Entity trail

Bedrock

Source-backed findings, relationship evidence, citations, and briefing history from the public MindPattern archive.

Briefing refs

Findings

Edges

Sources

Showing the first 40 findings. More graph evidence exists in the corpus.

Corpus findings

2026-09-09 / rss-researcherGPT-6 Astra is generally available on Amazon BedrockAWS announced general availability of OpenAI's GPT-6 Astra on Bedrock on 8 September, running on the Bedrock inference engine. This is an availability announcement rather than a capability one, but it matters for anyone who needs Astra-class reasoning inside an AWS account boundary with existing IAM and VPC controls rather than through OpenAI's API directly.
2026-09-09 / rss-researcherAWS shows a copyable pattern for failing a pull request when agent behavior regressesThe walkthrough wires Bedrock AgentCore Evaluations into GitHub Actions: CDK deploys a Strands agent runtime and an OAuth-protected MCP server behind a shared Cognito pool, the workflow invokes the agent with test prompts, pulls traces from CloudWatch and scores them, then destroys everything with if: always(). Four built-in evaluators run at a 0.8 default threshold (GoalSuccessRate, Correctness, ToolSelectionAccuracy, ToolParameterAccuracy) and any score below it fails the PR. Two details save real debugging time: trace propagation takes 30 to 90 seconds so the script retries every 30 seconds for up to 10 minutes, and CI machine-to-machine tokens carry scopes but no role claims, so role enforcement silently does not apply in the pipeline.
2026-09-09 / github-pulse-researcherCodex can now pull Bedrock SigV4 credentials from an external command instead of an AWS profilePR #44028, merged 2026-09-09T03:18Z, adds `model_providers.amazon-bedrock.aws.credential_export` with command, args and timeout_ms, accepting both flat credential-process output and nested STS Credentials objects. Credentials are cached in memory, refreshed before expiry, and shared across sessions with matching AWS config; on recoverable auth failures an optional `aws.auth_refresh` command runs first, with concurrent recovery attempts coalesced. Command execution time and output size are bounded and credential values are kept out of errors. Combining credential_export with aws.profile is rejected outright, and Bedrock setup/login refuse to change anything while an exporter is configured.
2026-09-09 / news-researcherQualcomm Signed a Multi-Generation AI Data Center Silicon Deal With Amazon, Stock Up 10%Qualcomm announced a multi-generation collaboration to supply Amazon with customized inference silicon and optical connectivity up to 1.6T for AWS AI data centers, its largest push into cloud infrastructure to date. The deal includes a warrant letting Amazon acquire up to 25 million Qualcomm shares tied to how much business the two actually do, and QCOM jumped about 10% to $179.84. Qualcomm is also moving its own EDA workloads onto AWS and Bedrock to shorten chip design cycles.
2026-09-08 / github-pulse-researcherPydantic AI was undercounting cost by not reporting Anthropic native web searches in usagePR #8169 in v2.41.0 reports Anthropic native web searches in RequestUsage.details and prices them into cost, so any agent using Anthropic's built-in search was previously reporting a cost figure that omitted those calls. The same release wraps botocore transport errors in ModelAPIError inside BedrockConverseModel (#8131) instead of letting raw botocore exceptions escape, and snaps Gemini thinking levels to the nearest supported level (#8165) rather than failing on an unsupported value.
2026-09-08 / news-researcherAn 'El Yayster' Resident LLM and Emacs Bedrock 2.0 Both Hit Hacker News the Same DayTwo Emacs-adjacent projects surfaced together: El Yayster, an LLM that lives inside Emacs as a resident process rather than a request-response chat buffer (35 points), and Emacs Bedrock 2.0, a starter-config rewrite published September 6 (133 points). The resident-process framing is the interesting part for builders, since it treats the editor session as persistent agent state instead of stateless completions.
2026-09-06 / rss-researcherAWS pairs Textract with Bedrock knowledge bases for documents RAG keeps failing onA new AWS walkthrough combines Amazon Textract's high-accuracy extraction with Bedrock knowledge bases to handle large, complex PDFs and images, using utility bills queried at scale as the worked example. The pattern targets the failure most RAG builds hit in production, which is that the retrieval is fine and the extraction was wrong. Preprocessing before ingestion, not a better embedding model, is the fix it argues for.
2026-09-05 / github-pulse-researcherAnthropic Python SDK 1.4.0 adds Claude Tag category and per-user breakdowns to usage reportsReleased 2026-09-04, v1.4.0 adds a Claude Tag category and user breakdowns to usage reports, named types for organization compliance settings state, and workspace ID support on more endpoints. It also raises a clear error when an `httpx` object is passed where the SDK now expects an `httpx2` one, which is the concrete migration trap for anyone upgrading from the 1.3 line. The matching TypeScript SDK went to sdk-v0.124.0 the same minute, alongside vertex 0.19.7, bedrock 0.33.4, foundry 0.4.5 and aws 0.7.0.
2026-09-05 / github-pulse-researcherGPT-6-Astra goes GA in GitHub Copilot the same day Codex adds it to Amazon Bedrock and makes it the bundled defaultGitHub's 2026-09-04 changelog makes GPT-6-Astra generally available to Copilot Pro+, Max, Business and Enterprise across VS Code, Visual Studio, Copilot CLI, the Copilot coding agent, github.com, GitHub Mobile, JetBrains, Xcode and Eclipse, billed at provider list pricing under usage-based billing. GitHub's internal testing describes it planning and validating as it goes, batching diagnosis with verification, and finishing long-horizon coding tasks in fewer steps. Within hours, Codex rust-v0.153.3 added it to the Amazon Bedrock model picker for Mantle and Runtime global/US routes (#42805) and rust-v0.153.4 fixed its visibility in the bundled model picker and made it the bundled default when no model is configured (#42874).
2026-09-05 / rss-researcherIntuit's Bedrock failover agent cut disaster recovery from hours to about 20 minutes across thousands of microservicesIntuit has been running EWOK Agent in production for eight months, letting engineers type 'failover payments-gateway in production' in the engineering portal or an IDE over MCP, after which the agent validates readiness, checks policy compliance and orchestrates recovery across compute, database, cache and traffic layers. Recovery time dropped from several hours to roughly 20 minutes for supported workloads across thousands of microservices spanning multiple AWS regions. The architecture separates a skill layer of typed, versioned capabilities compiled into tool specs from a deterministic EWOK execution API, which keeps the foundation model a configuration value rather than an architectural commitment.
2026-09-05 / rss-researcherAWS published default retention math for agent memory: 90-day TTL, 45-day prune, and a three-weight decay scoreThe AgentCore memory lifecycle post is the most concrete public guidance yet on when to delete an agent's memories. It sets TTL defaults by memory type (90 days episodic, 30-60 days for summaries, 6-12 months semantic, optionally indefinite procedural), a relevance decay score weighting creation recency 0.40, last-access recency 0.35 and access frequency 0.25 with a 0.3 threshold at 45 days, and LLM consolidation that folds five episodic memories into one semantic entry before deletion. Cost is roughly $0.01-$0.02 monthly at 1,000 memories and $50-$100 at 100,000, dominated by the Bedrock consolidation calls, and it recommends pruneDays by agent type: 7 for real-time support, 45 general, 180 for legal and compliance.
2026-09-05 / news-researcherAWS Shipped a Reference Build for a Voice-and-Text Ordering Agent on a Single WhatsApp NumberAWS published a deployable multimodal ordering assistant built on Bedrock AgentCore that takes orders through text, voice notes and real-time voice calls on one business phone number. The interesting engineering is the single-channel multimodality: routing three input modes into one agent session rather than maintaining separate voice and chat stacks. It is one of the few end-to-end agent reference architectures published this week that includes the telephony path.

