Observed Signal · May 16, 2026 · Product Launch · Source: DEV Community · Impact: 1/5 · Sentiment: Neutral
Developer Builds 1940s Detective Chatbot
A developer, Aniket Mehra, created Noir AI: Dream Detective — a 1940s‑style, cynical chatbot that 'roasts' users' dreams — and published a write-up on Dev.to on May 16, 2026. The app was built as an entry for Baidu's Build with MeDo hackathon using MeDo, a prompt-to-app generative builder. The project couples an ERNIE-based backend with a split-screen vintage UI and a dynamic 'Evidence Board' that performs real-time entity extraction from user input and displays visual sticky notes without page reloads. Mehra highlights that MeDo generated the React/CSS layout from prompts and that prompt engineering was required to tune ERNIE for both persona dialogue and structured entity tagging. A live demo and a Devpost submission are linked in the post.
Developer showcase of a generative app built with MeDo; demonstrates progress in prompt-to-app tooling but has limited impact on the wider AdTech/MarTech industry.
Track Baidu Signals & Market Shifts in Real-Time
Polaris7 autonomous intelligence agents track regulatory filings, primary sources, executive changes, and deal flow 24/7. Create your free Explorer workspace to monitor these entities.
Key Takeaways & Evidence Grounding
- Aniket Mehra built 'Noir AI: Dream Detective' and published the project on Dev.to on 2026-05-16.
- The app was created using MeDo, described as Baidu's generative app builder.
- The system uses an ERNIE model to produce 1940s detective dialogue and perform entity extraction.
- The app implements a real-time 'Evidence Board' UI that automatically adds visual sticky notes for extracted entities as the user types.
- Mehra submitted the project to the Build with MeDo Hackathon and linked a live demo and Devpost submission.
Connected Companies & Entities
2 Entities mappedOntology Mapping & Concepts
Related Market Signals & Shifts
Recent verified developments and strategic activity across this market segment.
Developer Builds Sales-Prep AI Using LLMs and LINE Bot
A developer built a Sales Prep AI accessible via a LINE bot (pre-talk.vercel.app) that takes a company or business-card input, runs web research, and returns a structured report. The system routes light input interpretation to Claude Haiku and heavy analysis/OCR to Claude Sonnet (the author initially used GPT-4o-mini), uses Tavily for web search, and stores reports in Supabase. Engineering challenges included Vercel Hobby's 10‑second timeout (worked around by streaming a heartbeat), hallucinations (mitigated via fact/inference separation and an output gate), official-site detection, and agent sprawl (reduced by tightening agent roles). Measured API cost per research run is roughly $0.40 (range $0.24–$0.52). The post is a technical case study describing architecture, costs, and practical mitigations rather than a commercial product announcement.
Developer Builds Kikar AI Messaging Platform
A developer, Bhavya Sharma, published a post describing Kikar — an AI-powered social messaging project that creates digital versions of users which learn from conversations and emulate individual styles. The post outlines the project's goals, desired future features (improved AI memory, voice, UI polish), the tech stack (Next.js, React, TypeScript, Tailwind CSS, Supabase, Capacitor, Groq API), and links to the project's GitHub repository. The article is a personal project write-up rather than a commercial product announcement.
Self-taught builder treats AI as partner, launches AI receptionist
A self-taught developer describes learning to build production software in four months by treating a generative AI as a partner rather than a tool. He implemented a safety-focused harness around a frontier model that enforces honesty via automated checks: blocked unproven claims, 89 enforcement hooks, cross-checks by rival models, and an immutable memory with 286 self-modification commits. The work produced Neverclosed, a live 24/7 AI receptionist that answers calls and website chats and books appointments. The author also earned $100 from participating in an AI red-teaming exercise. He published this post (verified before writing) to share the technical approach and lessons learned while building publicly.
Track Real-Time Market Signals & Shifts
Set up custom watchlists to receive automated, evidence-grounded executive digests whenever material signals or shifts occur across your tracked landscape.