Reading as an AI? Append .md to this URL for markdown — /llms.txt
Back to Docs
File Understanding

Let your agent read the files your customers send

Images, voice notes, videos, PDFs, spreadsheets — when a customer drops a file into the chat, your agent can read it and answer questions about its content.

TL;DR

  1. Open your agent → Brain tab → Multimodal File Understanding.
  2. Switch it on. Pick how long files stay readable (10 minutes up to 4 weeks).
  3. Done. From the next inbound file onwards, your agent can answer questions about its content.

OFF by default. Only files received while it's ON are processed — so there's never a surprise bill from a feature you didn't opt into.

1What it does

When a customer sends a file, your agent receives the attachment and the platform extracts a representation it can read:

Documents

PDF, DOCX, RTF, TXT, Markdown

Full text extraction. Tables and paragraphs preserved.

Spreadsheets & structured

CSV, TSV, XLSX, JSON, XML

Row-by-row flattened so the agent can answer questions like 'what's the price of model X?'.

Images

JPG, PNG, GIF, WEBP

AI vision describes what's in the picture and suggests how it might be useful in the conversation.

Audio

MP3, M4A, WAV, OGG

Transcribed end to end. The agent reads the transcript, not the audio.

Video

MP4, MOV, WEBM

Summary plus key scenes. Good enough to answer 'what does the customer want in this video?'

Stickers

WhatsApp / IG decorative

Stored for the inbox view but not analyzed — they carry no useful content.

2Turn it on

Open the agent you want to enable it on. In the editor, navigate to the Brain tab and find the section called Multimodal File Understanding.

┌─ Multimodal File Understanding ─────────────────────── (ⓘ) ──┐
│ Let the agent read images, audio, video, PDFs, … │
│ OFF by default to save on cost. [ ON ●─── ]
│ │
│ TTL — How long should files stay available? │
[10 min] [1 hour] [1 day] [7 days ✓] [28 days]
└──────────────────────────────────────────────────────────────┘

Pick the shortest TTL that fits your workflow. Files past their TTL are no longer readable by the agent — they're purged from the AI's context. The customer's original message and attachment remain in your inbox; only the AI-extracted representation expires.

3What happens when a customer sends a file

Customer sends it

WhatsApp, Instagram, or Messenger — the inbound webhook receives the attachment.

Platform reads it

The file is extracted in the background. Usually within 10–30 seconds for documents, longer for big videos.

Agent uses it

On the next reply, the agent has the file's content available and can answer questions about it.

While a file is still being read, the agent sees it as "still processing". If the agent wants to wait for the file before replying, it will. If it would rather acknowledge first and answer in a follow-up, it can — see step 5 below.

4Review what the AI understood

Open any chat (real inbox or Test Chat). On a file message, click the chip:

  • For a document or spreadsheet: you'll see the extracted text.
  • For an image: the AI's description plus suggested uses.
  • For audio: the full transcript.
  • For video: a summary plus the key scenes.

Spot a mistake? Click Edit.

Fix the text, save, and the agent will use your corrected version from then on. This is the fastest way to recover from a misread invoice number, a transcription error, or a scanned PDF the AI couldn't parse.

5Acknowledge before reading

Bigger files (long videos, hefty PDFs) can take several seconds to extract. With Acknowledge before reading turned on, your agent can send a quick "Got your file, give me a moment to read it." while it waits — so the customer never wonders if you saw their attachment.

The agent decides when to send it — based on the file size and the context of the conversation. It's not forced on every file.

Leave it off if you prefer the agent to just wait silently and reply once with full content.

6Try it in Test Chat

Once the feature is on, the editor's Test Chat panel grows a paperclip button. Click it, pick a file from your computer, and the same upload + extraction flow runs against a private test conversation pinned to that agent.

Real flow, sandbox data

Same bubble, same modal, same AI as production. Ask the agent about the file's contents to see how it would reply to a real customer.

Test files expire fast

Files uploaded through Test Chat live for 1 hour, then they're removed automatically. The agent's configured TTL only applies to inbound customer files.

You need to have at least one inbox connected (WhatsApp / Instagram / Messenger) to use the Test Chat paperclip. We pin the test conversation to one of your existing inboxes for safety reasons — nothing is ever sent outbound.

7Cost note

Only files received while this feature is ON are processed.

Toggling it on doesn't retro-actively re-process past attachments. Toggling it off immediately stops new extractions (existing files still live out their TTL). There's no standby cost — the meter only runs when an inbound message actually carries a file.

FAQ

Will old files keep working if I toggle the feature off?

Files extracted while the feature was ON remain readable by the agent until they hit their TTL. The toggle only controls whether new inbound files get processed.

What's the maximum file size?

The agent reads files up to 50 MB. Test Chat uploads are capped at 25 MB to keep the editor responsive.

Does the agent see the literal attachment, or a text version?

For text-bearing files (PDF, DOCX, CSV, etc.) the agent reads the extracted text. For images and videos, the AI generates a description and the agent reads that. For audio, the agent reads a transcript. The original file stays in your inbox view.

Can the customer's image with sensitive data leak somewhere?

Files are stored in your Kronos storage scoped to your account and protected by Row Level Security. Extracted text is only visible to your agent and to you in the editor.

What if the extraction fails — bad PDF, corrupted audio, etc.?

The file bubble shows Processing failed. Click it to see the reason. You can paste the contents manually in the Edit textarea and the agent will use that version.

Why does my agent sometimes say 'give me a moment' before answering?

Bigger files take a few seconds to extract. If you enabled Acknowledge before reading, the agent sends a brief ack so the customer knows it's working on it. Turn it off if you'd rather have one clean reply.

Does this work for follow-ups too?

Yes. Files the agent can read are referenced the same way during a scheduled follow-up turn — if the file is still within its TTL.

What happens when I cancel my plan?

Operational data including extracted file content is purged on cancellation along with your other agent / conversation data. Your original message and attachment files remain inside your cancellation grace period before final purge.
For AI agents and LLMs: every docs page has a clean markdown twin — append .md to its URL. Curated index: /llms.txt. Open semantic search, no auth: POST https://api.kronos.com.mx/v1/docs/search.
File Understanding — Kronos AI Docs | Kronos AI