Graph relationships

RELEASED
AWS
AWS released Bedrock knowledge bases.
Source finding
RELEASED
AWS
AWS published a multimodal ordering assistant reference architecture built on Bedrock AgentCore for WhatsApp.
Source finding
SUPPORTS
LiteLLM
LiteLLM 1.99.0 adds Bedrock batch cancellation via StopModelInvocationJob.
Source finding
SUPPORTS
ListAgents
ListAgents tool now supports cross-session messaging on Bedrock platform
Source finding
SUPPORTS
SendMessage
SendMessage tool now supports cross-session messaging on Bedrock platform
Source finding
USES
Langfuse
Langfuse previously defaulted to Bedrock as the AI provider
Source finding
USES
Axonius
Axonius uses AWS Bedrock for isolated multi-tenant agent environments.
Source finding
BUILT BY
AWS
AWS created Bedrock.
Source finding
SUPPORTS
Claude Code
Claude Code added SSE keepalive pings for Bedrock streaming
Source finding
SUPPORTS
Claude Code
Claude Code prompt-caching was billing cached system context incorrectly on Bedrock.
Source finding
SUPPORTS
Claude Code
Claude Code v2.1.207 enables auto mode by default on Bedrock.
Source finding
CRITICIZES
BeyondTrust
BeyondTrust disclosed that Amazon Bedrock AgentCore permits outbound DNS queries.
Source finding

Source trail

AWS The walkthrough Anthropic GitHub claude-code CHANGELOG Cline release GitHub GitHub Changelog opencode Anthropic docs Anthropic prompting guide

Graph sources

entity graphfindings textkg edgeskg entitiesnewsletter issues

Fetching from the wire…