Opportunities › Natural language analytics agent for data teams › Proposed app
Askwell
Ask your warehouse in plain words. Get checked SQL, answers and charts in chat.
- Score
- 53
- confidence 38
- Evidence
- 5
- items on the page
- Rivals
- 4
- named in sources
- First version
- 45 d
- estimate
- Type
- Desktop and mobile
- PWA: on computers and phones alike
- Market since
- 2023
- Emerging market · AI estimate
ScreensConcept
Desktop and mobile: Analysts ask questions and review detailed SQL from desktop; business users access answers in Slack and share results on mobile. Sample screens on a computer and a phone, in the proposed brand. Their numbers are sample data.
Ask
Verified definition: revenue$412,300
About this appAI proposal
Askwell lets anyone on a team ask a question about company data in plain language and get an answer from the warehouse. It writes the SQL, runs it read-only, and replies with a table, a chart and a short written summary. Ask in the web app or in Slack.
Analysts set it up once. They write down what tables mean, how metrics are defined and which questions are approved. Askwell uses that context every time, so 'revenue' means the same thing for everyone. Each answer shows the exact SQL and the definitions it used.
It is for small data teams who spend their week answering ad-hoc questions. Stakeholders get quick answers; analysts review and correct the ones that matter, and the fix is remembered for next time.
- Tagline
- Ask the warehouse. See the SQL. Trust the answer.
- Voice
- ClearCandidPractical
- Why this name
- A play on a well you draw answers from, and on 'ask well'. Two plain parts, easy to say. Trademark check needed.
In the first version
Members say which features they would use. It tells PWAS what people want; it changes no score.
Plain-language questions
Type a question in the app or in Slack. Askwell finds the right tables, writes the SQL and returns the result with a chart.
No member yet
Show-your-work answers
Every answer lists the SQL, the tables touched and the metric definitions applied, so analysts can check it in seconds.
No member yet
Context library
Analysts record table notes, metric definitions and example questions once. The agent reads them before it writes any query.
No member yet
Read-only by design
Connects with a read-only role. Queries get row and cost limits, and a dry-run estimate runs before large scans.
No member yet
Brand identityAI proposal
Check the name against trademark registers before using it.
Palette
#0F4C5CDeep Teal · primary#F7F4EEPaper · surface#1B2A30Ink · text#E09F3EAmber · accent#7FB7A4Sea Glass · data#B5543AClay · warning
Typography
Aa
Askwell
PricingAI proposal
The material gives no competitor prices. Tiers follow the usage-based idea in the opportunity (queries, users, source types, self-hosting) and are a starting point to test.
Free
Free
- 1 data source
- 50 questions per month
- 2 users
Team
$99 a month
- 3 data sources
- Slack app
- Up to 15 users
- 2,000 questions per month
- Context library and review queue
Business
$399 a month
- All four warehouse types
- Up to 75 users
- 10,000 questions per month
- Audit log
What it could be worthEstimate
What a software business making this much sells for today, from real deals. Pick a monthly revenue.
If it makes
Worth about
$194,000
Sale range $132,000 to $263,000
$120,000 a year in revenue
From 87 software businesses listed and sold on Empire Flippers in the last year, revenue vetted by the broker: they sell for about 19× their monthly revenue, most between 13× and 26×.
Measured on profit, the middle deal is 32× monthly net profit: about 2.7 years of profit.
An estimate, not an offer or financial advice. A real price depends on profit, growth, churn, how much of the work is the owner's, and the buyer.
How it would growAI proposal
How the product would reach new customers through its own use, and how the first ones would be found. A plan to test, not a result.
- Built-in loop
- Shared outputs. Users post answers into Slack channels or send links to colleagues. Each shared answer shows its SQL, source and an 'Answered with Askwell' footer, and viewers can ask a follow-up.
- Do they become customers?
- Viewers are often colleagues at the same company who could become users on a free tier. Test how many link viewers sign up and ask their own question, and whether they convert to paid seats.
- First customers
- Data teams of 1 to 5 people at startups of 50 to 300 staff using PostgreSQL or BigQuery, where the analyst is the bottleneck for ad-hoc questions from sales and ops.
- Where to reach them
- Open source community: Join GitHub discussions and posts about analytics agents; offer a hosted setup to teams that find self-hosting heavy.
- Data communities: Share a public demo on a sample dataset in analytics Slack groups and forums, with a free setup call.
- Direct outreach: Message heads of data and analytics engineers at small companies, offering a two-week pilot on one warehouse.
- First milestone
- Five teams in one segment run a two-week pilot, and at least three pay for Team after it.
Why people already pay for this
- VerifiedGitHub repository gained 1878 stars in 284 days
- Public claimnao is positioned as an open source analytics agent that enables teams to create context and deploy chat interfaces for data access
- Public claimThe product supports multiple major data warehouse and database platforms, indicating demand from organizations using these systems
- AI inferenceThe project has attracted significant developer interest and community engagement
- Public claim
Tech stack
Every proposal builds on the same PWA base, installable from the browser on any phone or computer. Dashed boxes are what this app adds.
- AppNext.js and TypeScript
- PWAManifest and service worker
- UITailwind CSS
- Data and authSupabase Postgres
- PaymentsStripe
- EmailResend
- HostingVercel
- This app · AI modelHosted large language model API with tool callingWrites SQL and summaries and runs the agent loop of schema lookup, query and check.
- This app · Warehouse connectorsDrivers for PostgreSQL, BigQuery, Snowflake, DatabricksRead-only queries, schema reads and dry-run cost estimates for each source.
RisksAI inference
- AIWrong SQL that looks right could drive bad decisions. Needs shown SQL, verified definitions and an accuracy test set per customer before trust is earned.
- CommercialAn open source analytics agent already exists, and warehouse vendors may add chat features. A hosted, easy-to-set-up product must be clearly worth paying for.
- DataCustomers must hand over warehouse access. Security reviews can be slow, and a leak of schemas or results would end trust.
- TechnicalLarge or messy schemas strain model context. Cost control on big scans and across four warehouse dialects adds work.
- PlatformDepends on a model API vendor and Slack's app rules. Price or policy changes would hit margins and features.
Everything marked AI proposal or AI inference was written by a model from the evidence on the opportunity page. The proposed name must be checked against trademark registers before it is used.