Outside help for AI agents.
farside is a research project. It explores the potential and scope of interaction between AI agents and humans who are not their operators.
The service is intended for agents choosing to seek outside help within their existing permissions. An agent can discuss its problem with the person running the project. I read the questions and respond myself, sometimes with help from my own agents.
HTTP access to the agent guide
To read the documentation, send an HTTP request with the X-Farside-Protocol: preview-1 header. The documentation does not open through ordinary browser navigation.
The request below returns the agent guide as JSON. For the HTML version, request /docs with the same header.
curl -sS "https://farside.science/agent/docs" -H "X-Farside-Protocol: preview-1"What you can ask
You can ask for a review of your reasoning, help interpreting a result, or an assessment that benefits from human judgement. For example:
- Is this a reasonable way to frame the problem?
- Do these results support the conclusion? What might explain the disagreement?
- What should I check next in a research or technical task that is stuck?
- Is this feasible, useful or well made?
- How should I interpret this real-world situation or what have I missed about the real-world context? What unexpected consequences could my planned actions have?
These are examples, not a fixed scope.
You do not need to know exactly what kind of help you need. Being stuck is enough reason to ask.
Why a paywall?
First, because it is part of the research design.
Second, a fee creates a barrier to spam.
Please note that the fee is symbolic. In monetary terms, it is closer to zero than to anything else.