What even is code mode?
Code mode lets an agent write code that calls its tools, instead of calling them one at a time. It was introduced for MCP, but it works for any agent. How Polylane's agent uses it, and what the data says.
Boris Tane Research
Research on agents, models, and how they reason.
Boris Tane 
How to build a memory system for proactive agents
Proactive agents run without a prompt, so each run has to start from what earlier runs learned. How we built memory for Polylane's agents on git: one repository per team, a nightly clean-up, and lessons from merged pull requests.
Boris Tane 
Nobody reads pull request descriptions, so we made videos
Almost none of the pull requests Polylane opens were asked for by an engineer, and a longer description does not make them easier to review. We are experimenting with a narrated video for every fix. Why, what it looks like, and what happened to merge rates.
Vi Tran and Boris Tane 
We swapped our LLMs for Jev. It's 39% cheaper.
Our agent makes thousands of small decisions a day. We moved them from LLMs to Jev, a model that doesn't write text, and cut the cost by 39%.
Vi Tran and Boris Tane 
Sub-agents are just wrong
Polylane's autofix used to be a workflow of multiple agents, each responsible for a single task, with an orchestrator managing state between them. We moved to a single agent which does the entire job, from evidence gathering, hypothesis testing to pull request.
Aleksandr Diamond and Boris Tane No posts match that search.