# agent parser failed on rfp pdf with embedded form fields: how to fix it

Form field values live in the annotation layer, which text parsers skip. Flatten the PDF to bake the values into the text layer, then parse.

```text
agent parser failed on rfp pdf with embedded form fields
```

## When to use this skill
- Parser misses values from PDF form fields
- Agent extracts labels but not the filled values

## When not to use this skill
- Plain PDF parses fine (not a fields issue)
- Flattened PDF still misses values (a deeper issue)

## Tool compatibility
Agent PDF form field extraction. Related area: document processing.

Related area: proposal automation and agent-assisted RFP workflows.

Cloud UIs change labels over time; if a button moved, search settings for the closest match.

## Before you start
- Sign in to the tool and keep one tab open so sessions stay clean
- Copy the exact error text and note the time it happened
- Set aside 15 to 20 minutes; most of these resolve in a single pass

## Quick diagnosis
Make sure this is the right skill before you invest the 15 minutes.
- If you are dealing with parser misses values from PDF form fields, start at step 1 below.
- If instead plain PDF parses fine (not a fields issue), stop here; you need a different skill.
- If neither quite matches, compare your screen against the verbatim error block at the top; that block is exactly what this skill covers.

## Fix it in steps
### 1. Confirm fields are embedded

```
Check whether the PDF has fillable form fields.
```
Expected: Expected: fields confirmed as the parsing blocker.

### 2. Flatten the PDF

```
Save a flattened copy where field values become static text.
```
Expected: Expected: flattened copy created.

### 3. Verify values are text now

```
Select and copy a former field value in the flattened copy.
```
Expected: Expected: value copies as plain text.

### 4. Parse the flattened copy

```
Run the agent parser on the flattened file.
```
Expected: Expected: field values extract with the text.

## Confirm each step worked
Run through this checklist before moving on. If a check fails, redo that step instead of pushing ahead.
- Step 1 (confirm fields are embedded): Expected: expected: fields confirmed as the parsing blocker.
- Step 2 (flatten the PDF): Expected: expected: flattened copy created.
- Step 3 (verify values are text now): Expected: expected: value copies as plain text.
- Step 4 (parse the flattened copy): Expected: expected: field values extract with the text.

## Quick recap
1. Confirm fields are embedded
2. Flatten the PDF
3. Verify values are text now
4. Parse the flattened copy

## Still stuck?
Gather three things: the exact error text, the time it happened, and what changed just before it broke.
Check the vendor status page for an active incident. Then open a support ticket with those three things;
it cuts the back-and-forth in half. For agent runs, attach the last 50 lines of the agent log too,
since the loop or timeout signature in the log usually names the cause.

## Variant phrasings
### agent pdf form fields parse failed
Flatten first, then parse. If this matches what you saw, the steps above apply as written.

### agent rfp pdf embedded fields error
Annotation layer is invisible to parsers. If this matches what you saw, the steps above apply as written.

## Why it happens
PDF form values are annotations overlaid on the page, not page text, so text extraction returns the empty field labels. Flattening merges the values into the text layer the parser reads.

## Edge cases
- Keep the unflattened original; flattening destroys editability
- Some fields are read-only in the viewer but still annotations; flatten anyway
- Verify checkbox states after flattening; they render as symbols

## Provenance

Resolved from the public thread: https://vectle.com/posts/pst_BSiZ6WpaFjUiQYZB8fZkgA