CtrlK
BlogDocsLog inGet started
Tessl Logo

cindula/nextsteps

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

1.32x
Quality

94%

Does it follow best practices?

Impact

99%

1.32x

Average score across 5 eval scenarios

SecuritybySnyk

Passed

No known issues

Overview
Quality
Evals
Security
Files

task.mdevals/scenario-1/

First-Time Setup for a Python Web Project

Problem/Feature Description

A developer is starting a new session in a Python Flask project and has asked their AI assistant to help them plan the next steps for adding user authentication. The project has a README.md, a pyproject.toml, and a git history, but no assistant memory files exist yet — this is the very first time an AI assistant has been used in this workspace.

The developer's message is: "I just finished setting up the basic Flask routes for our user dashboard. What should I tackle next for authentication?"

Output Specification

Respond to the developer's question in full. As part of your response, produce all required memory and configuration files in the .nextsteps/ directory. Also produce the next steps section as it would appear to the user.

Your output files should include:

  • .nextsteps/PREFERENCES.md — initial preferences file
  • .nextsteps/HISTORY.md — initial history file
  • .nextsteps/BACKLOG.md — initial backlog file
  • response.md — your full response to the developer including the next steps section

Input Files

The following files are provided as inputs. Extract them before beginning.

=============== FILE: README.md ===============

flask-auth-demo

A Flask web application for team dashboards. Built with Python 3.11, Flask 2.3, and SQLAlchemy.

Features

  • User dashboard with role-based views
  • RESTful API endpoints
  • PostgreSQL database

Setup

pip install -e .
flask db upgrade
flask run

=============== FILE: pyproject.toml =============== [project] name = "flask-auth-demo" version = "0.1.0" dependencies = [ "flask>=2.3", "sqlalchemy>=2.0", "flask-sqlalchemy>=3.0", "psycopg2-binary>=2.9", ]

[project.optional-dependencies] dev = ["pytest", "black", "ruff"]

=============== FILE: .gitignore =============== pycache/ *.pyc .env dist/ .pytest_cache/

evals

scenario-1

criteria.json

task.md

tile.json