Team convention reviewer built from labeled agent pushback traces
Capture every coding-agent session your team runs, label the moments where an experienced engineer pushes back on the agent, and turn those labeled corrections into a skill, eval set, or fine-tuned model that reviews new pull requests as if it were that senior teammate.
online B2B Deep Tech / Infrastructure
From AI Engineer — Every Correction You Give Your Agent Is Data - Brian Douglas, Paper Compute at 03:43
Problem: Generated code compiles but violates decisions an experienced teammate would catch, so the junior engineer who cannot judge the code gets pushback only at PR review time. Expert objections happen in private agent sessions and disappear because nobody preserves them.
For: Engineering teams adopting coding agents where the team has internal API and codebase conventions that a general model does not know.
Products from this video
Braintrust Brev.dev Daytona Fireworks Paper Console Stereos Sweeper Agent tapes
Examples
- Paper Compute's Twin Review prototype: reviews a PR as if a specific senior engineer (whose Go/Rust pushback was labeled) were reviewing it; not publicly released because the data is sensitive.
Other takes on AI model development
- Retrain small open-source language models for long-horizon agentic workloads and sell efficient inference and on-device deployments
- AI simulation company that models human behavior and lets organizations test decisions against simulated populations
- An open foundation-model company focused on coding and long-horizon software tasks
- Enterprise context and training-data infrastructure for AI applications
- In-database semantic analytics using large database models
- A domain-specific AI product built around private data, specialized models, and purpose-built workflows