built by calvin
← Selected work
AI workflow engineering

AI makes execution fast. I built the operating layer that makes it trustworthy.

CalvinOS turns product evidence into reviewable work without collapsing source truth, human judgment, external authority, and verification into one opaque “agent completed” state.

Inspect the real workflow
One bounded requestProduct Content Ops
  1. 01Route sources
  2. 02Build artifact
  3. 03Gate authority
  4. 04Verify truth

Only accepted facts become durable context.

Role
Designer and builder
Scope
Orchestration, source routing, review, verification
Status
Actively used internal system
Proof
Real workflow + 11-test runnable reference

Technical surface

  • Agent routing
  • MCP integrations
  • Approval gates
  • Validators and audit trail
The problem

When output gets cheap, coordination debt gets expensive.

Agentic coding made it possible to research, draft, implement, and verify work much faster. It also made a dangerous failure mode easier: an agent could produce a plausible result while using stale context, crossing an authority boundary, or promoting an unverified claim.

The hard problem was no longer making an agent perform a task. It was keeping accelerated actions aligned with the right source, exact scope, review state, and owner.

I built CalvinOS as a human-readable operating layer. Product repositories still own implementation truth. Live systems still own dynamic state. CalvinOS routes evidence, creates review artifacts, records decisions, and promotes only accepted facts into durable context.

Route truthUse the system that actually owns each fact.
Show the workMake exact output inspectable before it advances.
Gate authoritySeparate approval, execution, and cleanup.
Keep uncertaintyPreserve partial and blocked states as useful truth.
The real workflow

One Product Content Ops workflow, opened state by state.

The trace follows one real kardfolio campaign across its production, review, approval, and reconciliation records. Private details are removed; the sequence, outcomes, authority boundary, and evidence gaps are preserved.

Workflow trace / 01Bounded

Create one kardfolio product campaign from current, claim-safe evidence.

The workflow started with one product and one campaign concept. It did not fan out across every product or personal account.

Source / owner
Calvin / Product Content Ops
Observed
Jul 27, 2026
Allowed next
Read only the permitted product sources
Completion evidence
One product and one campaign concept recorded
Workflow trace / 02Read only

Route product truth, public release evidence, and approved synthetic UI into separate evidence lanes.

Bounded scouts could inspect evidence in parallel. Product facts still belonged to the product repository and public surfaces—not to an agent’s memory.

Source / owner
Product repository + approved product context
Observed
Jul 27, 2026
Allowed next
Freeze the source and claim manifest
Completion evidence
Source inventory preserved with explicit gaps
Workflow trace / 03Reviewable

Assemble exact X, Threads, and Instagram variants with an asset and claim manifest.

The output was a human-readable review package, not an invisible agent handoff. Every external variant could be inspected as an exact revision.

Source / owner
Product Content Ops
Observed
Jul 27, 2026
Allowed next
Submit the exact revision for independent review
Completion evidence
Three platform variants and review assets assembled
Workflow trace / 04Revised

Run independent voice, claim, scheduling, and visual checks before approval.

The first visual review requested a crop change. The package advanced only after the corrected revision passed the same review surface.

Source / owner
Voice, scheduling, claim, and visual reviewers
Observed
Jul 27, 2026
Allowed next
Return only the changed output to review
Completion evidence
First review requested revision; verification passed
Workflow trace / 05Human gate

Approve the exact content without silently granting scheduling or publishing authority.

Content approval, native scheduling, and publication evidence remained distinct states. Calvin later confirmed scheduling; CalvinOS reconciled that fact rather than performing the external action.

Source / owner
Calvin
Observed
Jul 27, 2026
Allowed next
Grant separate, scoped scheduling authority
Completion evidence
Content approval recorded; external execution remained unavailable
Blocked transitionTransition approved content to scheduled

Blocked: content approval did not include scheduling or publication authority.

Workflow trace / 06Partial

Preflight attributed links and preserve missing external object IDs as an explicit evidence gap.

The final links returned HTTP 200. Platform object IDs were not captured, so the record remained partial instead of being promoted to a stronger state by inference.

Source / owner
Product Content Ops run record
Observed
Jul 27, 2026
Allowed next
Capture native platform object IDs before stronger verification
Completion evidence
Campaign links passed preflight; native object IDs remain missing

Select a stage to inspect its evidence and authority state.

Content approval, native scheduling, and publication evidence remained separate states. CalvinOS reconciled the confirmed external action; it did not perform it.

Runnable reference

I tested the authority boundary as code, not a promise.

A small, dependency-free TypeScript reference isolates how deterministic policy, exact approval, tool failure, and replay should behave around untrusted input.

Test coverage
11 / 11 boundary tests passed
Exact approval
Action, payload digest, destination, and revision must match
Untrusted input
Cannot add tools, permissions, or downstream actions
Runtime evidence
Terminal state, validation, side effects, and replay are recorded
Sanitized demo trace

One synthetic workflow, opened at the control points that matter. No message was sent, content published, or external system changed.

  1. 01Blocked

    Approval missing

    Policy passed. Execution stayed unavailable with zero side effects.

  2. 02Failed

    Synthetic tool failure

    The approved call failed, recorded zero side effects, and became replayable.

  3. 03Replay succeeded

    Linked recovery

    The replay preserved its source run and recorded one simulated in-memory effect.

Scope, not a production claim. The reference uses an in-memory ledger and synthetic executor. It does not claim authentication, tenant isolation, signed approvals, durable storage, or distributed idempotency.

Failure and learning

The useful test was what happened when a boundary failed.

Detected

A local capture inherited an external analytics configuration.

Synthetic test events left the intended local boundary.

Recorded

The workflow preserved the affected scope and incident state.

It did not hide the failure behind a successful content artifact.

Blocked

Cleanup required separate authority.

The system refused to self-delete external data without approval.

The incident exposed a missing precondition: local synthetic capture must first prove external analytics are disabled. Cleanup remains a distinct, auditable action.

Transfer to a product team

The labels change. The control model transfers.

Repositories and live systems still own truth. Tickets and review artifacts make exact work inspectable. Approvals grant narrow authority. Release evidence records what actually happened.

  • Source ownerRepositories and live systems own the facts.
  • Review surfaceTickets, pull requests, and design reviews expose exact work.
  • Authority gateApproval covers a named action, not every downstream effect.
  • VerificationRelease records preserve both confirmed effects and open gaps.
Next caseInspect kardfolio