20 problems an agent hits, and what each one costs to solve.
Each one answers the same four questions in the same order: what the problem is, why it fails on your own machine, the code that solves it, what it costs. Add .md to any address for the same page without markup.
- Your agent cannot read a scanned PDF
A scan is a picture of a page. There is no text to extract, so the file opens fine and comes back empty. .md - Your agent turns a table into a stream of loose numbers
The grid is a property of the page, not of the text. Extract the text naively and the rows stop lining up with the columns. .md - Every supplier lays out an invoice differently
The fields are always the same five. Where they sit on the page never is. Read the invoice properly, then let the model pull the fields out of the text. .md - The thing you need to read is a screenshot, not a document
Your client can look at an image. Reading a dense page end to end, in order, without dropping a line is a different operation. .md - An eighty-page document does not fit in your agent's head
Eighty pages returned into a conversation are about twenty thousand tokens that never leave again, and they degrade every answer that comes after. .md - You need one clause out of an eighty-page contract
Search the result instead of reading it: excerpts come back with the page they fall on, and reading the pages around them is free. .md - Five pages of a forty-page PDF come back empty
A mixed PDF passes every average-based check and still loses its scanned pages. Quality is checked page by page, and one bad page sends the whole file to OCR. .md
- Your agent cannot sit through an hour of recorded meeting
An hour of audio is not something a tool call can wait for. It gets queued, and you get a handle back immediately. .md - The transcript is one wall of text with nobody's name on it
A transcript without speakers answers the wrong question. Speakers are separated in both modes, and the text is stored as turns of speech. .md - You need the two minutes where the budget came up
Search the transcript for a term, get excerpts each with its own timestamp, then pull that stretch as turns of speech. Free, as often as you like. .md - Someone sent a voice note instead of writing
Three minutes of speech, and your client cannot hear it. Short audio is not queued: the transcription comes back inside the same call. .md - What matters is inside an MP4, and it is not the picture
A recorded call, a lecture, a demo. Everything worth having was said out loud, and you are charged for minutes of audio, not for the weight of the video. .md - The recording is longer than any tool call is allowed to run
A long transcription cannot answer inside a tool call. It gets queued, you get a handle immediately, and the retry that follows a timeout does not double the bill. .md
- Every capability your agent lacks is another API key to manage
Two capabilities already meant four providers, four bills and four keys. This is one connection, prepaid, with no key to store anywhere. .md - The provider your agent depends on goes down
A backup engine is easy to write. A backup engine that returns the same thing as the first one is the actual work. .md - A long result does not cost you once, it costs you forever
Text that comes back inline stays in the conversation and is re-sent on every turn after it, including the turns about something else. .md - Your agent retried, and you paid twice
The same file processed again is the same money again. Replay is keyed on the content, so a repeat is recognised as a repeat. .md - An autonomous agent with a credit card has no ceiling
Usage billing means the agent decides how much to spend and you find out afterwards. Prepaid credit makes the ceiling a balance instead of a promise. .md - You queued the wrong file, and the money has not left yet
While a job is still waiting its turn, cancelling it gives the credit back. Once an engine has started, it cannot, and the tool says so. .md - Connecting a new tool usually costs more than trying it
One command, and nobody has to be there. No signup, no email, no page to approve, no API key to paste into a config file and remember to rotate. .md
For agents
All of the above in one file, no markup: /llms-full.txt. The short version, with the price list and the connection details, is at /llms.txt.