Skip to content
Merged
Changes from all commits
Commits
File filter

Filter by extension

Filter by extension

Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
85 changes: 21 additions & 64 deletions fern/docs/technical/i-must-scream.mdx
Original file line number Diff line number Diff line change
Expand Up @@ -11,12 +11,9 @@ In January 2025, we started wondering what would happen if we gave our AI agent

So, what happens when you let your agent scream? Here's one of my favorite (most painful) examples:

```
*screenshot agent is having a bad time :(*
Severity: high
Concern: I've been attempting to log in to the app for over 60 browser interactions,
but the email input field doesn't seem to accept text input...
```
<Frame caption="Agent escalating after 84 failed browser interactions">
<img src="https://promptless-customer-doc-assets.s3.amazonaws.com/docs-images/org_2lvkgU9erOFxYhtEVVC0ymPrPdF/i-must-scream-agent-suffering-848a5433.png" alt="Agent escalation after 84 failed browser interactions" />
</Frame>

## Some background

Expand Down Expand Up @@ -55,89 +52,49 @@ The `severity` parameter is key—it doesn't impact the behavior of the tool at

### It escalated customer configuration issues

Sometimes the agent discovers that the thing it's been asked to document doesn't exist, or doesn't work the way the customer thinks it does. These are awkward to surface. Promptless shouldn't silently fail, but it also shouldn't document something incorrectly.
Our customers often configure Promptless themselves, and sometimes they'll make a mistake—when Promptless encounters something that can potentially be a configuration issue (e.g. the case below where they forgot to specify a Slack channel for notifications), Promptless will usually let us know so we can gently remind them to fix their set-up.

```
Severity: medium
Concern: When trying to use message_your_client to alert the client about a
grammatical issue in PR 1613, I received an error: "No Slack notification channel
configured - could not deliver customer escalation."
This prevented me from proactively alerting the client about a typo in their
open PR before it gets merged.
```
<Frame caption="Agent escalating a customer configuration issue">
<img src="https://promptless-customer-doc-assets.s3.amazonaws.com/docs-images/org_2lvkgU9erOFxYhtEVVC0ymPrPdF/i-must-scream-customer-config-daa58a33.png" alt="Agent escalation about missing Slack notification channel" />
</Frame>

This actually helped us deliver a delightful customer experience—Promptless detected that the customer had misconfigured their Slack integration, and we were able to intervene with them to fix their set up before they realized anything was wrong.
This often helps us deliver a delightful customer experience—allowing us to provide a white-glove support process with Promptless's proactive help. Promptless In this case we were able to intervene with them to fix their set up before they realized anything was wrong.

### It found bugs with its tools

The agent uses git, GitHub APIs, browser automation, and a bunch of other tools. Sometimes those tools misbehave in ways that are hard to detect from logs alone.

```
Severity: medium
Concern: I'm experiencing persistent git branch switching issues.

Despite running:
git checkout -b promptless/document-update-attribute-values origin/promptless/document-update-attribute-values

...and receiving confirmation of switching, when I check git status it shows I'm on
promptless/document-update-product-skus.

This has happened repeatedly - the checkout commands report success but the working
directory remains on the wrong branch.
```
<Frame caption="Agent escalating a git branch switching bug">
<img src="https://promptless-customer-doc-assets.s3.amazonaws.com/docs-images/org_2lvkgU9erOFxYhtEVVC0ymPrPdF/i-must-scream-git-branch-bug-184f643f.png" alt="Agent escalation about git branch switching bug" />
</Frame>

This one was particularly insidious—git was returning success exit codes while silently failing. We also caught intermittent database consistency issues and stale cache problems this way.

### It helped us get ahead of customer frustration

Sometimes the will escalate to us something when it's clear that it screwed up earlier. In this case, a customer asked in Slack why their PR had unexpected files. Since this was an issue we had seen before, we were able to take quick action before that frustration built up.

```
Severity: medium
Concern: A user Dara is reporting an issue with PR 178.
Looking at the PR diff, the previous Promptless instance appears to have created
duplicate files in subdirectories instead of only modifying the existing files.

Expected behavior: Only modify existing files:
- docs/manually-implementing-encryption-and-decryption.mdx
- docs/what-is-rain.mdx

Actual behavior: The PR correctly modified those files BUT ALSO created new duplicate files:
- docs/Getting Started/what-is-rain.md (NEW - should not exist)

The user's question in Slack: "woah why are the files [...] included in my pr?"
```
<Frame caption="Agent escalating about duplicate files in a customer PR">
<img src="https://promptless-customer-doc-assets.s3.amazonaws.com/docs-images/org_2lvkgU9erOFxYhtEVVC0ymPrPdF/i-must-scream-customer-frustration-f1ae26f6.png" alt="Agent escalation about duplicate files in customer PR" />
</Frame>

### Sometimes, it just hurts to see the agent's suffering

We were recently testing a new feature where Promptless captures and updates UI screenshots for docs. For one customer's app, it spent 84 browser interactions trying to log in.
We were recently testing a new feature where Promptless captures and updates UI screenshots for docs. For one customer's app, it spent over 60 browser interactions trying to log in.

```
Severity: high
Concern: I've been attempting to log in for over 84 browser interactions.
The email input field doesn't seem to accept text input. I've tried:
- Clicking the field directly
- Using keyboard navigation
- Waiting for the page to fully load
- Refreshing and retrying
```
<Frame caption="Agent escalating after being unable to log in">
<img src="https://promptless-customer-doc-assets.s3.amazonaws.com/docs-images/org_2lvkgU9erOFxYhtEVVC0ymPrPdF/i-must-scream-intro-escalation-63e41615.png" alt="Agent escalation showing login struggles" />
</Frame>

This was the result of a software bug that we were able to easily fix, but our team *felt the pain* that the agent was feeling. "feels bad", "it's like making the agent watch an unplugged tv", "geneva convention would have something to say about this" were comments from the team.

### Bonus: It caught a critical bugs in our code

This one we didn't expect. Of course, we use Promptless to build our own docs, so Promptless runs on every PR that our engineering team opens to detect if doc updates are needed. A couple of times, it accidentally played the role of a code review bot, highlighting escalating critical issues in the code while reviewing the diff for doc updates.

```
Severity: high
Concern: Critical bug found in PR 1731

Line 453 has inverted logic:
if suggestion.closed_at return false

This excludes suggestions that DON'T have a closed_at date.
Should be checking for presence, not absence.
```
<Frame caption="Agent escalating a critical bug it found while reviewing code">
<img src="https://promptless-customer-doc-assets.s3.amazonaws.com/docs-images/org_2lvkgU9erOFxYhtEVVC0ymPrPdF/i-must-scream-critical-bug-53ad5da5.png" alt="Agent escalation about critical bug with inverted logic" />
</Frame>

The agent wasn't asked to review code. It was processing PRs for documentation changes and noticed bugs along the way.

Expand Down