Anyshift vs Bluebricks (2026)

Integrations cover AWS, GCP, Azure, Cloudflare, GitHub, GitLab, Kubernetes, Datadog, Grafana, Splunk, PagerDuty, incident.io, Sentry, Jira, Confluence, Notion and Linear. Annie posts RCA results as PagerDuty notes and incident.io comments and opens pull requests through a separate agentic GitHub app. The integrations number 25+, and the graph also reads Terraform code and Terraform state.

SourceAnyshift, docs.anyshift.io Root Cause Analysis, Propose Fix and llms.txt indexread 2026-10-05

The agent's write tools open pull requests, run deployments and handle approvals across AWS, Google Cloud and Azure from IaC in the customer's repositories, and remediation integrates with Wiz, Prisma Cloud and CrowdStrike findings.

Sourcebluebricks.co/docs/agent/agents-overviewread 2026-09-29

Annie runs its own investigation across the graph, logs and traces and returns a timeline, root cause and remediation steps, coordinating specialized agents along the way. Customers tune it with instructions, personas and effort modes, and automation rules route Slack messages with fallbacks for each sender and a fixed default. There is no builder, branching or multi agent flow that customers control.

SourceAnyshift, docs.anyshift.io Root Cause Analysis and llms.txt indexread 2026-10-05

Bluebricks runs plan and apply across a blueprint's directed acyclic graph, executing packages in parallel by dependency and passing each package's outputs to the next, across collections and environments with promotion between them.

Sourcebluebricks.co/docs/orchestration/runsread 2026-09-29

RCA starts automatically when an incident is created in PagerDuty or arrives through a webhook from incident.io, and investigations also start on demand from Slack and the Remote MCP, from pull request analysis and from proactive detection. Saved reports can run on a schedule, and automation rules let Annie act on Slack messages by itself.

SourceAnyshift, docs.anyshift.io Root Cause Analysis and llms.txt indexread 2026-10-05

An alert sent by a supported monitoring tool, Coralogix, opens an integration thread in which the agent starts investigating on its own. GitOps environments trigger plans from git pushes, and drift detection runs automatically.

SourceBluebricks docs, Integration threads and llms.txt index; bluebricks.co/docs/agent/integration-threadsread 2026-09-29

Annie and other agents query one versioned knowledge graph of infrastructure, applications, identity and team tools, with timestamped state changes and entity resolution that joins an EC2 instance, a Kubernetes pod, a GitHub repo, a Jira ticket and a Confluence page into single nodes. The graph links Terraform code, Terraform state and live infrastructure, and change history shows what changed and when before an incident.

SourceAnyshift, anyshift.io and docs.anyshift.io llms.txt indexread 2026-10-05

A context layer and cloud graph cover every resource, relationship and dependency in the connected cloud accounts, whether managed by code or not, built from IaC, configs and live cloud state, and the agent reasons over them.

Sourcebluebricks.co/docs/agent/agents-overviewread 2026-09-29

After each investigation Annie reflects and curates learnings that inform later investigations, covering infrastructure patterns, normal baselines and error signatures, effective queries and dashboard locations, and which services power which features and who owns them. Users add custom knowledge Annie cannot learn on its own, such as team conventions, vendor specifics and escalation procedures. Anyshift does not say who the learnings apply to, how long they are kept or how to view or delete them.

SourceAnyshift, docs.anyshift.io Memory and Agentsread 2026-10-05

Bluebricks keeps every message and action in each task's history, and a task can be resumed later where it left off. No retention period is published, and the agent keeps no memory that carries from one task to the next. Infrastructure state and deployment history are the application's own record.

Sourcebluebricks.co/docs/agent/agents-overviewread 2026-09-29

Annie's only write action, a fix pull request, runs when a person clicks Propose Fix on a hypothesis or answer. Write access is isolated in a separate agentic app while investigation stays read only, and nothing reaches production until a person merges the pull request.

Sourcedocs.anyshift.io/pages/product/propose_fixread 2026-09-29

The agent never auto-approves. It presents each plan and waits for confirmation before applying, collection policies add owner approvals, cost limits and blueprint allowlists, and the agent inherits the user's permissions and cannot bypass role restrictions.

Sourcebluebricks.co/docs/agent/governanceread 2026-09-29

Role based access control, multi factor authentication and single sign on are supported, with roles and permissions set out in their own documentation. Anyshift holds AICPA SOC 2 Type II, covering security, availability, processing integrity, confidentiality and privacy, and a trust portal is published at trust.anyshift.io. The platform runs on AWS with encrypted storage, data isolation and retention policies, and code is scanned continuously for secrets, vulnerabilities and risky dependencies.

