Hamming AI

Hamming AI is a testing, evaluation, and observability platform for voice and LLM AI agents. Its REST API runs experiments and voice/call test runs against your agents, manages datasets, registers custom scorers and evaluations, and ingests traces, logs, and production call logs for monitoring. A prompt optimizer and registry round out the platform.

6 APIs 0 Features

AIVoice AgentsLLMTestingEvaluationObservability

APIs

Hamming Experiments & Test Runs API

Create experiments, start and end experiment items, and update experiment status to run repeatable evaluation runs against agent and LLM outputs over a dataset.

Hamming Voice & Call Testing API

Run a voice agent against a dataset of scenarios by placing simulated outbound calls, create LiveKit rooms for direct agent-to-agent test runs, and retrieve the calls produced b...

Hamming Datasets API

List, create, and load datasets of test cases and conversation scenarios used as inputs for experiments and voice test runs.

Hamming Scorers & Evaluations API

Register custom scoring functions that compute scores over experiment results, complementing Hamming's library of built-in evaluation metrics.

Hamming Monitoring & Tracing API

Ingest traces and logs from instrumented agents and forward production voice call logs (e.g. provider call-ended payloads) for continuous monitoring of agent health and reliabil...

Hamming Prompt Optimizer & Registry API

List and fetch versioned, labeled prompts from the Hamming prompt registry to manage and optimize prompts used by agents under test.

Collections

Hamming AI REST API

OPEN

Pricing Plans

Hamming Ai Plans Pricing

2 plans

PLANS

Rate Limits

Hamming Ai Rate Limits

3 limits

RATE LIMITS

FinOps

Hamming Ai Finops

FINOPS

Resources

👥

GitHubOrganization

Sources

opencollection: 1.0.0
info:
  name: Hamming AI REST API
  version: '1.0'
request:
  auth:
    type: bearer
    token: '{{bearerToken}}'
items:
- info:
    name: Experiments
    type: folder
  items:
  - info:
      name: Create an experiment
      type: http
    http:
      method: POST
      url: https://app.hamming.ai/api/rest/experiments
      body:
        type: json
        data: "{\n  \"name\": \"<string>\",\n  \"datasetId\": \"<string>\"\n}"
    docs: Creates a new experiment (evaluation run) bound to a dataset.
  - info:
      name: Update an experiment
      type: http
    http:
      method: PATCH
      url: https://app.hamming.ai/api/rest/experiments/{experimentId}
      body:
        type: json
        data: "{\n  \"status\": \"FINISHED\"\n}"
    docs: Updates an experiment, for example to set its terminal status.
  - info:
      name: Start an experiment item
      type: http
    http:
      method: POST
      url: https://app.hamming.ai/api/rest/experiments/{experimentId}/items
      body:
        type: json
        data: "{\n  \"datasetItemId\": \"<string>\",\n  \"input\": {}\n}"
    docs: Starts an experiment item for a single dataset item.
  - info:
      name: End an experiment item
      type: http
    http:
      method: PATCH
      url: https://app.hamming.ai/api/rest/experiments/{experimentId}/items/{itemId}
      body:
        type: json
        data: "{\n  \"output\": {},\n  \"scores\": {},\n  \"status\": \"FINISHED\"\n}"
    docs: Ends an experiment item, recording output, scores, and status.
- info:
    name: Voice Testing
    type: folder
  items:
  - info:
      name: Run a voice agent against a dataset
      type: http
    http:
      method: POST
      url: https://app.hamming.ai/api/rest/voice-agent/{agentId}/run
      body:
        type: json
        data: "{\n  \"dataset_id\": \"<string>\",\n  \"to_number\": \"<string>\"\n}"
    docs: Starts a voice experiment by placing simulated outbound calls against a dataset of scenarios.
  - info:
      name: Get voice experiment calls
      type: http
    http:
      method: GET
      url: https://app.hamming.ai/api/rest/voice-experiment/{voiceExperimentId}/calls
    docs: Returns the calls run as part of a voice experiment with their scoring status.
  - info:
      name: Create LiveKit rooms for a test run
      type: http
    http:
      method: POST
      url: https://app.hamming.ai/api/rest/test-runs/create-livekit-rooms
      body:
        type: json
        data: "{\n  \"datasetId\": \"<string>\",\n  \"datasetItemIds\": []\n}"
    docs: Creates LiveKit rooms for a direct agent-to-agent test run without telephony.
- info:
    name: Datasets
    type: folder
  items:
  - info:
      name: List datasets
      type: http
    http:
      method: GET
      url: https://app.hamming.ai/api/rest/datasets
    docs: Lists the datasets available to the account.
  - info:
      name: Create a dataset
      type: http
    http:
      method: POST
      url: https://app.hamming.ai/api/rest/datasets
      body:
        type: json
        data: "{\n  \"name\": \"<string>\"\n}"
    docs: Creates a new dataset of test cases or scenarios.
  - info:
      name: Load a dataset
      type: http
    http:
      method: GET
      url: https://app.hamming.ai/api/rest/datasets/{datasetId}
    docs: Loads a dataset together with its items.
- info:
    name: Scoring
    type: folder
  items:
  - info:
      name: Register custom scoring functions
      type: http
    http:
      method: POST
      url: https://app.hamming.ai/api/rest/scoring/register-functions
      body:
        type: json
        data: "{\n  \"scoring\": []\n}"
    docs: Registers one or more custom scoring functions used to score experiment results.
- info:
    name: Monitoring
    type: folder
  items:
  - info:
      name: Ingest traces
      type: http
    http:
      method: POST
      url: https://app.hamming.ai/api/rest/traces
      body:
        type: json
        data: "{\n  \"traces\": []\n}"
    docs: Ingests a batch of trace events from instrumented sessions.
  - info:
      name: Ingest logs
      type: http
    http:
      method: POST
      url: https://app.hamming.ai/api/rest/logs
      body:
        type: json
        data: "{\n  \"logs\": []\n}"
    docs: Ingests a batch of log messages from monitored agents.
  - info:
      name: Ingest a production call log
      type: http
    http:
      method: POST
      url: https://app.hamming.ai/api/rest/v2/call-logs
      body:
        type: json
        data: '{}'
    docs: Forwards a production voice call log (e.g. a provider call-ended payload) for monitoring.
- info:
    name: Prompts
    type: folder
  items:
  - info:
      name: List prompts
      type: http
    http:
      method: GET
      url: https://app.hamming.ai/api/rest/prompts
    docs: Lists prompts in the registry, optionally filtered by label.
  - info:
      name: Get a prompt
      type: http
    http:
      method: GET
      url: https://app.hamming.ai/api/rest/prompts/{slug}
    docs: Fetches a single prompt by slug, optionally pinned to a label or version.
bundled: true