Anthropic setup

Anthropic provides Claude, a cloud-based AI model that the coaching platform uses to analyse your coaching transcripts and generate ICF competency assessments. You need an Anthropic account and an API key. Usage is pay-as-you-go; a typical coaching assessment costs a few cents per session.

Anthropic's API data is not used for model training, making it a strong choice if data privacy is important to you.

Anthropic create API key

Add provider and select model

Run deep AI analysis

AI assessment completed

View usage tokens in Claude Console

View cost for the day in USD

View logs and latency in seconds

---

Step 1: Create an Anthropic account

1. Go to console.anthropic.com
2. Click Sign up
3. Create an account with your email address, or sign in with Google

This is the Anthropic developer console. If you already use Claude.ai for chat, you can use the same login, but API access is managed separately.

Step 2: Add a payment method

1. Once signed in, click Settings in the left sidebar
2. Go to Billing
3. Click Add payment method and enter your card details

Anthropic API access requires a payment method. You are only charged for what you use.

Set a spending limit

Under Billing > Limits, you can set a monthly budget to avoid unexpected charges. A limit of $10 per month is more than enough for most coaching use.

Step 3: Create an API key

1. In the Anthropic console, go to API Keys in the left sidebar
2. Click Create Key
3. Give it a name (e.g. "Coaching Platform")
4. Click Create Key
5. Copy the key immediately. It will not be shown again.

If you lose the key, you can always create a new one and update it in the coaching platform.

Step 4: Configure the coaching platform

1. Open the coaching platform and go to Settings > AI
2. Select Anthropic as your provider
3. Paste your API key into the API Key field
4. Choose a model. See Choosing a model for recommendations. claude-sonnet-4-6 is the recommended model for honest, rigorous feedback.
5. Click Save

To test the connection, open any session with a recording and transcript, then click Generate AI Assessment.

Assessment speed

Claude assessments for complex sessions (PCC/MCC with 39 markers) take approximately 4 minutes. This is normal for Claude's thorough evaluation approach. If you see timeout errors, increase the timeout in Settings > AI > Advanced tuning.

Privacy

Anthropic does not use API data to train its models. Your coaching transcripts are processed and discarded. This makes Anthropic a good choice if you handle sensitive client data.

API limits

Anthropic's Tier 1 rate limits are tight for coaching assessments, especially with adaptive thinking enabled. If you run assessments frequently, consider upgrading to Tier 2. See API limits for details on context windows, output token budgets, and rate limits across all providers.

Troubleshooting

"API key invalid" error

Verify the key is correct. Go to the API Keys page in the Anthropic console and check that the key exists and has not been revoked. If in doubt, create a new key and update it in the coaching platform.

"Insufficient credits" error

Your Anthropic account has run out of credits. Go to Billing in the Anthropic console and add funds or check your spending limit.

Assessment takes a long time

Claude Sonnet evaluates each competency thoroughly, which takes longer than some other providers. A deep ACC assessment takes approximately 10 minutes and PCC/MCC assessments take approximately 15 minutes. If the assessment times out, increase the timeout in Settings > AI > Advanced tuning.

Assessment truncated or incomplete

If the assessment stops partway through, the response may have exceeded the output token limit. Try regenerating the assessment. If the problem persists, check that your session transcript is not unusually long.