← All implementations

monday.com · Agent system

Sphera / Atlas / Morphex

An internal agent system on Amazon Bedrock where agents have identities, managers, scopes, and performance scores; Atlas ships features, Morphex ships PRs autonomously.

1

Approach type
Agent system
Work
Coding, Code review
Human involvement
Autonomous
Invocation
Event driven, Interactive
Interfaces
Slack, Monday, Github
Deployment stage
Scaled
Evidence strength
Secondary only
Entry reviewed

How it works

The workflow the sources report for this implementation.

Stable identity + assigned human manager + scope + performance score

1

Automated review against monday standards (metrics, feature flags, security)

1

MEMORY.md + daily diary instead of vector retrieval

1

monday boards as the shared-state layer for human/agent collaboration

1

Where people stay involved

  • Atlas or Morphex feature task → tested and merged pull requestOutcome review · Level 4

Level 4 for Atlas or Morphex feature task → tested and merged pull request; human attention boundary: outcome-review.

1

Observation date
2026

Implementation details

Sandbox

Amazon EKS, one pod per active session; a remote sandbox tests each PR before review; EFS workspace mount

1

Harness

Claude Agent SDK behind a thin monday-agent-sdk wrapper (provider neutrality, cold-start optimization, custom harness opinions)

1

Model

Amazon Bedrock; Application Inference Profiles for routing; cross-region failover; PrivateLink (traffic stays in VPC)

1

Interfaces

slack, monday, github

1

Tool access

Triggers via Slack @mention, monday item assignment, or GitHub PR review → SNS → per-team SQS → consumers; monday MCP servers underpin the Guardrails

1

Knowledge

File-based memory: MEMORY.md (cross-session) + diary/YYYY-MM-DD.md; sessions/repos/secrets on EFS; durable records on S3

1

Credentials

Per-session secrets in AWS Secrets Manager; same RBAC as humans; real Slack/GitHub/monday accounts

1

Context management

Live state in ElastiCache (sub-ms); monday boards (Builders CoWORK) as shared state for tasks, status, handoffs

1

Reported results and limitations

The catalog records what the sources report, with the scope and the denominator of every figure. A qualification below limits the figure it sits under.

Reported metrics

Headline claim

Morphex: 19 of 20 PRs merge without human review

1

Reported by
monday.com
Scope
Morphex PRs that merge automatically after CI and Guardrails pass
Denominator
Morphex pull requests; sample size and period not supplied
Key observation

Morphex: 19 of 20 PRs merge automatically without human review

1

Reported by
monday.com
Scope
Morphex PRs that merge automatically after CI and Guardrails pass
Denominator
Morphex pull requests; sample size and period not supplied
Key observation

90% of Builders use AI coding tools monthly; adoption nearly doubled year over year

1

Reported by
monday.com
Scope
Monthly AI coding-tool adoption among monday Builders, including engineers, PMs, analysts, and designers
Denominator
Builders; not exclusively engineers
Key observation

Per-engineer PR throughput increased by more than 50%

1

Reported by
monday.com
Scope
Per-engineer pull-request throughput
Denominator
Engineers; baseline period and cohort size not specified
Key observation

Guardrails catches ~25% of agent PRs before human review; low single-digit revert rate

1

Reported by
monday.com
Scope
Recent cut of top PR-generating agents; Guardrails rejection before review and reverts among merged PRs
Denominator
Agent PRs for Guardrails rejection; merged PRs for revert rate

Lessons and interpretation

Evals from day one; should have been day one, not month nine

1

Skip the vector store; file-based memory (MEMORY.md) was the right answer

1

Remote-sandbox every PR before human review, with production-traffic replay

1

The existing auth/identity/deploy pipeline applies to agents; reuse it

1

AI engineering is building the feedback loops that let imperfect agents be trusted safely

1

Sources and research details

Citations link to the original publisher. Each source also keeps a preserved copy in the repository, so a changed or removed page stays checkable.

