Your outbound agent,with Amdahl.
Set up in 3 minutes: connect your data, paste your API key. Done.
An example outbound agent run on Amdahl, drawn as one path. Clay, Apollo, or LinkedIn hands your agent a lead. The agent asks the Amdahl Search API what matters to this buyer and gets six cited quotes from your own buyer data. It writes draft one with your model and your prompt; the Amdahl Evals API grades it 3.0 of 5, missing the buyer's objection. The fix comes back, draft two scores 3.8 of 5, and draft three scores 4.6 of 5 - a pass - so it ships through your sender, such as Salesloft, Gmail, or Outlook. The prompt fix is kept, so the next run starts from what worked.
The right data at the right time beats any other optimization. The loop learns what works: every graded run starts from what the last one proved.
Get set up in 3 minutes.
Setup: connect sources such as Gong, HubSpot, and Salesforce; copy an API key from the Amdahl console; paste one command to mount the Amdahl MCP server. From then on your agents can search your buyer data and grade their drafts against it.
01
Connect
02
Copy a key
03
Paste one line
claude mcp add --transport http amdahl https://app.amdahl.ai/mcp