BIG NEWS: Tilebox self-service is live.
Create an account for free to explore the tool with Community Access. No face-to-face friction 🥸
Need to level up? It doesn’t matter if you’re processing in the cloud, on prem, or in orbit. Pricing is based on capacity and support
As part of the launch we built https://t.co/m3FYC6Bl0d with an agent on Tilebox.
The site tracks US data center construction using satellite imagery, with a web frontend, backend workflow, before/after imagery, rankings..
Here's what we didn't have to do:
- set up workflow infrastructure
- build a complex CI/CD pipeline to roll out changes
- wire up observability
- copy-paste logs, traces, errors, and failure modes back into the agent
- explain where the satellite data lives or how to load it
- tell the agent how to parallelize the work
- manually deploy each workflow iteration
That's the development loop that this launch unlocked
data context → workflow code → deployment → observable jobs → inspectable outputs → iteration
Today we launched a major Tilebox update, covered exclusively by Payload.
The core idea is: AI agents should not just answer questions about geospatial data. They should be able to build, run, inspect, and improve the workflows that produce those answers.
For physical-world data, the hard part is not only the model. The data is huge, fragmented, governed, and spread across providers, clouds, internal systems, sovereign environments, and eventually orbit.
If an agent has to guess the dataset, schema, runner, logs, or output provenance, it will eventually make things up.
So we built Tilebox around the engineering loop: discover typed data, define a workflow, run it where the data lives, observe logs/traces/task status/outputs, debug, and rerun.
That is what makes agents useful for EO: reviewable workflow execution, not black-box answers.
Thanks to @payloadspace for covering the launch.
https://t.co/VsWsw3VMkz
We're excited to sponsor Berlin Aerospace Hack, and I'm personally excited to be there at the kick-off tomorrow!
To offer the most, we're boosting @tileboxio Community Access tier capacity for this weekend, and can't wait to see what Berlin will build
140 people, one day and two nights
Let's go 🚀
Next week, we'll gather hackers, engineers, and founders at MotionLab Berlin for the first-ever Berlin Aerospace Hackathon:
Three days of hands-on building, experimentation, and innovation across aviation and space 🛰️
From autonomous flight systems to satellite networks and orbital logistics, teams will tackle some of the toughest challenges in aerospace.
We're really excited to have @BerlinMotionLab, Bifrost Defence, @tileboxio, @inflection_fund, and @RadicalAero as partners on board! 🚀
🚀 Hackathon Challenge #3: Mini-Constellation Tasking Planner
Build a 24–72h imaging plan for a 3–6 sat constellation: maximize AOI coverage, avoid clouds, respect sun-angle + off-nadir limits.
This is real mission-planning work.
Use @tileboxio to:
🛰️ Query ephemerides, terrain masks, cloud forecasts
⚙️ Run batch schedule evaluations
💾 Reuse cached visibility + weather lookups
🌍 Pull open EO data (S1/S2/S3, Landsat)
Deliver:
• Coverage map (footprints by sat/time)
• Tasking schedule (CSV/JSON)
• KPIs: coverage %, off-nadir, cloud-free area
• Compare vs. naïve baseline
This is exactly how real operators plan imaging windows.
Join the Berlin Aerospace Hackathon ↓
https://t.co/QJHt8XpwYK
🆕 #CNG2025 session video
Lukas Bindreiter shows how the @tileboxio workflow orchestrator helps process geo data at scale. He explains how its decentralized "task runner" architecture enables you to transition from local development to production-scale.
▶️ https://t.co/oL4eXl27Fd
🆕 #CNG2025 session recording
See how @tileboxio uses S2 Geometry for fast spatial queries on massive datasets. Lukas Bindreiter hows their polygon indexing for scalable catalogs
▶️ https://t.co/2FCjXQhMlB
Friday closing #LPS25 challenge:
In your metadata catalog, how many Sentinel 2A MSI L1C granules do you find in this AOI for 2024 between Tonga 🇹🇴 Samoa 🇼🇸 and Fiji 🇫🇯?
Bonus points if you know what issue I'm referring to
We'll be in Vienna Saturday till Tuesday. DM me or reply and let's meet and talk all about workflow orchestration, spatio-temporal datasets, catalogs, data pipelines and cal/val, in-orbit processing and clustered computing in space
10m resolution cloud-free Sentinel 2 mosaic over Ireland, Spring 2025
Open source code, ready to use, re-use, adapt, deploy as a service, and monetize
The code for this, dev to interactive map, was developed, deployed, executed within a bit more than 2 person days
Tilebox is ready to Go!
We just released our Go SDK and Go documentation, one of the most widely used languages for cloud-native apps.
Each code snippet in the @tileboxio docs is now available in both Python and Go.
Tilebox is sponsoring the EUSPA Cassini Hackathon Austria taking place in Innsbruck this weekend, all participants get two months free Tilebox Starter tier to speed up Copernicus data access, prototyping and service development
Participants, see you online!
Tilebox spatio-temporal datasets are now fully supported in all languages and you can create your own!
Core problems this solves:
- finding relevant data quickly (e.g. all Sentinel 2 granules along the US coastline) – Tilebox is now >100x faster than what's out there
- storing auxiliary geographic data (e.g. weather stations, ground truth, aeronet data, ...)
- cataloging higher level data
Tilebox at @cloudnativegeo in Snowbird!
We present
- the performance of spatio-temporal datasets
- the flexibility of Tilebox workflows
Ask Megan or Lukas for a coupon code if you want to try it out at high capacity!
Catch Lukas Bindreiter on stage for two technical deep dives:
- Beyond Points: Efficient Spatio-Temporal Polygon Indexing for Scalable Catalogs
- Tooling Designed for the Complexities of Space Data: A Hyperspectral Data Workflow
CNG Conference 2025 | April 30 - May 2
Meet @tileboxio at @SpaceCommExpo in London!
Let's talk about
- high performance data access, cataloging and distribution
- cloud agnostic, flexible, multi-environment data pipelines
- in-orbit processing with a level of developer experience you know from the ground
I'll be there March 11-12 (as well as before and after, since I call London my home now)
🛰️ Sentinel-2C data is out!
Tilebox Datasets integrates with a large number of open datasets, enabling every level of user to access valuable data right away. The first Sentinel-2C data points were released today, and it’s already integrated and ready for our users.
Check out our full Sentinel-2C support (both level 1C and 2A products) with a free Community Access account: https://t.co/NbZEFqtC1i