Writing

Running two multi-agent workflows — one for research and planning, one for execution and review — across a week of software projects, and what actually held up.

Borrowing divergent-thinking techniques from creativity research to push agent workflows toward structurally diverse solutions instead of the first obvious one.

Coding agents fail unpredictably because they are a complex system layered on another complex system — the codebase — and prompt engineering alone can't tame the emergent failures.

On the Agent Advocate role at Sourcegraph — advocating for the infrastructure that lets coding agents work reliably in production, not just better prompts.

Building CodeScaleBench — task design, verification, QA, and the infrastructure orchestration behind a benchmark for coding agents on large, multi-repo codebases.

Where today's coding-agent benchmarks fall short, and how to measure agent performance with stronger context retrieval at enterprise scale.

A working Amp practice after four months of heavy use — planning, context management, and verifying code across many projects.

A secure iPhone-to-Mac setup with Blink Shell and Tailscale to run the Amp CLI and manage coding projects from a phone.

An automated Slack bot that triages security advisories, generates detection queries, and produces content artifacts to speed up vulnerability response.

Five repeatable failure patterns for coding agents in large codebases — and why the fix is retrieval and code-search infrastructure, not just better models.

The real engineering requirements and costs of building an internal code-intelligence platform equivalent to a commercial offering.

Using Deep Search and Code Search to find repositories exposed to poisoned LiteLLM packages, separating version-pinned code from genuinely at-risk dependencies.

A benchmark for evaluating how coding agents perform on enterprise-scale, multi-repo software development tasks across the full SDLC.

New high-severity React Server Components vulnerabilities surfacing after incomplete initial patches — denial of service and source-code exposure — with remediation guidance.

Automating remediation of CVE-2025-55182 across many repositories with Batch Changes, the MCP server, and Deep Search — applying patches, tracking progress, and validating fixes at scale.

An operational guide to deploying AI coding agents in large enterprise environments — context engineering, code retrieval, review pipelines, and human oversight.

Why universal code search across every repo, branch, and code host — on a unified platform — is essential to stay productive as codebases grow.

A report on how AI coding agents perform against enterprise-scale codebases, finding that code understanding and context-retrieval quality are the primary drivers of success.