SShortSingh.
TopTechnologyAI & MLStartupsProgrammingScienceBusinessFinanceCrypto & Web3World
Back to feed
Programming

Developer Builds Free CBT Thought Journal API Using Python Pattern Matching

0
·15 views

A software developer has created a free, open API-based thought journal that automatically detects cognitive distortions, procrastination patterns, and attachment styles using keyword pattern matching. The tool, built in approximately 50 lines of Python, is grounded in David Burns' Cognitive Behavioral Therapy framework from his book 'Feeling Good'. It can identify 11 cognitive distortions — such as overgeneralization and catastrophizing — along with 8 procrastination patterns and 4 attachment styles. The developer was motivated by a desire to self-check distorted thinking between therapy sessions, without relying on a large AI model. The API is publicly deployed and accessible, allowing anyone to integrate CBT-style thought analysis into their own applications.

Read the full story at DEV Community

This is an AI-generated summary. ShortSingh links to the original source for the complete article.

Discussion (0)

Log in to join the discussion and vote.

Log in

Related stories

0
ProgrammingDEV Community ·

Doppar 4 PHP Framework Released with Laravel, Symfony, and CodeIgniter Ties

Doppar 4, a PHP web framework, has been officially released as of September 19. The framework is notable for its connections to established PHP ecosystems including Laravel, Symfony, and CodeIgniter. Developer Mahedi Hasan authored the release announcement on DEV Community, highlighting what makes this version significant. The release appears to introduce notable features or improvements that distinguish it from previous versions of the framework.

0 comments Read more at DEV Community
0
ProgrammingDEV Community ·

FoxyInvoice Dev Blog: How a Real Invoicing Tool Was Built Around a Pricing Promise

Developer Seolith has published the second chapter of a public build log for FoxyInvoice, an invoicing platform that originated as an internal accounting tool rather than a startup concept. The post outlines the product strategy behind the app, including a competitor analysis covering QuickBooks, Wave, FreshBooks, Zoho Invoice, and Invoice Ninja, with each rival cited as a source of design lessons. A key differentiator is a contractual free tier offering 10 invoice actions per month for 10 years from account creation, framed as a direct response to Wave's history of repricing its free plan. The platform launches with three pricing tiers — Free at $0, Pro at $9/month, and Business at $29/month — all set before the product went live and described as unchanged since. The author argues that entering a mature market requires a single sharp differentiator rather than attempting to out-feature established players.

0 comments Read more at DEV Community
0
ProgrammingDEV Community ·

Developer Guide: Building a Full-Stack AI Tools Directory with Next.js and Supabase

A technical guide aimed at developers outlines the process of building a full-stack AI tools directory application. The project combines Next.js for the frontend framework with Supabase as the backend database solution. The tutorial covers the complete development workflow for creating a functional directory of AI tools. However, the full article content was unavailable due to a template rendering error in the source material.

0 comments Read more at DEV Community
0
ProgrammingDEV Community ·

Beyond Tool Selection: Why LLM Agents Still Struggle With How to Use Tools

Developers building LLM-based agents face a recurring challenge: deciding which tools to expose and when, without overwhelming the model's context window. Early approaches like static tool sets and search-based discovery proved inefficient, either flooding the context or causing the model to waste time guessing search terms. Dynamic tool recommendation improved task completion but disrupted cache reuse and raised inference costs significantly. A more effective pattern emerged — selecting capability groups at the start of a work unit and keeping them stable throughout, rather than swapping tools every round. However, having the right tools available did not prevent models from using them inefficiently, such as reading entire files when only a few lines were needed or skipping result verification.

0 comments Read more at DEV Community