Skip to main content

Reliability

Trust the controls. Inspect the evidence.

Inspect access, revisions, recovery, and retention. Source-tested controls and live production assurance are different; Kam is not yet running for customers.

Source
Implemented and tested
Delivery
Built · off by default
Live assurance
Not qualified

Recorded review: 2026-10-07. Live deployment, permissions, performance, and production authorization remain separate gates.

Your questions, explicit controls

What protects the State your agents use?

Can an old worker overwrite a result?

Conditional acceptance checks the required revisions and authority.

See the evidence boundary

Source-qualified; live recovery remains unqualified.

Read the implementation contract →

Can another workspace read my data?

The server resolves access. Knowing a record ID is not permission.

See the evidence boundary

Source controls exist; deployed permission review remains separate.

Read the implementation contract →

Does a correction erase the first report?

A correction adds a revision. Earlier revisions remain readable while retained.

See the evidence boundary

Implemented in source; exact reads remain subject to access and retention.

Read the implementation contract →

What happens when evidence expires?

An expired required input must remain explicit, not silently become current.

See the evidence boundary

Retention contracts exist; managed context compilation is planned.

Read the implementation contract →

Inspect the release evidence and exact source checkpoint

How far each part has been proven

Six levels, from planned to production.

As of the recorded review on 2026-10-07, nothing is live-tested. This is a fixed review, not a live monitor.

  1. Planned · not available

    Design direction. No implementation is claimed.

  2. Source-implemented

    Implemented in reviewed source with source-level tests. Not executed as a packaged artifact.

  3. Locally qualified

    Exercised as a packaged or local artifact (CI, local lab, or simulated AWS transports). No live AWS deployment.

  4. Live-qualified

    A passed live qualification receipt binds this exact package to an isolated AWS deployment.

  5. Pilot only

    Live-qualified and authorized for a named, bounded pilot. Not general availability.

  6. Production-authorized

    Live-qualified and explicitly authorized for production use.

Which code and packages were reviewed
Backend, package, toolkit, and SDK identities in this release combination
ComponentCommitReferenceNotes
Source the website claims were reviewed against1db8cf00main through PR #219Every public capability statement is checked against this checkpoint.
Reviewed source, packaged and qualified in CI1db8cf00main · qualification run 37686977815Same commit as the reviewed source. Package, SDK and native artifact round trips passed with simulated AWS transports; not a live deployment.
Packaged candidate selected for live qualification284f26e5PR #206 candidate · merged as a215d31f · run 37605352449Named by the backend live-AWS approval document at the reviewed checkpoint. No live receipt exists.
Native developer toolkit1db8cf00merged in PR #176 (d5056454) · native artifact round trip in run 37686977815Linux x64 only. No public distribution.
History and State SDK candidate1db8cf00SDK 0.36.0 · artifact round trip in run 37686977815Not published to npm. The website console vendors this exact tarball.

Deployment check (2026-10-07). No deployment of the History/State candidate was found in the inspected AWS Regions. Existing Kam resources belong to earlier products and are not evidence for this one. Live qualification receipts recorded: 0.

Capability evidence

Highest evidence level each capability’s recorded evidence supports
CapabilityShown levelLimit
HistoryLocally qualifiedPackage qualification is not a live deployment.
Identity & membershipLocally qualifiedCovered by the same package qualification as History.
Views & current StateSource-implementedNot deployed. Package coverage of View reconciliation is not confirmed for the website.
State queries & ComponentsSource-implementedSDK 0.36.0 candidate; whether the SDK artifact round trip exercises queries is not confirmed for the website.
Metrics, materialize & watchPlanned · not availableDesign preview only.
Turn LifecycleLocally qualifiedMerged native toolkit; reference-only local frames.
Context compilerPlanned · not availableDesign direction only.
Operational durabilitySource-implementedHistory and reconciliation progress are durable in source; no named checkpoint API.
Profiler & developer toolkitLocally qualifiedMerged; Linux x64 only; no public distribution.
Optional AgentCore deliveryLocally qualifiedDefault off; simulated AWS transports only.
Export, deletion & restore fenceSource-implementedLive erasure and restore drills are qualification gates.

Reviewed code: 1db8cf00. Package picked for live testing: 284f26e5. Live deployment: none yet.

Open the fixture State inspector →

Status of each part, in detail

Ordered, versioned ledger

Source and package tested

Exact revisions, pinned daily pages, corrections, rolling windows, and independent 400/730-day synthetic-history checks. Synthetic time is not observed uptime.

Rust State and Observations

Source implemented

State pointers, immutable structured Observations, and change evidence are conditionally persisted. The SDK 0.36.0 candidate reads current Active State and exact retained Observations. No State or Context endpoint is deployed.

State reconciliation

Source implemented

Bounded View registration, acyclic reverse-dependency membership, replay-safe cursor/task progress, and bounded same-scope multi-source dependency processing are implemented. Cross-scope joins and a deployed State endpoint remain staged.

State queries

Source implemented

The reviewed SDK 0.36.0 baseline, unpublished and undeployed, implements state(), component(), and bounded select stages (where, pick, orderBy, take) with explain() and value() over the admitted evidence of one View's Active State. SDK 0.37.0 merged in PR #220 (not publicly published and not included in the pinned 0.36.0 website qualification) adds bounded operators over that same selected collection. General source-payload queries, managed metrics, calculation caching, graph traversal, materialize(), watch(), and lifecycle integration remain separate planned capabilities.

