-paste ready.

vector-search-in-production.mdExport .md
# Vector Search in Production
> 18:24 · May 28, 2026 · Maya Chen

## Summary
A pragmatic walkthrough of why naive cosine
search disappoints at scale, and the three
fixes that matter.

## On screen [04:32]
Architecture diagram: Client → API
Gateway → Kafka → Worker → PostgreSQL.

## Transcript
**[03:58] Maya Chen:** If you take one
line home: chunk on structure, not count.

```python
def chunk(doc):
    for s in doc.sections:
        yield s.heading + s.body
```
Persistent video intelligence

Every video analyzed once.

The timeline is cached, so each follow-up reuses the same grounded visual evidence instead of processing the video again.

Try VidLens
// cached timeline segment { "start": 272, "speech": "The request flows…", "visual": "Architecture diagram…", "ocr": "Client → API Gateway → Kafka" }

Give your AI the whole video.

Not just the transcript — the diagrams, slides, and code on screen, as one AI-ready document your agent can call.