Observe
It tells you what it couldn’t answer
Every conversation your agent has comes with a forensic receipt, and its blind spots arrive ranked — which means you’re never guessing whether it’s working, and you always know what to fix next.
Free credits included. No credit card required.
The headline stat
Containment: how much it handled without a human
Observe opens with the answer, not a dashboard maze. The first number you see is containment — the share of conversations resolved without a person — beside your conversation trend and warm transfers. No vanity metrics, no charts you have to decode.
Containment
The share of conversations resolved end to end by the agent — the one number that says whether it is earning its keep.
Conversations
Volume with a trendline, plus outcome and sentiment breakdowns — so a busy week and a rough week look different at a glance.
Warm transfers
How often the agent handed off to a human — each one with full context passed along, and each one traceable to its Receipt.
The improvement loop
Blind spots come to you, ranked
Most platforms show observability as QA plumbing you have to dig through. Observe keeps a running list of the questions your agent couldn’t answer, ordered by how often they come up — which means the most valuable fix is always at the top, and fixing it takes a sentence, not a ticket.
- 1See the gap — the question, how often it came up, and why it missed.
- 2Tag the call into Assist — it attaches as a chip, and the copilot reads that exact conversation.
- 3Fix it in plain English — "add our heat pump services to the knowledge base."
- 4Deploy — the change lands on your draft first, then goes live when you say so.
Questions the agent couldn’t answer
Illustrative example — values from the scripted demo, not live data.
Receipt
Call · voice · 3m 12s- Call startedvoice
- Caller"Do you have any openings tomorrow morning?"
- Knowledge lookupservice area & hoursgrounded 0.86
- Tool — Book appointmentGoogle Calendarsuccess · 412ms
- Guardrail — pricing disclosureallowed
- Agent"You’re booked for the 8-10 AM window tomorrow."
- Call endedcompleted
Illustrative example — values from the scripted demo, not live data.
The Receipt
A forensic timeline for every single call
Open any conversation and the Receipt shows exactly what happened, turn by turn: every knowledge lookup with a grounded score, every tool call with its status and duration, every guardrail decision, every verification event, every handoff — which means “why did it say that?” is a question with an answer, not a mystery.
It’s the same transparency you get before publishing - the guardrails you set show up here as decisions you can audit, call by call.
Also in Observe
Built for the owner who reads the rough ones
Sentiment triage
Open the rough calls first — conversations sorted so frustration surfaces instead of hiding in averages.
Topics
What callers actually ask about, grouped — so you learn what your phone line is really for.
Transcript search
Search every word of every conversation. Find the call where someone mentioned the warranty.
Fleet view
Running more than one agent? See per-agent performance across your whole fleet at a glance.
See it in the Studio
Watch the gap list turn into a fix
The Observe act below replays the real flow: the metrics strip, the ranked gap list, a call tagged into Assist, and the Receipt scrolling through one conversation.
ACT 5 — OBSERVE: See what it handled, what it missed, and the receipt for every call.
Scripted demo — a replay of the real product, not a live session.
FAQ
Observe, answered plainly
What is containment for an AI phone agent?
How do I find out what the agent couldn’t answer?
What is a Receipt?
How do I fix a bad call?
Can I see every conversation, not just summaries?
Build an agent that shows its work
Draft it in minutes, put it on a line, and read its first receipts tonight.
Free credits included. No credit card required.