Engineering perspectives
What our team is thinking about before it becomes code, research, or product.
:format(webp))
Work with us
Join Parloa to build what's next in artificial intelligence. We're always looking to work with the best and the brightest engineers and researchers.
:format(webp))
The latency paradox: Why voice AI speed is a budget, not a target
Parloa believes that for the most natural-sounding conversations, latency in AI agents should be assessed as a budget, not a a set target. Read why.
:format(webp))
Multi-agent architecture: A look inside Parloa’s Subtask Agents
Most multi-agent work leverages supervisor LLMs at the routing layer. Multi-agent work for Voice AI requires an alternative approach. Learn how the architecture differs.
:format(webp))
The hidden layer of personalization in AI agents
Parloa's Agent Architect explains how linguistic style matching is permeating the AI agent space for more personalized customer experiences.
:format(webp))
Agentic software engineering at scale: Parloa’s Claude Kitchen
95% of Parloa's code is written by AI. Learn what made the company transition to agent-written code and how we make it work.
:format(webp))
The engineer, reimagined: AI-driven development at Parloa
AI is rapidly transforming how software gets built at Parloa. Engineers are shifting from writing code to orchestrating AI agents that generate, review, and refine it. In this new model, developers focus less on implementation and more on guiding workflows, setting guardrails, and ensuring quality.
:format(webp))
GPT-5.2 doesn’t just follow instructions, it follows through
There’s a specific kind of model failure we like to track closely. It doesn’t show up in latency graphs or user feedback. It sounds like the system is doing the right thing. It looks like it’s doing the right thing. And yet: the action never happens.
:format(webp))
What happens when calls never end?
Every customer conversation has a rhythm: a start, a middle, and (generally) an end. But what happens when it doesn’t?