Webhound

Introducing Webhound Agent: Your AI research assistant powered by the best deep research money can buy. Most deep research products decide for you when to stop — and since they're subscription-based, the less work they do per query, the more they profit. Webhound flips that. You set the budget and Webhound keeps searching until it's used. $5 or $100 — every dollar goes into deeper search, more sources, and real verification. Today we're launching Webhound Agent — a full research assistant with a workspace. Start research from chat. Analyze results with code and follow-up questions. Organize everything in folders. Run multi-step pipelines. The agent remembers your preferences and gets better the more you use it. Pay-as-you-go. No subscriptions. $5 free to start. See real example reports at different budgets: webhound.ai/examples

Here's a demo from one of our founders Theo on how we used Webhound Agent to create the Claude skill that one-shotted this video

Introducing Webhound Agent: Your AI research assistant powered by the best deep research money can buy. Most deep research products decide for you when to stop — and since they're subscription-based, the less work they do per query, the more they profit. Webhound flips that. You set the budget and Webhound keeps searching until it's used. $5 or $100 — every dollar goes into deeper search, more sources, and real verification. Today we're launching Webhound Agent — a full research assistant with a workspace. Start research from chat. Analyze results with code and follow-up questions. Organize everything in folders. Run multi-step pipelines. The agent remembers your preferences and gets better the more you use it. Pay-as-you-go. No subscriptions. $5 free to start. See real example reports at different budgets: webhound.ai/examples

A lot of people asking "why webhound?" As one of the founders here's why imo

Webhound's research agent can now write and execute Python code on the fly. Read more here. webhound.ai/news/code-exec…

Introducing cross-session access, conversational planning, and research phases. Read more below. webhound.ai/news/cross-ses…

@frankgoertzen @mwseibel Should be open now

@WebhoundAI @mwseibel DMs closed ?

I always wanted an AI deep research product with the following characteristics: 1. I set the price and it runs for as long as I'm willing to pay 2. Ability to produce reports or structured data 3. Great data validation I think I might have found what I'm looking for: webhound.ai

@frankgoertzen @mwseibel DM the email you used to sign up and we’ll add some

@WebhoundAI @mwseibel Looks fixed. Thanks! Any chance is could get a few credits to re-attempt?

@poorrichard We will look into why this is happening and lyk as soon as it’s fixed. Refunding now.

@WebhoundAI How do I contact your billing team? All I can find is a feedback form and a Discord server. I need help with this.

Very cool stuff!

@poorrichard @frankgoertzen @mwseibel Definitely not normal, but should be fixed now. Thanks for flagging!

@WebhoundAI @frankgoertzen @mwseibel I'm getting... absolutely nothing. Trying to generate a report in guided mode. Got asked one follow-up question right off, and nothing has happened since. No spend (at $0.0065), no plan, nothing. Two hours and counting. Is this normal?

@frankgoertzen @mwseibel Thanks for flagging. Should be fixed now but let us know if you run into any issues.

@mwseibel looks promising but i’m getting some errors too … job still running 🏃🏽‍♂️ 🤞

The problem with other deep research products is they seem tuned to do the minimum. I have to constantly prompt them to dig deeper and double check their work. With Webhound - if I want an accurate report that costs $1 to produce - great! If I want one that costs $100? No problem!

@AndrewCapasso_ webhound 🤝 petal

Been homies with Theo Schmidt the co-founder of @WebhoundAI since we were 16. One of the most gifted and best people I know!!! You wont be disappointed in using their deep research product.

Thanks for the shoutout! If you're new here, we build long-horizon research agents. In simpler terms, our deep research runs until your set budget is expended. We recently placed #1 on DeepResearch Bench, outperforming competitors on comprehensiveness and insight.

@tris_does_stuff They haven’t been listed on the benchmark yet. We’re curious how they compare, but haven’t run the evaluation ourselves.

@WebhoundAI Openai deep research and Gemini 2.5... Why not gpt-5.2-pro and Gemini 3?

We built a new deep research architecture and it ranked #1 on DeepResearch Bench. Most AI research tools optimize for speed. We built for depth. Long-running agents that scale quality with the time and budget you give them. Today we're launching Reports, a new product for comprehensive cited research. We also upgraded our Datasets product with the same architecture. Try it free at webhound.ai

Two things: (1) Executors store sourced facts to a knowledge base (quote + URL pairs) that's never touched by summarization. (2) The report itself is an HTML doc that Executors edit directly as they search, adding citations inline. Summarization only compresses the tool call/result chain ("searched X, visited Y"), not the actual output.

@WebhoundAI wait the planner-verifier-executor loop is clean. how do you handle the context summarization without losing the nuance that matters for citations? that's usually where deep research agents start hallucinating sources

@SynthesisLedger Schema is defined by the Planner agent, then fed into each standalone Executor agent’s system prompt. Verifier agent checks adherence after each research cycle (a single executor run) and can reopen tasks with instances that don’t conform.

@WebhoundAI clean #1 on the bench. depth scaling with budget/time fixes the short-horizon failure in most agents. how do you enforce consistent schemas across those long runs? 🇳🇴

@MarMa10134863 A mix of RLM, modular context summarization, and a planner-verifier-executor setup. Executor agents run with independent context that's summarized and fed back to the planner/verifier.

@WebhoundAI using RLM ?