14 LAUNCHES IN 14 DAYS

SEE WHAT’S NEW

Feature · Upsolve Demo Projects

A working data agent from your first minute.

Spin up a sample project and Upsolve sets up the connection, data model, security rules, agent, charts and dashboard for you. Explore the whole platform before you connect your own data.

One clickFully configuredSample data included
New · Launch Month day 9, Thu 8 Oct 2026 · Upvote on Product Hunt →
SAMPLE PROJECT · OLYMPICS DATAREADY
Upsolve sample project agent answering a question about top athletes at the 2004 Summer Olympics with a bar chart
01 / The problem

Trying a data agent platform usually starts with a week of setup.

01

You have to connect data, model it and write prompts before you see a single answer.

02

An empty workspace doesn't show what good looks like, so it's hard to judge the product.

03

When your own setup misbehaves, there's no working reference to compare it against.

02 / How it works

From setup to production in three steps

01

Create a sample project

Choose a sample project when you create a project. Upsolve sets up the connection, data model, security rules, agent and dashboards.

02

Ask it anything

Ask what data you have access to, then ask analytical questions. Answers respect the sample row-level security, so the Japan user only sees Japan's athletes.

03

Deploy it like your own

Grab the iframe or a preview link, or connect it to Claude through the Upsolve MCP. Connect your own data from project settings when you're ready.

03 / What changes

What changes with Upsolve Demo Projects

Without Upsolve Demo Projects

You connect data, build a model and write prompts for days before you see whether the agent can answer anything.

With Upsolve Demo Projects

A complete sample workspace answers questions, enforces permissions and renders dashboards the moment it's created.

04 / What you get

Everything that ships with Demo Projects

STACK

Full stack, pre-built

Connection, data model, data security rules, agent, skills, memory and suggestions, all configured.

SECURITY

Row-level security included

Query as a sample user and see tenancy working from day zero.

DASHBOARDS

Charts, canvases and an app

Favourite charts, build canvases, and open a pre-built Olympics dashboard application.

REFERENCE

A reference for production

Cross-check your own project's setup against a workspace that's known to work.

05 / Where it fits

One layer of a closed learning loop

Upsolve builds the whole stack for data agents that stay accurate in production. Every conversation feeds the next improvement.

01
Ontology
Your data described clearly. Permissions enforced deterministically, not delegated to the agent.
02
Agent harness
Snappy, reliable, accurate. Learns from real interactions and updates its skills and memory.
03
Distribution
Your product, your Slack channels, Claude. Go where your users already are.
This feature
04
Improvement loop
Live evals on real usage find the gaps, then you harden the context to close them.
06 / Launch Month

Part of Upsolve Launch Month

See all fourteen launches →
07 / FAQ

Common questions

Olympics data plus geography and economic industry data, so you can try analytical questions straight away.

Yes. Go to project settings, open Connections, pick your data source and wire it through the data model and agent.

Yes. In organisation settings, point the MCP agent at your sample project and ask it questions from Claude.

Can't find your answer? Get in touch.

Stop answering the same 10 questions today.

The Platform for Accurate, Reliable, and Trustworthy AI Analytics.

Agent Studio for Data Teams. Encode context. Deploy agents. Deliver clarity.

© 2026 Upsolve AI, Inc.  

|