New: Voice AI Playbook, 6 short videos →
Full observability for your Dograh voice agents
Connect your Dograh workflow to Tuner with one node and no code. Every call’s transcript, latency, tool calls, and cost is captured automatically, so you catch hallucinations, broken flows, and missed intents before your callers do.
Setup
Integrate in minutes, no code
Add the Tuner node to your Dograh workflow, paste three values from Tuner, and publish. Every call after that lands in Tuner automatically.
01
Create a Dograh agent in Tuner
Create a new agent in Tuner and pick Dograh as the provider. Tuner generates the Agent Remote ID for you.
02
Add the Tuner node
In your Dograh workflow, click Add node, open Integrations, and add Tuner. The node sits off to the side and never joins the live conversation.
03
Paste your credentials
Copy your Agent Remote ID, Workspace ID, and Tuner API key into the node. Turn on Calculate cost to send a cost for every call from your own provider rates.
04
Publish and monitor
Save and publish the workflow. Every completed call, with its transcript, latency, tool calls, and cost, shows up in your Tuner Call Logs.
Features
Everything you need to run Dograh agents in production
Turn production from a black box into something you can actually monitor, measure, and improve.
Catch failures early
Automatically flag hallucinations, broken flows, dead air, early hangups, and other failure conditions before they show up in your churn data.
See where latency comes from
Break out STT, LLM, and TTS latency turn by turn and at p50 and p90, so you can see which provider in your Dograh stack is slowing conversations down.
Get alerted when something breaks
Get notified when red flags, failed evals, or other conditions appear in production, while there’s still time to fix them.
Simulate calls before you ship
Tuner calls your Dograh agent through the Cloudonix SIP domain Dograh sets up for you. No carrier or phone number needed, and every call is scored with your production evals.
Replay real calls
Save real Dograh calls to a Dataset and replay them with the exact same caller audio, to prove a fix or try a new STT, LLM, or TTS provider before you switch.
Track cost on every call
Turn on Calculate cost in the Tuner node and enter your own LLM, STT, TTS, and telephony rates. Tuner shows what every call cost, with no separate billing pipeline.
Why Tuner
See what's happening in production
Voice agents fail quietly, and at a scale no team can review by hand. Tuner turns every production call into structured data you can search, debug, evaluate, alert on, and test against.
Comparison
Tuner vs Dograh’s built-in QA
Dograh’s QA node runs one LLM review on each transcript and shows the result on that run. Tuner adds the production quality layer on top: evals, voice metrics, alerts, and testing across every call.
Capability
Tuner
Pass/Fail evals with evidence from the call
30+ voice quality metrics & red flags out of the box
Alerts when evals fail or metrics cross a threshold
Root-cause diagnosis with a specific fix, not just scores
SIP call simulations with AI callers, using your live evals
Replay real calls with the exact same caller audio
LLM review of every call transcript
Turn-by-turn transcripts & call recordings
FAQ
Frequently asked questions
Common questions about connecting Tuner to your Dograh agents.
Read the docs
Which Dograh versions are supported?
Do I need to write any code?
How long does setup take?
Does the Tuner node add latency to my calls?
What gets captured?
Can I test my agent before going live?
How does Tuner call my Dograh agent?
Does Tuner work with self-hosted Dograh?
Dograh has a QA node. What does Tuner add?
Can I define my own evaluations and metrics?
How is Tuner priced?
Is my call data private and secure?
