Sign InOpen Brain
AI EngineerVideoSource Linked

How We Solved Agent Building — Andrew Qu, Vercel

Vercel’s data agent improved after replacing prescriptive specialist pipelines with a filesystem, Bash and company-specific context. Eve packages that pattern as conventions.

AI Engineer · Sep 14, 2026
Open Source Open MarkdownOpen JSON
Source Summary

Vercel’s internal data agent began around **30% on its evals**. Moving from tightly scoped specialist agents toward a sandboxed filesystem agent with Bash, file access and company context **roughly doubled the eval score**, according to the talk.

Practical Implication

Builders should test whether a capable agent can navigate domain files and a few general tools before encoding every workflow edge. Keep proprietary semantics in inspectable files and skills; use framework conventions only where they reduce runtime, deployment and channel plumbing.

Agent-Ready Context
Vercel’s internal data agent began around **30% on its evals**. Moving from tightly scoped specialist agents toward a sandboxed filesystem agent with Bash, file access and company context **roughly doubled the eval score**, according to the talk.

Builders should test whether a capable agent can navigate domain files and a few general tools before encoding every workflow edge. Keep proprietary semantics in inspectable files and skills; use framework conventions only where they reduce runtime, deployment and channel plumbing.

The results describe one internal data workload rather than a published general benchmark. Eve packages the final architecture, but the talk does not establish how much improvement came from the filesystem, newer models, revised context or other simultaneous changes.
Connected Context · Feed7 Judgment

This adds unusually concrete internal eval evidence to the filesystem-agent pattern, but does not isolate which architectural change produced the gain. Against the candidates, it supports testing a general agent with inspectable domain context before building specialist pipelines, while strengthening the need for stable task contracts, trace-based diagnosis and controlled comparisons before generalizing the reported improvement.

Agents Without Code: Skills, YAML, and Filesystems Replaced Python — Philipp Schmid, Google DeepMindThe pull-request agent independently reaches the same minimal architecture of general tools, files and skills, while emphasizing that outcome evals remain necessary.The Unreasonable Effectiveness of Separating the Task from the Model — Maxime Rivest & Isaac MillerDSPy’s separation of task contracts from models and harnesses is a prerequisite for determining whether the reported eval gain came from architecture rather than simultaneous implementation changes.Improving Agents is a Data Mining Problem — Vivek Trivedy, LangChainTrace mining provides the next diagnostic step: recurring production failures can seed replayable evals and identify whether context, tools, orchestration or models need adjustment.The Building Blocks of GTM Orchestration — Arman Vaziri, RampRamp shows that extending this pattern across business workflows requires shared entity context and durable execution, not merely a filesystem and Bash.
Context Map
agentcodingdata#harness-engineering#skills#agent-evals
Uncertainty
The results describe one internal data workload rather than a published general benchmark. Eve packages the final architecture, but the talk does not establish how much improvement came from the filesystem, newer models, revised context or other simultaneous changes.