1. Collaborative IDE for Building AI Agents 2. At the heart of it, there is a new programming language that merges plain English with concepts like loops, conditional statements and function calling. 3. We also support forking, API deployment and sharing as a hosted app. 4. Think replicate meets replit for Agents with a proprietary programming language.
Cofounder and CEO at Wordware -- an IDE for Natural Language Programming and Agent Orchestration. Previously I cofounded and exited KRISTALIC, which tried to augment the human memory. Before that, I studied Deep Learning at Cambridge. The most interesting fact about me outside of work is that I travelled to 103 countries and was part of multiple high-altitude mountaineering rescue operations in Kyrgyzstan and Nepal. I also do sailing, paragliding, kitesurfing and boxing.
Robert Chandler is a founder & CTO at Wordware. He started his career as an early engineer at a self-driving car startup, Five AI, which was acquired by Bosch. Here he lead the Offline Perception team which accelerated the dev-test cycle through automated ground truthing and was awarded 5+ patents in the process. He has been in the AI space for over a decade since studying Information Engineering at the University of Cambridge.
Wordware is an IDE that enables anyone to build complex AI Agents and applications. Domain experts and engineers can now iterate 20x faster with prebuilt tools, API deployment, tracing, and more.
Currently, prompting is mostly done by engineers inside the code base. This is just a coincidence, and it yields poor quality and a long iteration cycle due to communication overhead with domain experts.
Wordware is the go-to tool for these cross-functional teams. Our clients range from AI tinkerers developing their ideas to large companies using Wordware as their whole LLM backend.
It’s a tool (an IDE) that enables you to quickly build custom AI agents for specific use cases, like legal contract generation, marketing content automation, invoice analysis, candidate screening, generating PRDs, and many more. We call applications built on Wordware ‘WordApps’ because you can create them using natural language—in other words, using words (pun intended).
Our core belief is that the domain expert—not the engineer—knows what good LLM output looks like. For example, lawyers building legal SaaS need to be deeply involved in the process, and working directly in the codebase or going back and forth with engineers isn’t the way to go. Most of our clients are cross-functional teams, including less technical members, who need to collaborate with engineers on LLM applications, such as assessing prompt outputs, and care about the speed of iterations.
We are in production with 7 YC Companies and looking to give other early-stage companies with their AI Stack on fire unreasonable amounts of attention. Start for free or book a demo at www.wordware.ai.
I met Robert (my CTO) at the University of Cambridge. We have both worked with LLMs since BERT and created well-performing stacks before AI Ops was a term. We both have exits in the field.