Turn Frames and profiler

Merged · locally qualified

Validated local Turn Frames, reference preparation, and State profiling exist in the merged native toolkit and run locally only. They do not intercept live AgentCore turns, submit model requests, persist managed Turn Receipts, or authorize external effects.

Live Turn Lifecycle and Context

Planned · not available

The product direction is to resolve current operational checkpoints, detect typed changes, compile bounded Observations, bind turns to exact ReadSets, and revalidate consequential effects. No live runtime hook or managed action barrier is claimed.

Native developer toolkit

Merged · locally qualified

Native toolkit 0.1.0 is merged into the backend (PR #176) and qualified in CI as a network-disabled Linux x64 artifact. No public binary release, macOS/Windows distribution, or live AWS connection is offered here.

Customer lifecycle

Source implemented · live unqualified

Bounded owner export, primary-state deletion, restore fences, and Marketplace entitlement reconciliation are implemented in source. Live buyer, erasure, restore, and revocation journeys remain qualification gates; no deployed completeness is claimed.

AgentCore delivery

Implemented · default off

Destination binding, per-generation obligations, scheduling, publication receipts, exact retrieval verification, and metadata-only status are implemented. Optional Memory write-back remains separately qualified with simulated AWS transports.

Carry-forward consolidation

Proposed · not implemented

A versioned long-term summary baseline and automatic S3 archival are not implemented. Checkpoint recovery does not preserve expired contributions as institutional knowledge.

Real-history verification (Kam Sports)

Planned · not executed

The verification plan replays real Kam Sports history through the unchanged History contract across the 365-UTC-date working window and checks exact reads, corrections, and recovery. Kam Sports grading stays authoritative; Kam records grades, it never computes them. No run has completed yet.

History console

Implemented in website source

A read-only, Amplify-authenticated console browses workspaces, scopes, UTC days, and exact revisions through existing History API reads. It is not connected to a live History deployment, because none exists yet; without configuration it reads nothing.

Production assurance

Not yet qualified

Source checks and independent artifact execution do not establish deployed IAM, a Marketplace listing, production SLOs, compliance approval, or measured costs and latency.

Recovery

Lost work is found again. Old work is not trusted.

If a worker restarts, saved work is picked up again. Work based on an older version is rejected, and anything uncertain stays visible instead of being retried blindly.

Retention

A rolling window, not a yearly reset.

Inspect the rolling-window diagram

Working history advances one UTC date at a time

Before the working window

Expired contributions are removed from the reducer’s rolling state.

Today − 364 → today

365 UTC dates. Quiet histories also need maintenance as the window moves.

A checkpoint resumes work; it is not a lifetime summary. It preserves the applied sequence and retained rolling state, not all historical meaning.

Schematic, not to scale. Supporting evidence has a separate creation/acceptance clock: up to 730 days, with direct-prior-revision extensions for corrections. Inspection is limited by evidence availability. Automatic S3 archival and carry-forward consolidation are not implemented in the reviewed backend.
Kam and AgentCore retention responsibilities
Data layerPolicyMeaning
Kam working history365 UTC datesToday and the preceding 364 UTC dates. The window advances daily; out-of-window contributions are removed from rolling state, not consolidated into a permanent baseline.
Kam supporting evidenceSeparate inspection limitsSupporting revisions and references may remain for up to 730 days, with direct-prior-revision extensions for corrections. Inspection ends when its evidence expires; this is not automatic cold-tier archival.
AgentCore raw eventsConfigurable, up to 365 daysAWS applies this retention to raw short-term events. It is separate from Kam’s window and AgentCore long-term records.
AgentCore long-term recordsSeparate lifecycle policyAWS documents explicit deletion workflows. Raw-event expiry is not a universal long-term-record deletion policy.
How History stays continuous

History, State, and retention

A rolling window. A maintained state.

Kam advances working state as outcomes arrive and time moves forward. A recovery checkpoint keeps processing continuous; it is not a permanent summary of everything the system has seen.

Rolling operational history

The working window contains today and the previous 364 UTC dates. It advances each day, not through annual resets.

Checkpointed rolling state

Processing resumes from the persisted checkpoint and applies accepted transitions. Exact reads use published views rather than rebuilding the full history.

Versioned supporting evidence

Revisions and references support inspection until their deadlines. Supporting evidence may be retained for up to 730 days, with correction-related extensions.

Current boundary: Outcomes older than the working window stop contributing to rolling state. The current reducer does not preserve their meaning in a lifetime summary or move them automatically to S3.

Carry-forward consolidation — Proposed · not implemented. Preserve selected historical meaning in a versioned summary baseline while older evidence follows a separate archive policy. This is a proposed extension, not the behavior of the current rolling reducer.

Read the retention and continuity contract

Speed

No speed numbers until they are measured live.

No production p99 is published yet. Speed will be measured on a live deployment, step by step, alongside the oldest unfinished work and errors.

Security review

Ask for the evidence.

Build, dependency, and test evidence is ready to review. Live permissions, isolation, and data deletion still need live testing.

One project. A clear test.

Try Kam on one real project.

Tell us what your agents do and what keeps going wrong. We set what success looks like first.

Discuss an evaluationSee evaluation scopeNot launched yet. No production promise.