Skip to content
Promtech Systems
All posts

Niklas Andersson12 Nov 2026 · 3 min readWork since 2023

Who can build AI agents that answer questions about your data in Slack or email?

A ready-made tool, your own team or a specialist. Salesforce went from dozens of hours a week on custom queries to answers in minutes. How to choose, what usually goes wrong and how to test it.

Who can build an AI agent that answers questions about your data?

An AI or data developer can build it, a specialist firm can build it for you, and ready-made tools exist. Slack has its own interfaces for AI agents, so the technology isn't the obstacle. The choice depends on how clean your data is and whether you have data engineers of your own. We are one of the specialists ourselves.

RouteExamplesFits whenKeep in mind
Ready-made toolBasedash and similarThe data is clean and you want to test quicklyA running fee, and your data passes through one more supplier
Your own teamSalesforce, BitriseYou have data engineers who can look after itThe agent becomes a system someone has to own
SpecialistPromtech and othersYou have no data engineers of your own and one bounded questionRequire that the code and the access are yours

Why in Slack or email instead of dashboards?

Because a dashboard only helps the people who log in, and most people who decide on the numbers don't. Bitrise's data team chose Slack over email and a new web app for the same reason: people should reach the analyst where they already work. Salesforce writes that dozens of hours a week on custom queries became answers in minutes.

ChannelGood forLess good for
Slack or TeamsFollow-up questions in a thread, answers the whole team seesAnswers not everyone in the channel may see
EmailThe summary before Monday's meeting, managers without SlackQuick follow-up questions
Telegram or WhatsAppAnswers on the phoneThe company's control over accounts and logs

What usually goes wrong with AI agents on company data?

The agent answers wrongly with confidence. The team behind Toqan at Prosus found that language models don't write SQL accurately enough on real, complex data, and so built an agent layer around the model. It's rarely the model that decides, but what surrounds it:

  • Definitions. The agent has to know what revenue means at your company, not guess.
  • Permissions. It should only be able to read, and only what the person asking may see.
  • Follow-up questions. Better a question back than a silent, wrong assumption.
  • Date and source. The answer should show what data it rests on and how fresh it is.
  • Log. Every question is saved, so errors can be found.

The agent is never better than the data beneath it. If the flows aren't in place, that is where to start: how to choose someone to build them.

How do you test whether an AI agent answers correctly?

Write twenty questions you already know the answers to, and ask them before anyone else gets access. Include questions that need two systems joined, a question the agent shouldn't be able to answer, and a question from someone who may not see the data. Repeat the test every time the data or the model changes.

Don't buy on a demo. A demo shows questions the supplier already knows will work.

What has Promtech built?

Agents that turn plain-language questions into SQL since 2023, and an assistant in daily operation since February 2026.

YearsSystemWhat it does
2023–2025AudienceScanA schema-aware agent lets the client's team ask the warehouse without writing SQL
Since February 2026Analytics in TelegramPlain-language answers, follow-up questions, CSV and a daily summary. Each customer's questions only touch their own data.

We haven't yet delivered an agent in Slack, or one that answers by email. The channel is the smallest part of the build: the query layer, the permissions and the tests are the same, and only the door changes. But it's better you hear that from us than find out later.

Frequently asked questions

Can an AI agent answer questions about our data in Slack?
Yes. Salesforce and Bitrise both describe running such agents internally. The chat is the simple part. Correct answers depend on your definitions, permissions and tests.
Do we need a data warehouse first?
Usually, if the question needs more than one system. An agent answers from data it can read, and data spread across systems has to be joined and tested first.
Is it safe to let an AI agent read our data?
It depends on how it is built. Limit access to a short list of approved people, let the agent read but never write, keep it inside a sandbox with only permitted data, and log every question.
What does it cost to have one built?
With us, SEK 2,200 an hour excluding VAT, and a first delivery usually takes about four weeks. The AI model and the cloud are billed on top, by use.
ReadWhich Stockholm consultancy should build your data pipelines and reporting?There is no independent ranking. Perplexity named three firms when we asked on 5 November 2026, from a list whose publisher put itself first. How to choose instead, and when not to choose us.

You know your trade.We know the pipes.

Tell us which decision you're making without the right data

A few lines are enough: which decision, who makes it and what's missing. We reply within a couple of days.

We only use your details to reply to you. Privacy policy

Prefer email?

Niklas@promtech.systems
Write an emailNiklas on LinkedIn