  1. AI Teammates: how monday.com runs production AI agents on Amazon Bedrockhttps://aws.amazon.com/blogs/machine-learning/ai-teammates-how-monday-com-runs-production-ai-agents-on-amazon-bedrock/Case study · Independent secondary · Last source verification: 2026-08-31
    Preserved copy ↗
Research details for every claim on this page
  1. Summary
    Statement type
    Fact
    Provenance
    Reported
    Confidence
    Medium
    Confidence reason
    A linked participant or independent source reports the claim.
  2. Headline claim
    Statement type
    Metric
    Provenance
    Reported
    Confidence
    Medium
    Confidence reason
    A linked participant or independent source reports the claim.
    Reported by
    monday.com
    Scope
    Morphex PRs that merge automatically after CI and Guardrails pass
    Denominator
    Morphex pull requests; sample size and period not supplied
    Method
    Not reported
    Observation date
    Not reported
  3. Sandbox
    Statement type
    Fact
    Provenance
    Reported
    Confidence
    Medium
    Confidence reason
    A linked participant or independent source reports the claim.
  4. Harness
    Statement type
    Fact
    Provenance
    Reported
    Confidence
    Medium
    Confidence reason
    A linked participant or independent source reports the claim.
  5. Model
    Statement type
    Fact
    Provenance
    Reported
    Confidence
    Medium
    Confidence reason
    A linked participant or independent source reports the claim.
  6. Interfaces
    Statement type
    Fact
    Provenance
    Reported
    Confidence
    Medium
    Confidence reason
    A linked participant or independent source reports the claim.
  7. Tool access
    Statement type
    Fact
    Provenance
    Reported
    Confidence
    Medium
    Confidence reason
    A linked participant or independent source reports the claim.
  8. Knowledge
    Statement type
    Fact
    Provenance
    Reported
    Confidence
    Medium
    Confidence reason
    A linked participant or independent source reports the claim.
  9. Credentials
    Statement type
    Fact
    Provenance
    Reported
    Confidence
    Medium
    Confidence reason
    A linked participant or independent source reports the claim.
  10. Context management
    Statement type
    Fact
    Provenance
    Reported
    Confidence
    Medium
    Confidence reason
    A linked participant or independent source reports the claim.
  11. Supporting component
    Statement type
    Fact
    Provenance
    Reported
    Confidence
    Medium
    Confidence reason
    A linked participant or independent source reports the claim.
  12. Supporting component
    Statement type
    Fact
    Provenance
    Reported
    Confidence
    Medium
    Confidence reason
    A linked participant or independent source reports the claim.
  13. Supporting component
    Statement type
    Fact
    Provenance
    Reported
    Confidence
    Medium
    Confidence reason
    A linked participant or independent source reports the claim.
  14. Supporting component
    Statement type
    Fact
    Provenance
    Reported
    Confidence
    Medium
    Confidence reason
    A linked participant or independent source reports the claim.
  15. Key observation
    Statement type
    Metric
    Provenance
    Reported
    Confidence
    Medium
    Confidence reason
    A linked participant or independent source reports the claim.
    Reported by
    monday.com
    Scope
    Morphex PRs that merge automatically after CI and Guardrails pass
    Denominator
    Morphex pull requests; sample size and period not supplied
    Method
    Not reported
    Observation date
    Not reported
  16. Key observation
    Statement type
    Metric
    Provenance
    Reported
    Confidence
    Medium
    Confidence reason
    A linked participant or independent source reports the claim.
    Reported by
    monday.com
    Scope
    Monthly AI coding-tool adoption among monday Builders, including engineers, PMs, analysts, and designers
    Denominator
    Builders; not exclusively engineers
    Method
    Not reported
    Observation date
    Not reported
  17. Key observation
    Statement type
    Metric
    Provenance
    Reported
    Confidence
    Medium
    Confidence reason
    A linked participant or independent source reports the claim.
    Reported by
    monday.com
    Scope
    Per-engineer pull-request throughput
    Denominator
    Engineers; baseline period and cohort size not specified
    Method
    Not reported
    Observation date
    Not reported
  18. Key observation
    Statement type
    Metric
    Provenance
    Reported
    Confidence
    Medium
    Confidence reason
    A linked participant or independent source reports the claim.
    Reported by
    monday.com
    Scope
    Recent cut of top PR-generating agents; Guardrails rejection before review and reverts among merged PRs
    Denominator
    Agent PRs for Guardrails rejection; merged PRs for revert rate
    Method
    Not reported
    Observation date
    Not reported
  19. Lesson
    Statement type
    Inference
    Provenance
    Catalog judgment
    Confidence
    Medium
    Confidence reason
    The catalog derives this observation from the linked sources.
  20. Lesson
    Statement type
    Inference
    Provenance
    Catalog judgment
    Confidence
    Medium
    Confidence reason
    The catalog derives this observation from the linked sources.
  21. Lesson
    Statement type
    Inference
    Provenance
    Catalog judgment
    Confidence
    Medium
    Confidence reason
    The catalog derives this observation from the linked sources.
  22. Lesson
    Statement type
    Inference
    Provenance
    Catalog judgment
    Confidence
    Medium
    Confidence reason
    The catalog derives this observation from the linked sources.
  23. Lesson
    Statement type
    Inference
    Provenance
    Catalog judgment
    Confidence
    Medium
    Confidence reason
    The catalog derives this observation from the linked sources.
  24. Operating model assessment
    Statement type
    Inference
    Provenance
    Catalog judgment
    Confidence
    Medium
    Confidence reason
    The secondary source reports predominantly automatic merges and automated guardrails, while humans manage tasks and outcomes.
    Observation date
    2026

The catalog records no related implementation for this entry yet.

Back to the directory →