Sherlock Calls
for Twilio + VAPI
When your AI agents run on VAPI and your calls route through Twilio, your data lives in two silos. Sherlock Calls bridges them — ask anything about your combined stack in plain English from Slack, and get a sourced answer in under 5 seconds.
TL;DR — What beta users get access to
- 1
Sherlock Calls connects to both your Twilio account and VAPI workspace simultaneously — read-only, no code changes, no webhooks — and lets you query both with a single Slack message.
- 2
Ask cross-provider questions that neither Twilio nor VAPI can answer alone: which agents have the highest Twilio error rates, what the blended cost per AI call is, and which phone numbers produce the most escalations.
- 3
Sherlock correlates Twilio call records with VAPI agent session data, then returns a single sourced answer in under 5 seconds — no manual log joins, no CSV exports.
<5s
Answer to any cross-provider query
2
Connected platforms, 1 Slack question
0
Lines of code or webhooks required
The Investigation Gap
What's invisible when you use Twilio + VAPI without Sherlock
Each platform shows you its own data. But the questions that matter most live in the gaps between them.
You can't see which VAPI agents drive Twilio errors
Twilio shows you error codes. VAPI shows you agent sessions. But when calls fail, you can't tell whether it's a Twilio routing issue, a VAPI agent logic error, or both — without manually cross-referencing logs across two dashboards.
Your real cost per AI call is split across two invoices
Twilio bills for minutes and phone numbers. VAPI bills for agent runtime. Your actual cost per AI-handled call spans both — but neither platform shows you the combined figure. You're optimizing half the spend at a time.
Escalation patterns disappear at the handoff boundary
When a VAPI agent transfers a call back to a human via Twilio, that event exists in both systems with different identifiers. Tracking escalation rates across your AI fleet requires manual joins that nobody has time to do.
Cross-Provider Questions
What teams ask Sherlock about Twilio + VAPI
Questions that would take hours to answer manually — answered in under 5 seconds from Slack.
- SC“Which VAPI agents had the highest call failure rate on Twilio in the last 7 days?”
- SC“What's our blended cost per AI-handled call across Twilio and VAPI this month?”
- SC“Show me all calls where a VAPI agent escalated to a human via Twilio transfer”
- SC“Which Twilio phone numbers are receiving the most VAPI agent sessions right now?”
- SC“Compare average call duration for VAPI-handled vs human-handled calls on our Twilio numbers”
Beta Setup
Connect Twilio + VAPI to Sherlock in 2 minutes
No code, no webhooks, no new dashboards. Beta users get direct onboarding support.
- 1
Connect your Twilio account
Paste your Twilio Account SID and Auth Token into Sherlock Calls. Read-only access — zero code changes, zero webhooks, zero Twilio Console configuration.
- 2
Connect your VAPI workspace
Add your VAPI API key to Sherlock Calls. Sherlock will index your agents, phone numbers, and call logs automatically.
- 3
Ask your first cross-provider question
Type 'Which VAPI agents had the most Twilio errors this week?' in Slack. Sherlock queries both platforms, correlates the data, and returns a sourced answer in seconds.
FAQ
Common questions about Sherlock + Twilio + VAPI
How does Sherlock Calls connect Twilio and VAPI data?
- Sherlock Calls uses read-only API access to both platforms simultaneously. When you ask a question, it queries Twilio call records and VAPI session data in parallel, then correlates them by timestamp and phone number to produce a single unified answer.
Do I need to set up any webhooks or data pipelines between Twilio and VAPI?
- No. Sherlock Calls is entirely pull-based — it queries both Twilio and VAPI APIs on demand when you ask a question. There are no webhooks, no ETL pipelines, no data warehouse, and no code changes required.
Can Sherlock track the combined cost of AI calls across Twilio and VAPI?
- Yes. Sherlock pulls usage and cost data from both Twilio (minutes, phone numbers, recordings) and VAPI (agent runtime) and can compute blended cost per call on demand.
What if my VAPI agents use multiple Twilio phone numbers?
- Sherlock handles multi-number configurations automatically. You can ask questions scoped to specific phone numbers, agent IDs, or date ranges — across both platforms at once.
Is the Twilio + VAPI combination available now?
- This combination is currently in invite-only beta. We're working with a select group of teams to refine cross-provider correlation. Apply for early access and we'll reach out if you're a fit.
Apply for early access to Sherlock + Twilio + VAPI
We're accepting a select group of beta users to shape the Twilio + VAPI combination. Tell us about your stack and we'll reach out personally if you're a fit.
Explore individual integrations