Engineering Blog
5 days ago
9min
What we learned working with robots to rewrite Hex
Eight hard-fought lessons for successfully using AI in software engineering


Nov 9, 2026
3min
Crashing the cost of data intelligence
Reducing the cost per conversation with the Hex agent by 75%.

Nov 4, 2026
6min
The AI sorcerer’s stone
What a summer of building a self-improving agent taught me about research, ephemerality, and curiosity.
Jul 29, 2026
7min
Caching is all you need
Our cache hit rate looked great. Our cost data disagreed. Here's what we found when we stopped trusting the average.
Author/ Zach Kirby & Olivia KoshyTags/ EngineeringMay 22, 2026
10min
How we built a lab to evaluate data agents
Inside Hex's eval architecture and the synthetic business it runs on.
Author/ Izzy MillerTags/ Engineering, ResearchMay 8, 2026
8min
How we built (and rebuilt) topic discovery into the Hex Context Agent
What are people actually asking your agent?
Author/ Charlene ChamblissTags/ Engineering, Research
Feed [17]
5 days ago
What we learned working with robots to rewrite Hex
Eight hard-fought lessons for successfully using AI in software engineering
Nov 9, 2026
Crashing the cost of data intelligence
Reducing the cost per conversation with the Hex agent by 75%.
Nov 4, 2026
What a summer of building a self-improving agent taught me about research, ephemerality, and curiosity.
Jul 29, 2026
Our cache hit rate looked great. Our cost data disagreed. Here's what we found when we stopped trusting the average.
May 22, 2026
How we built a lab to evaluate data agents
Inside Hex's eval architecture and the synthetic business it runs on.
May 8, 2026
How we built (and rebuilt) topic discovery into the Hex Context Agent
What are people actually asking your agent?
May 7, 2026
The golden age of the destination engineer
Why the engineers who care more about users than code are going to run the table.
Jan 14, 2026
Don’t be naked when the agents arrive
As AI agents absorb routine work, PMs and engineers need new leverage — judgment, focus, and clarity — to build the right thing.
Oct 22, 2025
Improving the Notebook Agent: error clustering
Why you should analyze your agent's reasoning, not just its errors
Apr 14, 2025
I'm sorry, but those are vanity evals
Using GPT-4.1 as a case study of our framework for impactful LLM evaluation
Mar 6, 2025
Beating browser bottlenecks with virtualization
Inside our new approach to virtualization
Jun 20, 2024
How we made AI charts generate 8x faster, going from an average response time of 10.3s to 1.3s
Nov 17, 2022
We took down production by misconfiguring our ETL
Here’s what we learned and how you can avoid it