Momentic Launches AI Agents That Test Web and Mobile Apps by Exploring Them

·5 views

Momentic, a Y Combinator W24 startup, has launched QA agents that autonomously plan, explore, and bug-bash web, iOS, and Android apps to surface defects. Its founders, both former engineers from companies like Robinhood and Retool, built the tool to replace the brittle, hand-maintained scripts typical of Playwright and Selenium. The company's custom agent harness, called Mo, uses a self-organizing graph of parallel sub-agents, each running its own browser or device. In a 60-minute benchmark across four open-source apps, Mo found 269 bugs with 84% precision, far more than Codex's 86 bugs at 86% precision, though at a higher cost per bug.

Read the full story at Hacker News

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

Discussion (0)

Sports betting model's 3,671 predictions failed to beat the bookmaker

A developer logged every probability their sports-betting model produced before matches over 16 days, yielding 3,671 settled predictions. On standard metrics the model appeared strong, with a Brier score of 0.1629 where lower is better. However, when compared against bookmaker probabilities, with the bookmaker's margin removed, on 510 matching predictions, the model did not come out ahead. The author argues that any model comparison needs a clear baseline, a count of paired cases, and confidence intervals. They have published a public repository so readers can reproduce the figures and apply the same evaluation method to other systems, such as classifiers and LLM pipelines.

0 comments Read more at DEV Community

ProgrammingDEV Community ·

claude-seo: A Claude Code MCP Toolkit for Automated SEO Audits

A developer evaluated the open-source claude-seo repository, which exposes 26 SEO sub-skills and 19 sub-agents as MCP tools for Claude Code, as a possible addition to a content automation pipeline. The tool's value lies in pre-filtering crawl and audit data into structured diagnostic categories rather than feeding raw HTML or Lighthouse dumps to the model. Live metrics such as Search Console rankings and Core Web Vitals require separate API credentials, otherwise only synthetic analysis is available. Testing found the schema generation module could hallucinate invalid JSON-LD types, requiring manual Schema.org verification, and the E-E-A-T scoring is heuristic rather than backed by external quality or authority data. The author reports a roughly 40% drop in token use through a relay gateway, but judges the tool best suited as an internal audit smoke test rather than a full competitive SEO solution.

0 comments Read more at DEV Community

ProgrammingDEV Community ·

Developer Unveils State-Machine Replacement for Enterprise IT Governance, Sparking Backlash

The Business Impact Governance Framework (BIGF) has drawn strong reactions across the global IT sector since its release. Its architect has announced that a deterministic queuing system now handles all complaints because of the volume of objections from middle management. The framework replaces manual approval processes with what its creator calls mathematically sound Governance as Code. The complaint queue is organized by job role, including change advisory boards, agile directors, and compliance consultants. The author has since closed the queue, directing further grievances to a null endpoint.

0 comments Read more at DEV Community

ProgrammingDEV Community ·

Docker Extends Deadline for $250 Free Cloud VM Credit Promo to January 31, 2027

Docker has extended the deadline for its promotion offering $250 in free cloud VM credits. The offer can now be claimed until January 31, 2027. The original article, published by Fayaz on DEV Community, announced the promotion and the update. The extension was described as a response to the promo's popularity among developers. Readers are advised to check Docker's official channels for full eligibility terms.

0 comments Read more at DEV Community