Chat with your database in plain English
Simplifying AI is an AI-native company. We build ChatPlotDB, the AI data analyst for PostgreSQL, MySQL, DynamoDB, CSVs and spreadsheets, and Relay, the AI chatbot that answers your customers from your own content.
We set out to make a database answer questions the way a colleague would, in plain English, in seconds, for everyone.
ChatPlotDB connects to PostgreSQL, MySQL, DynamoDB, or a CSV or spreadsheet you drag in, then writes the SQL and hands back a table or a chart.
Nothing to write, nothing to install, nobody to ask. The people who understand the business ask the question themselves.
Two ideas hold it together.
Grounded in your schema: a configuration layer sits between the question and the query, so it knows which tables matter, how they join, and what your team's words mean.
Read-only, and shown to you: queries execute read-only against a role you control, and the SQL that produced the answer is there beside it rather than hidden.
Chat with your database. In plain English.
Connect PostgreSQL, MySQL, or DynamoDB and ask questions in plain English. ChatPlotDB reads your schema, writes the SQL, runs it read-only, and hands back a clean table or chart.
It's self-service analytics for the whole team, grounded in your real tables, so the numbers are trustworthy. The generated query is shown alongside the answer, so you can read exactly what produced the number, refine, and drill deeper in the same conversation.
Eight accounts crossed 20% ARR growth this quarter. Northwind Traders leads at +34%.
The lift is concentrated in the last six weeks: ARR crossed $1.4M on 10 May and has held above it every trading day since.
Americas is driving 61% of the expansion, and every account in the top ten is on an annual plan, so the growth is renewal-backed rather than one-off.
We built ChatPlotDB so anyone on the team can get a trustworthy answer from the database without waiting on an analyst.
No analyst in the loopEvery query makes it smarter. Continuously.
ChatPlotDB gets better the more you use it. A built-in feedback loop learns your team's terminology, KPIs, and business logic, tuning accuracy on your specific data over time.
The effect compounds: the engine answering your hundredth question is measurably faster and more accurate than the one that answered your first, with no manual retraining required.
142 accounts, 8.4% of enterprise ARR, down from 171 in Q2. Nine of them had an open support ticket in the last 30 days.
| Account | Seats | ARR | Closed |
|---|---|---|---|
| Northwind Traders | 1,240 | $412K | Aug 14 |
| Kestrel Logistics | 860 | $301K | Aug 2 |
| Halcyon Health | 640 | $255K | Jul 27 |
| Vertex Manufacturing | 520 | $198K | Jul 19 |
| Brightline Retail | 470 | $176K | Jul 11 |
Q1 198, Q2 171, Q3 142: churn has fallen every quarter this year, and the Q3 drop is the steepest of the three.
Tell us what went wrong
The product that answers your hundredth question should be sharper than the one that answered your first: that flywheel is the whole point.
Sharper with every queryAnalyze CSVs and Excel files. Instantly.
No database? No problem. Drag in a CSV or Excel file and start asking questions right away, ideal for one-off reports or data that never made it into a warehouse.
ChatPlotDB infers the structure and lets you filter, aggregate, join, and chart it conversationally, no formulas, no ETL. Analysis that meant hours of pivot tables now takes a single question.
Coverage is 2.1× in Americas but only 1.3× in EMEA: EMEA needs $1.8M more pipeline to hit plan.
| Territory | Open pipeline | Quota | Coverage |
|---|---|---|---|
| Americas, East | $1.3M | $0.60M | 2.2× |
| Americas, West | $0.9M | $0.45M | 2.0× |
| EMEA, North | $0.6M | $0.42M | 1.4× |
| EMEA, South | $0.5M | $0.43M | 1.2× |
| APAC, ANZ | $0.5M | $0.24M | 2.1× |
| APAC, Japan | $0.3M | $0.16M | 1.9× |
EMEA, South is the thinnest of the seventeen at 1.2×, and it carries the largest quota in the region: half of the EMEA shortfall sits in that one territory.
Nothing was loaded anywhere first: the file you attached is being read in place, all 18,402 rows of it.
Most questions start life as a spreadsheet. We wanted those answered in seconds, with zero setup.
From upload to answer in secondsQuery your data from Slack. Where work happens.
Bring ChatPlotDB into the tools your team already lives in. Ask data questions right inside Slack and get answers (tables and charts) without switching context or opening a dashboard somewhere else.
