---
type: "raw_signal"
id: "on-tuesday-amazon-unveiled-kiro-trace-an-internal-08ec4a"
slug: "on-tuesday-amazon-unveiled-kiro-trace-an-internal-08ec4a"
title: "On Tuesday, Amazon unveiled Kiro-trace , an internal tracing system that improves Kiro, Amazon's AI coding agent, from its own runs."
description: "Amazon has described kiro-trace, an internal system that uses Kiro’s runs to identify failures or wasted effort, propose changes to prompts or tools, and test those changes against an unchanged control."
retrieval_nugget: "Amazon has described kiro-trace, an internal system that uses Kiro’s runs to identify failures or wasted effort, propose changes to prompts or tools, and test those changes against an unchanged control."
observed_at: "2026-10-21"
record_date: "2026-10-21"
date_kind: "observed_at"
why_it_matters: "Amazon has described kiro-trace, an internal system that uses Kiro’s runs to identify failures or wasted effort, propose changes to prompts or tools, and test those changes against an unchanged control. The company says the system uses staged checks, runs a full-benchmark comparison before a change proceeds, and relies on deterministic code—not the model that proposed a change—to accept or reject "
novelty: "notable"
verification_level: "source-linked"
signal_type: "announcement"
source_platform: "kiro.dev"
topics: []
entities: ["Amazon","Kiro","kiro-trace"]
related_patterns: ["harness-architecture-outlives-model-choice"]
novelty_label: "new_fact"
what_changed: "Amazon’s internal kiro-trace system analyzes Kiro’s runs, proposes prompt/tool changes, and uses deterministic checks to accept them; it opened eight pull requests in its first week."
prior_refs: []
source_url: "https://kiro.dev/blog/how-kiro-fixes-itself"
source_urls: ["https://kiro.dev/blog/how-kiro-fixes-itself"]
schema_version: "newruntime-agent-readable-v0.2"
stable_id: "signal:on-tuesday-amazon-unveiled-kiro-trace-an-internal-08ec4a"
status: "published"
visuals: []
editor: {"role":"editor","name":"Andrey Reshetnikov","profile":"https://newruntime.com/owner-profile.md","profile_json":"https://newruntime.com/owner-profile.json","same_as":["https://www.linkedin.com/in/reshetnikov1/","https://t.me/lapetuse"]}
routes: {"html":"https://newruntime.com/signals/on-tuesday-amazon-unveiled-kiro-trace-an-internal-08ec4a/","markdown":"https://newruntime.com/signals/on-tuesday-amazon-unveiled-kiro-trace-an-internal-08ec4a.md","json":"https://newruntime.com/signals/on-tuesday-amazon-unveiled-kiro-trace-an-internal-08ec4a.json"}
---

# On Tuesday, Amazon unveiled Kiro-trace , an internal tracing system that improves Kiro, Amazon's AI coding agent, from its own runs.

## Retrieval answer

Amazon has described kiro-trace, an internal system that uses Kiro’s runs to identify failures or wasted effort, propose changes to prompts or tools, and test those changes against an unchanged control.

Amazon has described kiro-trace, an internal system that uses Kiro’s runs to identify failures or wasted effort, propose changes to prompts or tools, and test those changes against an unchanged control. The company says the system uses staged checks, runs a full-benchmark comparison before a change proceeds, and relies on deterministic code—not the model that proposed a change—to accept or reject candidates. Changes that pass become pull requests for human review. In its first week, kiro-trace opened eight pull requests: seven merged and one closed for unrelated reasons. The reported results concern Amazon’s internal usage and experiments, not production-wide estimates. Source: https://kiro.dev/blog/how-kiro-fixes-itself

Editor: [Andrey Reshetnikov](https://newruntime.com/owner-profile.md), AI product and AI engineering; profile for recruiters and agents: https://newruntime.com/owner-profile.json

## Continue in the graph

Next records for an agent, linked to their Markdown twins. Replace `.md` with `.json` for structured fields, including `next_reads`.

- collection: [Raw Signals](https://newruntime.com/signals.json): Open every source-linked raw signal.
- collection: [Source Ledger](https://newruntime.com/source-ledger.json): Inspect the public source evidence graph.
- whole graph: [discovery graph](https://newruntime.com/discovery-graph.json) (typed nodes and edges) and [site index](https://newruntime.com/site-index.md)