Daily

Connect your own voice bot — built with Pipecat or anything that can join a Daily room — and let RubricHQ’s simulated caller talk to it over real audio.

Both parties join one Daily room:

• rubric-test-caller — RubricHQ’s AI caller, running your scenario.
• your agent-under-test — the bot you’re testing.

They publish and subscribe to each other’s audio; RubricHQ records the call and produces transcript + audio metrics.

The model: rooms, tokens, and who creates them

A few Daily facts that decide how the integration is wired:

• A room (a https://<domain>.daily.co/<name> URL) is one call/session. A meeting token authorizes one identity to join one room.
• Creating rooms and minting meeting tokens requires your Daily API key. Joining a room requires only the room URL + a meeting token — never the API key.
• So the only real question is who creates the room and mints the tokens. That gives two modes:

Configure this under Agent → Channels → Web, provider Daily.

Credentials (for “We create rooms”)

Provide your Daily API key in either place — RubricHQ resolves per-agent override → workspace default → error:

1. Workspace default — Settings → Integrations → Transport Providers → Daily: API Key. Used by every agent that doesn’t override.
2. Per-agent override — Agent → Channels → Web → “We create rooms” → Daily API key. Overrides the workspace default for that one agent.

Mode 1 — You create rooms (client)

You own the Daily account; RubricHQ never needs your key.

Config

Sequence

1. RubricHQ POSTs to your Bot Runner URL with the run context.
2. Your service creates a Daily room, starts your bot in it, and returns a meeting token for our caller.
3. RubricHQ’s caller joins that room with the room_url + token you returned, and the conversation runs.

What we send → your Bot Runner URL

1
POST {bot_runner_url}
2
Content-Type: application/json
3
4
{
5
  "rubric_run_id": "1234",
6
  "metadata": {
7
    "scenario_id": 8,
8
    "scenario_name": "Cooperative Upbeat Payment Flow",
9
    "agent_id": 1
10
  }
11
}

What you return (immediately, in the HTTP response)

1
{
2
  "room_url": "https://your-domain.daily.co/client-459ff0f5",
3
  "token":    "<a Daily meeting token for rubric-test-caller>"
4
}

Reference bot runner (client mode)

1
# POST /api/create-and-join-daily
2
import secrets, time, httpx
3
4
DAILY = "https://api.daily.co/v1"
5
H = {"Authorization": f"Bearer {DAILY_API_KEY}", "Content-Type": "application/json"}
6
7
async def create_and_join_daily(req):
8
    room_name = f"client-{secrets.token_hex(4)}"
9
    exp = int(time.time()) + 3600
10
    async with httpx.AsyncClient(timeout=15) as c:
11
        r = await c.post(f"{DAILY}/rooms", headers=H, json={
12
            "name": room_name, "privacy": "private",
13
            "properties": {"exp": exp, "max_participants": 10},
14
        })
15
        room_url = r.json()["url"]
16
17
        async def mint(user):
18
            t = await c.post(f"{DAILY}/meeting-tokens", headers=H, json={
19
                "properties": {"room_name": room_name, "user_name": user, "exp": exp}})
20
            return t.json()["token"]
21
22
        bot_token, caller_token = await mint("pipecat-bot"), await mint("rubric-test-caller")
23
24
    start_your_bot_in(room_url, bot_token)        # your agent joins
25
    return {"room_url": room_url, "token": caller_token}

Mode 2 — We create rooms (rubric)

RubricHQ creates the Daily room with your API key, mints a token for your bot and one for our caller, then POSTs your join endpoint so your bot enters the room.

Config

Sequence

1. RubricHQ creates a Daily room and mints a bot_token (for your bot) and a caller token (for our caller).
2. RubricHQ POSTs your join endpoint with the room_url and the bot_token.
3. Your bot joins that room with the token we minted; our caller joins too; the conversation runs.

What we send → your join endpoint

1
POST {web_call_url}/api/session
2
Content-Type: application/json
3
4
{
5
  "room_url": "https://your-domain.daily.co/rubric-188-aaa02027",
6
  "token":    "<a Daily meeting token for pipecat-bot>"
7
}

What you return

1
{ "status": "started", "room_name": "https://your-domain.daily.co/rubric-188-aaa02027" }

Reference bot runner (rubric mode — Pipecat)

1
# POST /api/session  — join a Daily room RubricHQ already created
2
async def create_session(req):
3
    start_your_bot(room_url=req["room_url"], token=req["token"])
4
    return {"status": "started", "room_name": req["room_url"]}

Optional room config — “Room Properties (JSON)”

When RubricHQ creates the room (“We create rooms”), you can pass any Daily room properties as JSON under Agent → Channels → Web → Room Properties (JSON). They’re merged into the room’s properties; RubricHQ’s required keys (exp, max_participants) take precedence.

1
{
2
  "enable_recording": "cloud",
3
  "enable_dialout": false,
4
  "lang": "en",
5
  "start_audio_off": false,
6
  "eject_at_room_exp": true
7
}

Recording

enable_recording controls Daily-side recording. Allowed values:

When Daily-side cloud recording is enabled, RubricHQ also fetches the vendor’s own recording link after the call and surfaces it on the run, alongside our capture.

Commonly useful properties

This is the testing-relevant subset; any key from the Daily room config reference is accepted and passed through.

Choosing a mode

Results

When the call ends, the transcript, audio recording (speaker-separated when available), and metrics appear automatically on the run in RubricHQ — your bot runner doesn’t need to report anything back. If a call can’t proceed (missing/incorrect credentials, room creation failed, or the bot never joins) the run is marked failed with the reason rather than left hanging.