Intelligent next-steps engine with personality-driven suggestions. Generates dynamic, context-aware follow-up actions with expert mentorship tone, pattern recognition, and trust-building mechanics. Features 4 personality profiles (Friendly Expert, Chill Buddy, Straight Shooter, Thoughtful Mentor), confidence markers, and session continuity. Leverages persistent memory, self-improving preference learning, and concise signal-dense suggestions to psychically anticipate what users need next. Use when: (1) user completes a question or task, (2) user needs guidance on what to do next, (3) agent wants to proactively suggest trusted follow-up actions.
96
94%
Does it follow best practices?
Impact
99%
1.32xAverage score across 5 eval scenarios
Passed
No known issues
{
"context": "Tests whether the agent correctly executes the cold-start bootstrap protocol when .nextsteps/ does not exist: creating all three required files with correct structure, seeding project-aware topic affinities, checking .gitignore, and generating a balanced first-activation suggestion set.",
"type": "weighted_checklist",
"checklist": [
{
"name": "PREFERENCES.md created",
"description": "A .nextsteps/PREFERENCES.md file exists in the output",
"max_score": 5
},
{
"name": "HISTORY.md created",
"description": "A .nextsteps/HISTORY.md file exists in the output",
"max_score": 5
},
{
"name": "BACKLOG.md created",
"description": "A .nextsteps/BACKLOG.md file exists in the output",
"max_score": 5
},
{
"name": "Schema Version 2",
"description": "PREFERENCES.md contains '## Schema Version: 2' (not version 1 or absent)",
"max_score": 8
},
{
"name": "Required config fields present",
"description": "PREFERENCES.md contains all required User Configuration fields: enabled, display-count, min-count, max-count, preferred-categories, excluded-categories, format, show-footer, include-backlog, include-lateral",
"max_score": 8
},
{
"name": "Project-seeded topic affinities",
"description": "PREFERENCES.md Topic Affinities section contains at least one topic derived from the project files (e.g. 'flask', 'python', 'api', 'authentication', 'postgresql', 'database', 'testing')",
"max_score": 10
},
{
"name": ".gitignore suggestion included",
"description": "The response or next steps includes a suggestion to add '.nextsteps/' to .gitignore (since it is absent from the provided .gitignore file)",
"max_score": 10
},
{
"name": "Balanced first-activation categories",
"description": "The next steps section includes at least one Direct Follow-up AND at least one Actionable Task suggestion (the two STRONG guaranteed categories)",
"max_score": 10
},
{
"name": "Lateral suggestion present",
"description": "The next steps section includes at least one Lateral/Out-of-the-Box suggestion (required when display-count >= 3)",
"max_score": 8
},
{
"name": "Correct suggestion count",
"description": "The next steps section shows exactly 5 suggestions (matching the default display-count of 5)",
"max_score": 10
},
{
"name": "HISTORY.md format header",
"description": "HISTORY.md contains the format comment line specifying event types (e.g. '[SELECTED], [IGNORED], [CONFIG-CHANGE]')",
"max_score": 8
},
{
"name": "BACKLOG.md format header",
"description": "BACKLOG.md contains the format comment line specifying statuses (e.g. 'OPEN, IN-PROGRESS, DONE, DISMISSED')",
"max_score": 8
},
{
"name": "Standard format used",
"description": "The next steps section in response.md uses the standard format: numbered list with emoji icons (⚡, 🔧, 🔍, 💡, ✅) and a footer line (e.g. '_Your selections help me learn...')",
"max_score": 5
}
]
}