01
Conversational AI Voice Agents
Forward-deployed across four production LLM voice-agent launches — solar, real estate, fitness and restaurant ordering — covering campaign setup, CRM integration, UAT and post-launch reliability.
Four projects that show how I work: a latency-bound voice programme run in production, a planner that has to keep its measurements honest, a local-first code mapper, and a fine-tuned model behind a narrow interface.
01
Forward-deployed across four production LLM voice-agent launches — solar, real estate, fitness and restaurant ordering — covering campaign setup, CRM integration, UAT and post-launch reliability.
02
Ask a geospatial question in plain language. A planner selects the right tools, grounds the answer in retrieved context, and returns an analysed map instead of a plausible sentence.
03
A CLI that scans a repository, draws a compact ASCII map, and puts one short, truthful description beside every file and directory — deterministic Python first, a small local model only where prose is worth generating.
04
A terminal-style interface that turns a plain-English request into an executable shell command, served by a Phi-3-mini model fine-tuned with QLoRA.