SourceAnyshift, docs.anyshift.io compliance and llms.txt indexread 2026-10-05

Role based access with per role permissions, SSO setup, collection policies and owner approvals, and audit logs of every agent action make up the control surface. No attestation is published, and the trust center at trust.bluebricks.co is empty.

SourceBluebricks docs, Agent Governance and llms.txt index (Roles and Permissions, SSO); bluebricks.co/docs/agent/governanceread 2026-09-29

Each RCA carries a timeline of events, root cause details with evidence from the customer's systems and affected resources, and fix PRs link back to the conversation, but there is no record of the steps, queries or tools Annie used in the run, and retention is not stated. Saved reports can be reused and scheduled, and change history shows what changed, when, and what came before an incident.

SourceAnyshift, docs.anyshift.io Root Cause Analysis and llms.txt indexread 2026-10-05

Every approval, rejection and action taken through the agent is recorded, task history keeps the plans, decisions and outcomes, and each run records plan output, apply logs, inputs, outputs and state changes.

Sourcebluebricks.co/docs/orchestration/runsread 2026-09-29

The product is SaaS with a 30 minute setup, and there is no self hosting, VPC, region or residency option. The service runs on AWS.

SourceAnyshift, docs.anyshift.io complianceread 2026-10-05

Bluebricks runs as SaaS or with a self hosted runner. The Bluebricks Deployments Controller runs as a Kubernetes operator to run IaC tasks in the customer's own cloud account, with an Orchestrator in a Box option and self hosted cloud guidance, across AWS, Google Cloud and Azure.

SourceBluebricks homepage and docs llms.txt index; bluebricks.coread 2026-09-29

There is one agent, Annie, with product capabilities (RCA, reports, proactive detection, propose fix) and Graph API use cases (alert noise, configuration churn, pull request blast radius). Those are features of one product, not separate agents or templates a customer adopts. Saved reports can be reused across the team.

SourceAnyshift, docs.anyshift.io llms.txt indexread 2026-10-05

Blueprints are reusable templates customers create from their own code, and the agent's prebuilt workflows for discovery, drift detection, codification and right sizing are capabilities of one agent. There is no vendor shipped blueprint catalog.

SourceBluebricks docs, Agent Overview and llms.txt index; bluebricks.co/docs/agent/agents-overviewread 2026-09-29

Anyshift lists its model providers among its external providers, and customers cannot choose the model. An effort mode trades speed against depth of reasoning, and personas set tone, depth and assumptions, but neither changes the model.

SourceAnyshift, docs.anyshift.io compliance and llms.txt indexread 2026-10-05

The models behind the Bluebricks agent are not disclosed, and there is no customer choice of model. The agent can be driven from Claude Code or any MCP client, but that does not let the customer pick its model.

Sourcebluebricks.co/docs/agent/agents-overviewread 2026-09-29

There is a read only Graph API over HTTP with a TypeScript SDK (@anyshift/graph-sdk), a CLI, a Graph MCP server and a published OpenAPI specification, plus Annie Remote MCP for triggering RCA from an IDE. The Graph API serves code, CI pipelines, internal platforms and other AI agents, and the CLI works from the terminal, scripts and CI.

SourceAnyshift, docs.anyshift.io Graph API and llms.txt indexread 2026-10-05

A REST API at api.bluebricks.co/api/v1, with long lived API tokens or JWT bearer authentication, manages collections, blueprints, environments and their logs and cloud account connections. The Bricks CLI has a full command reference, and a Bluebricks MCP server can provision, plan and deploy.

SourceBluebricks docs, API overview and llms.txt index; bluebricks.co/docs/api/readmeread 2026-09-29

Pull request blast radius and drift detection check the customer's infrastructure changes before they ship, which tests the change, not the agent. There is no way to test Annie's own answers. Drift detection shows the gap between what Terraform declares and what is actually running.

SourceAnyshift, docs.anyshift.io llms.txt indexread 2026-10-05

The plan phase reports resources to create, update and destroy before apply, and policies check cost and allowlists. Those checks validate each infrastructure change, and there is no agent evaluation harness.

Sourcebluebricks.co/docs/orchestration/runsread 2026-09-29

Annie works through integrations, read only live queries, Slack, pull requests, an API and MCP, and does not control a browser, desktop or computer. The only write access sits in a separate agentic GitHub app that opens fix pull requests.

SourceAnyshift, docs.anyshift.io Root Cause Analysis and Propose Fixread 2026-10-05

The agent acts through IaC tools, cloud APIs, a CLI, an API and an MCP server, with no browser, desktop or computer control.

Sourcebluebricks.co/docs/agent/agents-overviewread 2026-09-29