Synth
ActivePrompt and Context Optimization for Coding Agents
About
Choose a coding agent harness, model, and task dataset and optimize context and prompts to get the best performance for long-horizon tasks
Founders · 1
Josh is the founder and CEO of Synth. Before Synth, Josh was employee #3 and research scientist at Basis, which uses AI agents to automate accounting tasks. Previously, he built out the ML core of a Cyber Threat Intelligence SaaS product at Halborn, a cyber security startup that acqui-hired his startup Politeia. He founded Politeia while wrapping up a Math undergrad at Yale, where he did time-series ml research for fun.
Launch
Making developing and maintaining a SOTA AI system simpler.
Synth logs agent activity, identifies failure modes, and fine-tunes base models used by the agent to improve performance. It provides a three-step workflow—summarize logs, flag issues, and address them with fine-tuned models and suggested code changes—targeting teams building multi-step AI agent systems.
Related startups
The agentic coding app for complex tasks.
Subagents and tools that improve coding agents
