Launching today

Dippr
A data platform served to your agents, with one prompt
91 followers
A data platform served to your agents, with one prompt
91 followers
It’s where your agents build and run your company’s software, tools and apps – with access to your company data across sources, the context to understand it, and the rules to use it safely.





Launch Team

AWS Activate CreditsCredits that fuel your startup’s next milestone
Promoted
Hey Hunters, Hoshang here, one of the makers of Dippr.
About a year ago, we gave every team in our company coding agents. Within a month, a new ticket showed up in our queue: "can my agent access company data?" Sales, CS, marketing, almost everyone was building their own tools and automations.
The agents could build almost anything, but they couldn't reach the data safely. Someone on support needed numbers from our warehouse they didn't have access to, and we wanted to say yes without handing over the keys to the whole warehouse. Everyone was building, but the numbers didn't match from one tool to the next, which caused confusion. And whatever they built stayed local and static. Only a few lucky ones ever got hosted.
All of us could build far more with agents, but our data infrastructure couldn't keep up with AI's curiosity.
So we built Dippr, a complete data platform reimagined for agents, served to them with one prompt.
- Dippr connects to all your sources and tools, and agents query across them at once, on our own federated query engine.
- You set permissions per agent, even when the person using it has no login to the source, so each agent sees only what it should.
- Drop in your .md files and Dippr builds the semantic layer, ontology and golden questions from them, so the numbers match in everything anyone builds.
- Automations let your agents run things on a schedule with fresh data.
- A hosting layer runs and versions everything your agents build, with the rules in one place and every query logged.
Our team now builds things they never imagined they could. One of our reps built their own version of Gong, our product team runs its own product-led outreach, our support team built a customer facing portal to run onboarding and QBRs.
Dippr gives the data infrastructure for your agents to work with. The UI is yours
Paste this into your agent to get started and tell it what you want to build.
We're always happy to chat more if you'd like to learn more about how we've seen our customers setup their data infrastructure for agents . Book 30 mins here
Thanks @hoshang_m, I created a small application with couple of prompts. Looks cool with graph and tables.
Is there any option to connect snowflake account with key-value pair if I don't have account password or MFA?
Please can you explain how exactly automations work? Is there any gaudrail there?
What a beautiful landing page! I had been lurking on the beta channel updates but it caught me by surprise.
Loved the "Reveal your prompt" functionality on the landing page.
I wanted to build an analytics dashboard and analyse visitors to my product across Google Analytics and Hubspot and it built a whole fricking application with just the right levers I needed, just from the generated prompt.
Two questions:
1. Can I share this dashboard or specific read only reports on it with my team members?
2. Is it possible to restrict access to the PII records, so customer info doesn't end up being visible in the reports?
@sahrizv Thanks for giving Dippr a try!
Yes! If you go to our Agent RBAC page on the app, you should be able to set permissions for your team and even agents so your team can only see what they're allowed to.
And Yes, on the same screen if you click on 'Column Masks' you should be able to restrict access to PII records.
Feel free to hit me up if you have any questions!
@hoshang_m Thanks, I'm trying out your suggestions, will let you know how it goes.
@sahrizv Sure looking forward to it!
Dippr.ai killed the most boring job in my week: answering “can you send me the latest numbers?”
I run marketing, GTM and DevRel. All our numbers lived in one Google Sheet. It held web traffic, SEO, LinkedIn, email, YouTube and content, 9 months of it. Everyone opened it and nobody could read it. So I became the human dashboard.
So I built the “Web traffic & SEO” app on Dippr. Here is how:
I loaded the sheet tabs into a Dippr workspace database with one dip db load command. It takes CSV, Excel, JSON and Parquet. That gave me 12 tables.
I defined each metric once: sessions, signups, organic share. Every page uses the same definition, so two people never get two answers.
I built the pages: Overview, Traffic and search, SEO health, LinkedIn, Email, YouTube, Content. Each page has a period filter and a “Copy link” button.
I added access rules, so each viewer sees only the rows they are allowed to see.
I set a routine that checks for traffic spikes every Monday at 9:00 and writes up what changed. It is read-only, so it cannot break anything.
My favorite trick is keeping the Google Sheet as the backend. The team continues typing into the familiar sheet, while Dippr provides a real database, shared metric definitions, access rules, and a single app. No new tool was learned; no rows were migrated.
Pros:
Build once, use forever. The agent does not burn tokens redrawing the same chart every time someone asks.
It is shared. My manager, the content team and I open the same link and see the same number.
Governance comes built in, so I could show it to leadership without a security review panic.
The Monday routine and the dashboard read the same data, so the alert and the chart always agree.
@atharva_shah This is one of my favourite tools you’ve built!
VC-esque question: (Sorry) Who are your direct competitors, and what do you do differently from them?
@alchemist_studio Thanks for the question!
Databricks and Snowflake are the closest alternatives. Both let you build agents and apps on your data, with their own semantic layer and catalog, but they work best within their own ecosystems. Dippr lets agents query across warehouses and other sources without locking you into one platform.
We also built Dippr from the ground up for agents, not just for people using AI. Agents are the ones querying the data and building apps, so we designed for the volume of queries and the permissions that come with that.
This saves a lot of back and forth. Nothing worse than getting 3 different answers depending on who pulled the numbers -Congrats, team!
@henry_habib Thanks! Just drop in the .md files where you define your metrics. Dippr uses them to build the context layer, including the ontology and golden questions, so everyone’s agents work from the same definitions.
Hey PH, Michiel here, also one of the people building Dippr.
Short version of what it is: you connect your databases and warehouses, and then people, AI agents and small data apps can all query across them, each with their own access.
I wanted to say a bit about how we thought about the design, because most of it comes from things that annoyed us.
The first was copying data. Nearly every "let your agent talk to your data" setup starts by piping everything into yet another store. We didn't want to build that, so Dippr queries the sources where they are. Postgres, Snowflake, ClickHouse, BigQuery, Redshift, Iceberg, a Google Sheet somebody in finance maintains. You can join across them in plain SQL.
The second is the one I care about most. When an agent runs a query, it runs as you, with your grants, after you've consented to it. We don't hand it a service account that can see the whole warehouse. Same story for apps: if I open a dashboard and you open the same one, we each get the rows we're allowed to see. It made a lot of things harder to build, and I still think it was the right call.
One smaller thing: you can define certified metrics, so when an agent gets asked for revenue it uses your definition instead of making up its own SQL.
There's a CLI called dip that signs you in and hooks up Claude Code, Codex or whatever you use.
Honest question for anyone reading: how are you giving agents access to data today? I'm curious what people have duct-taped together, and which sources you'd want us to add next.
I'm around all day, ask me anything.
@michiel_de_smet Letting agents run queries without giving them more access than they need is a big one! Almost everyone we spoke to struggled with this.
Hoshang, I followed what you had suggested earlier, and it works as expected.
Thank you for building this, I'm going to talk about this at the next meetup I attend here.
@sahrizv Love it! Thanks! Did you also explore the semantic layer?
@hoshang_m Ah, not yet. I don't currently have a use case for that since our data vocabulary is limited, but I guess for our data team it might be a way to centralise the semantics. Will pass it on to them.
@sahrizv Got it. Yes, that would be awesome! Thanks again for spending time on Dippr and I'm glad you found it useful.