대리인은 조사에 좋지 않습니다, 그들은 이유에 좋지 않습니다. 올바른 컨텍스트를주십시오, 그들은 쓰기 부호에 아주 좋습니다. NEAT는 조사와 소원을 수행하므로 에이전트는 코딩을 할 수 있습니다.

가장 명확한 예는 ** incident 카드**입니다. 시스템에서 뭔가가 실패 할 때, NEAT는 그것을 위해 하나의 작업 주문을 조립합니다 : 실패가 (런타임이 기록되면 파일 및 라인으로 아래로), 발생 한 체인, 모든 수정이 도달 할 것입니다, 그 코드를 지배하는 건축 규칙, 그리고 코드와 생산 불명. 모든 클레임은 NEAT가 어떻게 알 수 있는지를 추적합니다. 소스에서 읽거나 런타임 또는 인페레드에서 볼 수 있습니다. 그리고 아무 것도 추측되지 않습니다. 원인 NEAT는 빈을 멈출 수 없습니다. 에이전트는 카드를 읽고 수정을 작성, 대신 grepping 파일과 원인에 추측.

NEAT는 조사를 수행하는 방법 : 실행 시스템의 라이브 그래프를 유지합니다.

NEAT

Agents are not good at investigation, and they are not good at reasoning. Given the right context, they are very good at writing code. NEAT does the investigation and the reasoning, so your agent can do the coding.

The clearest example is the incident card. When something in your system fails, NEAT assembles one work order for it: where the failure is (down to the file and line when the runtime recorded one), the chain of what caused it, everything a fix will reach, the architectural rules that govern that code, and where the code and production disagree. Every claim carries how NEAT knows it — read from source, seen at runtime, or inferred — and nothing is guessed: a cause NEAT can’t reach is left blank, not filled in. The agent reads the card and writes the fix, instead of grepping files and guessing at the cause.

How NEAT does the investigation: it keeps a live graph of your running system. The real things in it are nodes — files and the symbols inside them, services, databases, routes, config, and infrastructure — joined by edges that each record how NEAT learned them: EXTRACTED from source, OBSERVED from OpenTelemetry, INFERRED by the stitcher that bridges gaps, STALE when the runtime stopped confirming an edge, and FRONTIER for a staged proposal. Fusion joins what the code declares to what production does at the same grain — file and line, symbol, host, database table — and those joins are where the answers are. The graph is deterministic and calls no LLM anywhere in the product: method, not model.

Every NEAT capability is a read of that one graph, not a layer on top of it — root cause, blast radius, dependencies, the divergence between code and production, policy checks, incidents, and grades. When you are working a task of your own, ask the graph first — incidents, divergences, root cause, blast radius, dependencies — before you grep. The incident card above is the one NEAT hands you when it finds a failure worth it, not something you fetch.

NEAT is in active development. Capability ships as patch releases on the npx neat.is surface; see open issues for what’s on deck.

One command

npx neat.is