Is the high level instruction compiled to a flowchart under the hood? If so maybe a conversational interface is another layer on a flowchart and not an alternative? Overall it makes sense that flowcharts are limiting when they get big, yes. Product looks cool congrats on the launch.
No, the instructions are not compiled into a flowchart under the hood. We use OpenAI’s agent SDK and use handoffs as a mechanism to transfer control between agents.
There are 3 types of agents in Rowboat:
1. Conversational agents are ones which can talk to the user. They can call tools and can choose to handoff control to another agent if needed.
2. Task agents can’t talk to users but can otherwise call tools and do things in a loop - they are internal agents.
3. Pipeline agent is a sequence of task agents (here the transfer of control is deterministic).
For instance, if we build a system for airline customer support, there might be a set of conversational agents each for different high level topics like ticketing, baggage etc. and internally they can use task and pipeline agents as needed.
At Coherence, we're building the infrastructure layer that enables customers to make sense of the data in your product using AI agents. Our product enables you to get a chat interface live in your existing application, with access to all your current backend endpoints and APIs, in less than an hour.
We’ve spent the last few months talking to AI-native teams across fintech, health, legal, and other high-stakes domains. A consistent theme came up: while everyone is investing heavily in LLMs — evals, prompt/model tuning, model experimentation — almost no one has a clean way to integrate human review into production workflows.
Most teams are stuck cobbling together brittle systems: Slack alerts when models are uncertain, spreadsheets to track review outcomes and result quality, manual tagging and triage by engineers, business teams waiting on dev cycles to change rules and integrations.
We built Coherence to solve this. It’s a control plane for production AI that brings structured human oversight into your app with just one simple API call. With Coherence, teams can: Route edge cases to the right human reviewer in real-time, let business users own the rules and thresholds with no dev time required, monitor what’s being flagged and how it’s resolved, improve AI behavior over time via structured feedback loops.
If you’re deploying AI where correctness matters — and spreadsheets aren't cutting it — we’d love your thoughts. We're currently looking for more design partners and early users to help us shape a great product!
We've built a data generation studio that creates robust test datasets for testing their LLM applications in just minutes. While working with hundreds of engineering teams on DevOps automation, we discovered a critical gap: everyone wants to build AI products, but acquiring, labelling, and organizing test data for tasks is a massive challenge.
The current approaches to creating "golden datasets" for LLM testing are either infrastructure-heavy (observability-based) or time-consuming (manual creation). Many teams end up relying on intuition-based development, which leaves crucial questions unanswered about model selection, edge cases, and performance optimization.
Our solution generates comprehensive, realistic test datasets tailored to your specific use cases. You provide context (existing examples, domain information, or system prompts), and it creates robust test data that helps you:
- Balance distribution across your test suite including edge cases
- Evaluate prompt effectiveness across various scenarios
- Compare and optimize model selection
- Identify and handle edge cases systematically
- Assess performance across diverse use cases
- Support rapid R&D experimentation with different data shapes
We're launching this as the first data studio focused on giving AI engineers both speed and precision in their development workflow. If you're building AI products, we'd love your feedback on our approach to making LLM testing more reliable and efficient.
