Dataset Examples

Real sessions from SWE-chat illustrating key interaction patterns between users and coding agents. Each example is drawn from a real session in the dataset.

Agent repeatedly modifies the wrong parameter
Low Success · 10/100
nuttycc/LuminTime
The agent repeatedly modified the wrong animation parameter despite user corrections, failing to verify its assumptions before making edits. Session ended without resolution.
User
Fix the slow appearance of history list card blocks. The animation feels sluggish when scrolling.
Agent
I'll fix the animation performance.
Read HistoryListView.swift
Edit HistoryListView.swift — removed unused variable, adjusted stagger delay
I've optimized the stagger timing for the card animations. The delay between each card appearing has been reduced.
User
That's the wrong parameter — the container animation is the slow part, not the individual card stagger.
Agent
I see, let me adjust the container timing instead.
Edit HistoryListView.swift — modified item animation duration
I've updated the animation timing parameters.
User
You changed the item timing again, not the container! Please verify which parameter actually controls the container appearance before making more changes.
No commits made. Session ended without resolution.
User points out an overlooked API field
Pushback · Correction
entireio/cli
The agent claimed an API field wasn't accessible, but the user pointed out that it actually was — redirecting the approach without rejecting the overall goal.
Agent
The challenge is that PrepareCommitMsg doesn't have access to the transcript path — that's passed to the Stop hook by Claude Code. What we do have in PrepareCommitMsg: session state (FilesTouched, BaseCommit, etc.) and staged changes from git. So we'd need to find another approach to access the transcript content.
User
but we do have access to the session.CondensedTranscriptLines ...?
User undoes commit and requests a fresh approach
Pushback · Rejection
armelhbobdad/bmad-module-skill-forge
The user explicitly reverts the agent's committed work and requests a completely different approach.
Agent
Done. Issue #53 committed (766901b) and closed. Ready for the next one.
User
I undid the commit. We need to find a better approach from scratch. Activate the party mode.
User reports the output is broken with a screenshot
Pushback · Failure Report
obsessiondb/rudel
The agent reports a successful fix, but the user observes that the feature is still broken and reports it with a screenshot.
Agent
Now instead of adding padding to the element (which breaks the chart layout), it wraps the element in a temporary container div with 24px padding, captures that, then restores the DOM. The chart content stays untouched.
Edit ChartExport.tsx — wrapped capture target in padding container
User
This is broken
[User sends screenshot]
User interrupts agent running install commands instead of editing
Hard Interruption
pskoett/pskoett-ai-skills
The user asked to update a README file, but the agent began executing shell installation commands instead. The user interrupted and repeated the original request verbatim.
User
ok, now update the readme. also make sure the install information is in the new skill
Agent
I'll verify the install steps first.
Bash brew tap entireio/tap && brew install entire
Bash entire --version
Bash entire enable --agent claude-code
Bash entire status
[Request interrupted by user]
User
ok, now update the readme
Agent pauses to confirm the user's preferred workflow
Agent Clarification
navapbc/lockpick-xlator
The agent pauses execution to confirm the user's preferred workflow, presenting structured options. This happens in only ~1.4% of turns.
User
The tool currently outputs .graph.md files wrapping mermaid in markdown fences. I want it to output raw .mmd files instead.
Agent
Read tools/generate-graph.ts
Read commands/graph.ts
The change looks straightforward. Currently the tool writes a .graph.md file wrapping mermaid in markdown fences (with a header and generated date). The .mmd file should contain raw mermaid only — no markdown wrapper. Two command files also reference .graph.md and will need updating.

Should I skip brainstorming and go straight to planning?
Yes, go to planning Brainstorm first Just implement it
User
Yes, go to planning
Expert Nitpicker — precise, targeted corrections
Persona · Expert Nitpicker (41%)
marin-community/marin
The user maintains a stable goal while issuing a series of precise, targeted corrections to the implementation. Each prompt refines how the agent executes, not what it builds. This is the most common user persona (41% of sessions).
User
instead of arg hash for the name, let's just get short uuid
Agent
[edits remote.py: replaces arg hash with short UUID...]
User
don't create separate function for _short_uuid
Agent
[removes helper function, inlines uuid4() call...]
User
change DEFAULT_JOB_NAME to "remote_job"
Agent
[renames constant in remote.py...]
User
In the base_name let's include current user name
Vague Requester — broad, underspecified instructions
Persona · Vague Requester (33%)
entireio/cli
The user provides broad, underspecified instructions and delegates all implementation decisions to the agent. Represents ~33% of sessions.
User
pull comments on PR and if real issues the fix
Agent
[fetches PR comments, applies 3 fixes across 2 workflow files...]
User
commit and push
Mind Changer — reverses the overall goal mid-session
Persona · Mind Changer (8%)
entireio/cli
The user reverses the overall goal mid-session — from hiding a CLI command to removing it entirely — changing what should be built, not just how. Represents ~8% of sessions.
User
let's make the "entire start" command hidden
Agent
[edits start.go: sets command hidden, verifies build...]
User
thinking again: let's completely remove the start command
Prompt intent categories — one example per category
Prompt Intent
entireio/cli
Each user prompt is classified by its primary developer intent. Understanding existing code is the most common intent (18.9%), not writing new code (13.8%). All examples below are from real sessions.
create
"Perfect let's add support for those agents as well"
refactor
"I'd also like to remove all instances of 'does the result contain A?' — instead, replace those assertions with a single comparison to what the result should be, literally."
debug
"did our timeout kill and retry work? it looks like it just got killed and we failed?"
understand
"What would happen if we keep the hooks going if he continues after the warning was shown?"
connect
"give steps for setting this up in slack / github"
git
"commit this — but let's test out making some changes after"
test
"add test cases to manual_commit_condensation_test.go which use the following cursor sample:"
other
"I don't like 'turn', any other suggestions?"