Results post straight into the channel, so anyone can see the numbers, ask a follow-up, and decide together, with the data and the discussion in one place.
/cpdb-setdb <config_key>•Show current database: /cpdb-setdb3 repliesLast reply 4 days ago/cpdb-askAsk a data question/cpdb-helpShow ChatPlotDB help and example questions/cpdb-setdbSet this channel's database/cpdb-modelChoose your chat model (per user)/cpdb-dashboardView, watch, and manage dashboards/cpdb-linkLink your Slack account to ChatPlotDB
Region | Accounts | Revenue -------------------------- North America | 412 | 1,284,900 Europe | 287 | 861,400 APAC | 196 | 540,250 LATAM | 118 | 312,780Was this helpful?👍Helpful👎Not helpful
Insights belong in the conversation, not buried in a dashboard nobody opens.
Answers right inside SlackAsk your data anything,get an answer in seconds
Connect a database, ask in plain English, and ChatPlotDB writes the SQL, runs it, and hands back clean tables and charts your whole team can read.
What would you like to know?
An AI data analyst for your database,an AI chatbot for your customers
ChatPlotDB, Relay and Charts run on one engine. Start wherever your team feels the pain first; the rest is already there when you need it.
ChatPlotDB
The AI data analyst: connect PostgreSQL, MySQL, DynamoDB or a spreadsheet, ask in plain English, and get the SQL, the table, and the chart back.
Learn moreRelay
The AI chatbot for your website, WhatsApp, Slack and Telegram. It learns your content, answers customers instantly, and hands off to a person when it should.
Learn moreCharts
Ask a question about your data and get the right visualization back: bar, line, pie, and more.
Learn more
I was running a team with 200,000 leads and 10,000 paying customers, and the data was all there – but the people who understood the business couldn’t query it, and the people who could write SQL didn’t know what to ask. ChatPlotDB is the tool I wanted then: you ask the question yourself, and the answer comes back in seconds.”
FAQs
ChatPlotDB is an AI data analyst for your own databases. You connect a data source, ask a question the way you'd ask a colleague, and it plans the query, writes the SQL, runs it, and hands back an interactive table or a chart, with the SQL visible the whole time.
It is built for the people who understand the business but don't write SQL: operations, support, finance, founders. No query to write, no ticket to the data team, no waiting.
PostgreSQL and MySQL with credentials encrypted at rest and SSL modes supported, Amazon DynamoDB with items flattened into queryable tables, and CSV or Excel files uploaded and queried directly with no setup at all.
A single conversation can also span several sources at once: a stitched config composes between two and five databases so one question can reach across them.
No. You ask in plain English and ChatPlotDB writes the SQL for you. The generated query is always shown, so anyone who does read SQL can check the logic, and anyone who doesn't can ignore it entirely.
If a metric you name is ambiguous, the agent asks a clarifying question before it queries anything, rather than guessing and returning a confident wrong number.
No. It only ever issues read queries. The recommended setup goes further: connect it with a database role that has SELECT on the tables you want queried and nothing else, so the credential itself cannot modify anything.
The SQL that produced each answer is shown alongside it, so anyone who reads SQL can check exactly what ran.
A text-to-SQL box turns one sentence into one query and hopes for the best. Between your question and the answer, ChatPlotDB puts a configuration layer that knows which tables matter, how they join, and what your team's words mean, so "active account" resolves to the same thing every time, for everyone.
That layer is the difference between a demo that works on a clean schema and something a team can rely on against a real one.
Anthropic's Claude models are the default: Sonnet 5 for everyday analysis, Opus 4.8 for the hardest multi-step reasoning, Haiku 4.5 for fast, cheap lookups. OpenAI's GPT-5.5, Z.ai's GLM, DeepSeek and Moonshot's Kimi are selectable too, and you pick per conversation.
On the managed service, model calls go to each vendor's API. On an enterprise deployment they don't leave your cloud: ChatPlotDB runs in your own AWS account and serves those same models through Amazon Bedrock, in the region you choose.
Yes. The Slack app answers data questions in the channel where the question came up and posts the table or chart straight back into the thread, so the numbers land next to the conversation that needed them rather than in a tool nobody opens.
Answers you want to keep can be saved to a dashboard as cards, refreshed on a schedule, and set to ping Slack when a number crosses a threshold you define.