Sherlock Calls
for PostgreSQL
Your PostgreSQL database holds the operational truth of your business: call records, user accounts, subscription states, and every structured event your application writes. But querying it requires SQL access, context switching, and time you don't have during an incident. Sherlock changes that: ask any question about your PostgreSQL data in plain English from Slack and get a sourced answer in under 5 seconds. Invite-only beta for operations and engineering teams.
TL;DR — What beta users get access to
- 1
Sherlock Calls connects to PostgreSQL via host, port, database, username, and password — read-only access to your operational tables in under 2 minutes, no SQL required.
- 2
Ask 'How many users cancelled their subscription in the last 7 days?' or 'Show me all call records for account ID 4821 this month' — Sherlock translates to SQL, queries PostgreSQL, and returns a sourced answer in Slack.
- 3
PostgreSQL is the world's most widely deployed open-source relational database — running the operational backends of most voice AI, SaaS, and contact center platforms.
<5s
Time to query PostgreSQL data from Slack
0
SQL required — ask in plain English
Any
PostgreSQL table or view Sherlock can query
About PostgreSQL
What is PostgreSQL?
PostgreSQL is an open-source object-relational database management system with a strong reputation for reliability, feature robustness, and standards compliance. It is the most widely deployed open-source relational database and serves as the operational backend for a large proportion of SaaS platforms, voice AI stacks, and contact center applications. PostgreSQL supports full SQL, ACID transactions, advanced indexing, and JSON storage, making it suitable for operational workloads ranging from user account management to call record storage and event logging. It is available as self-hosted deployments and managed services including Amazon RDS, Google Cloud SQL, Azure Database, Supabase, and Neon.
About Sherlock Calls
What is Sherlock Calls?
Sherlock Calls is an AI call detective that lives in your Slack workspace. It connects to voice providers, CRMs, and ad platforms, then answers any question about your calls in plain English — in under 5 seconds, with no code, no new dashboards, and no SDK required. Think of it as a senior analyst always on call, inside the tools your team already uses.
Beta Setup
Connect PostgreSQL to Sherlock in 2 minutes
No code, no webhooks, no new dashboards. Beta users get direct onboarding support.
- 1
Provide your PostgreSQL connection details
Enter your PostgreSQL host, port, database name, username, and password in Sherlock's integration settings. Sherlock validates the connection before saving. Read-only credentials are strongly recommended — Sherlock never writes to your database.
- 2
Describe your schema (optional but recommended)
Optionally describe your key tables and columns so Sherlock can generate accurate queries. For example: 'calls table has id, account_id, status, duration_seconds, provider, created_at'. The more context, the better the query accuracy.
- 3
Start asking questions in Slack
Ask 'How many calls failed in the last hour?' or 'Show me all accounts with more than 50 failed calls this week' — Sherlock translates to PostgreSQL SQL, executes the query with read-only credentials, and returns structured results in your Slack thread.
Beta Use Cases
What beta teams are asking Sherlock about PostgreSQL
- SC“How many calls failed in the last hour?”
- SC“Show me all accounts with more than 10 failed calls this week”
- SC“What is the average call duration for premium plan users vs free plan users?”
- SC“How many new user signups did we have yesterday?”
- SC“Which accounts have the highest call volume this month?”
- SC“Show me all call records for a specific phone number in the last 30 days”
Beta Features
What beta users can do with PostgreSQL
Natural Language to PostgreSQL SQL
Ask any question about your operational data in plain English. Sherlock generates accurate PostgreSQL SQL, executes it with read-only credentials, and returns the result with the query shown for transparency.
Operational Data Investigation
Query call records, user accounts, subscription states, and any other operational table directly from Slack. No need to open pgAdmin, DBeaver, or a terminal during an incident.
Cross-Source Correlation
Combine PostgreSQL query results with live data from Twilio, ElevenLabs, HubSpot, and other connected providers. Correlate your application database with telephony and voice AI events in one investigation.
Schema-Aware Query Generation
Sherlock learns your table structure and generates queries that match your actual column names and data types — not generic SQL that fails on the first run.
Read-Only and Secure
Sherlock connects with read-only credentials and never executes INSERT, UPDATE, DELETE, or DDL statements. Your production database is always protected.
AI Tools
5 specialized tools, zero configuration
Sherlock picks the right tool automatically. You just ask in plain English — the AI knows which APIs to call and how to correlate the results.
Beta users get direct access to all tools below — with personal onboarding from the Sherlock team.
FAQ
Common questions about Sherlock + PostgreSQL
How does Sherlock Calls connect to PostgreSQL?
- Sherlock connects via the standard PostgreSQL wire protocol using your host, port, database, username, and password. Read-only credentials are strongly recommended. The connection is validated before being saved.
Does Sherlock work with managed PostgreSQL services like RDS, Supabase, or Neon?
- Yes — Sherlock connects to any PostgreSQL instance accessible over the network, including Amazon RDS, Google Cloud SQL, Azure Database for PostgreSQL, Supabase, Neon, and self-hosted deployments.
Can Sherlock query any table in my PostgreSQL database?
- Sherlock can query any table or view that the connected user has SELECT access to. We recommend creating a dedicated read-only role with access scoped to the specific schemas and tables relevant to your investigation use cases.
Does Sherlock store my PostgreSQL data?
- Sherlock does not store your PostgreSQL table data. Query results are used to generate the Slack response and are not persisted beyond the session. Your database credentials are encrypted at rest. Full details at usesherlock.ai/privacy.
What kinds of questions can I ask about my PostgreSQL data?
- Any question your operational data can answer: call counts, account lookups, subscription status checks, churn analysis, failure breakdowns, cost aggregations, and trend queries. If it can be answered with a SQL SELECT, Sherlock can answer it in plain English from Slack.
Apply for early access to Sherlock + PostgreSQL
We're accepting a select group of beta users to shape the PostgreSQL integration. Tell us about your stack and we'll reach out personally if you're a fit.
Even more powerful combined
Also works with