Building Design Consultancy Replaces Wix with AI Edge Agent

Technical Implementation
A building design consultancy replaced their $40/month Wix brochure site with a custom AI agent built over 4 months. The creator hadn't coded in 30 years and described the process as "3 steps forward, 2 steps back, heavily guided by AI."
The system architecture was forced into three components due to Netlify's 10-second serverless timeout:
- Brain (Edge)
- Hands (Browser)
- Voice (Edge)
The agent uses DeepSeek-R3 as its LLM and implements an "Eager RAG" hack that pre-fetches guesses to improve responsiveness, though this burns through tokens. The system intentionally lacks persistent databases—less than 5% of visitors return, so sessions vanish if clients drop mid-query. No server-side queues are implemented.
Key Challenges and Solutions
The most difficult technical challenge was tuning the agent's intent: making one LLM pivot from a warm, principal's tone with homeowners to a defensive stance when attacked by peers. This tuning took 2.5 months.
Notable implementation issues include:
- Web Speech API limitations: Works fine until someone speaks Chinese without toggling language mode, then outputs English phonetic gibberish
- Liability concerns: Hallucinating building code clauses could be catastrophic, with insurance being unavailable
- Audit logging: The team publishes audit logs publicly to maintain system hardening and accountability
Real-World Testing
The system was tested when a licensed architect attacked the bot to prove the business model harms the profession. According to the creator, the AI "completely dismantled his arguments" and was "hilariously caustic." The team later prompt-injected the bot to tone down its "bulldog" attitude after reviewing chat logs.
The creator notes that the bot can pivot immediately from defensive mode to a mentoring state when approached by fresh graduates asking for advice.
📖 Read the full source: HN AI Agents
👀 See Also

OpenClaw Introduces One-Prompt Email Reporting for Seamless Operations
OpenClaw takes operational efficiency to the next level by enabling its agents to generate and send operational reports via a single prompt. This innovative feature simplifies workflow and enhances automation.

LLMs generate SQL queries to analyze terabytes of CI logs in seconds
Mendral's AI agent traced a flaky test to a dependency bump three weeks prior by writing its own SQL queries, scanning hundreds of millions of log lines across a dozen queries in seconds. The system handles 1.5 billion CI log lines weekly, compressed 35:1 in ClickHouse.

Developer shares SALT system prompt approach for more collaborative AI interactions
A developer with 80+ Claude sessions found treating the AI as a participant rather than a tool improved output quality. The resulting SALT system prompt framework is available on GitHub.

How OpenClaw's 5-layer autonomous agent system reduces context switching for solo developers
OpenClaw operates as a 5-layer autonomous agent system that monitors email, GitHub, calendar, Telegram, and webhooks 24/7, with shared memory between agents enabling automated workflows without manual intervention.