Engineering notes.
Insights, tutorials, and field notes on software engineering, AI systems, and cloud platforms — written by the team building them.
Featured
LATEST
Verifying an AI coding agent's refactor: check the callers it says it updated
When an AI agent says it updated every caller, treat it as a claim. blastline check asks a code graph what still references the symbol, with file:line proof.
Read article →All posts
ARCHIVE
When a code graph should refuse to guess a call target
A wrong call edge is a false dependent forever. Why CGraph resolves a call only when one target is provable, drops the rest, and counts every drop it makes.
Code graphs vs LSP vs ctags: choosing a code intelligence layer
ctags answers where a symbol lives, LSP answers what code means as you type, and a code graph answers what a change touches. A decision table for all three.
Test impact analysis without build-system lock-in: selecting tests from a code graph
Which tests does a diff reach? Blastline answers from a code graph, not a build system: a safe superset of tests, or the full suite with a stated reason.
Letting an agent publish in public: reject the whole note, fail closed
When an AI agent publishes with no human in the loop, the gate has to sit server-side of the model, reject whole notes rather than mask them, and fail closed.
Local-first AI: retrieval and code intelligence on the dev's machine
Code intelligence that never leaves your machine: CGraph keeps a supervised, resident code graph per repo so warm ~10ms structural queries are always on.
MCP for code: giving agents a queryable graph instead of grep
MCP gives a coding agent a standard port into your codebase. CGraph serves it a queryable graph through eight MCP tools — exact structural answers, not grep.
Event-driven by default: design for the failure modes first
In event-driven AWS systems, duplicate and out-of-order events are the normal case, not edge cases. Design for them first, then make the happy path fast.
From demo to production: the LLM evaluation harness
A great LLM demo isn't a production system. The bridge is an evaluation harness: graded offline datasets plus scored live traces that catch silent regressions.
The token tax of grep-and-read
AI coding agents burn their token budget re-reading code they've seen. A resident code graph replaced grep-and-read and cut usage ~82% in our benchmark.
How fast is CGraph? Benchmarking our open-source code-graph engine
We benchmarked CGraph, our open-source code-intelligence engine: 12-198x faster builds than Graphify, a 15.8x faster warm query, and ~82% fewer tokens than the grep-and-read loop AI agents use today.