1. Use your own scorer
2. Read the account
Pull the account record withPOST /v2/context, or get_context from an agent. It carries the firmographics, buying signals, people, and timeline your scorer needs.
3. Score it with your own logic
This part is your code. Any model or rule set works. Here is one example that asks a decision model typed questions about the account. It uses Jev through OpenRouter’s decisions endpoint. That endpoint is in alpha and belongs to OpenRouter, so check their docs before you depend on it.4. Send the score
tier and OpenNous derives it from your tier bands. Agents send scores with the score tool and its scorer and scores fields.
5. Read it back
The score is now the account’s ICP fit.get_context, the accounts list, and tiers all show it, with your reason and the history of past scores.
As deals close, each score is checked against what happened. Rename scorer when you change your model, for example acme-v2, and the history shows which version scored each account.