All essays
Essay 02 / The operating architectureAuthor’s essays

How the Inverted Firm Is Built

Work, authority, evidence and human finality

Michael StröckSeptember 202610 min read

A shared production graph, explicit authority and a version-bound evidence ledger. How the operating thesis becomes a firm, and what still has to be built.

7. The firm is a shared production graph

Infra One is building the human-and-agent production layer for regulated financial operations. Its initial wedge is fund administration.

Fund administration today is often organised around people handing work to people: an administrator prepares, a manager reviews, a partner signs, and evidence is scattered across spreadsheets, inboxes, shared drives and individual memory. Software may help each actor, but it rarely becomes the durable location of work, authority and evidence.

Infra One reorganises the work around a shared production graph.

A production unit can be a NAV, reconciliation, filing, KYC refresh, capital-call notice, distribution, investor communication, audit request, handover or software change. It has:

  • A purpose, scope and acceptance criteria.
  • A state and explicit progression path.
  • Dependencies on data, documents, rules, approvals and upstream work.
  • A claimant and attributed production history.
  • Defined permissions for people, agents and services.
  • Automated validations, exceptions, reviewer findings and decisions.
  • A finality gate.

The defining proposition is simple:

Humans and agents are first-class participants in the same firm.

Both can receive work, claim it, produce an output, hand it off, raise an exception and be named in the record. Their permissions differ. A qualified person may decide a material exception and approve a regulated outcome; an agent may not. But the work does not happen in a human system with agents on the side. It happens in one production graph.

8. What exists today

Infra One already operates the core orchestration primitives in its own engineering environment through Harness. Harness began as an issue tracker and developed into an operating layer for work that must be coordinated, evidenced and reviewed.

In the current engineering instance:

  • Every material unit of work begins as an issue with scope, acceptance criteria and dependencies.
  • A model may classify or explain a new issue, but people retain authority over approval-state transitions.
  • A human or agent can claim approved work through controlled assignment.
  • An approved task can be implemented by an agent on a fresh branch.
  • The platform, not the agent, performs privileged workflow actions such as opening a pull request.
  • Review findings, verdicts and final decisions are stored server-side against the exact commit under review.
  • A changed commit creates a new identity, requiring review validity to be reconsidered according to workflow rules.
  • Closure depends on configured evidence and gates, not on an actor’s assertion that the work is complete.

This is live evidence for the work graph, controlled claiming, attributed execution, review ledger and workflow analytics. It is not a claim that fund production is already automated or that an engineering workflow automatically satisfies the full requirements of a regulated financial-services control framework.

An internal August engineering observation illustrates the model: a screenshot and a small number of prompts led to eleven reviewed, merged and closed pull requests over roughly 78 hours, the removal of ten legacy modules and a guard intended to prevent their reintroduction. The meaningful point is not the count. It is that scope, dependencies, tests, review verdicts, merge state and closure were durable system state rather than an unstructured transcript or an individual’s memory.

9. The architecture

A regulated production implementation requires more than a model and a task queue. It needs distinct layers that make work, authority, evidence and finality explicit.

LayerWhat it doesPlain-English description
Work graphRepresents work units, dependencies, owners, deadlines, states and escalationsThe live map of everything that must happen to complete a fund operation
Policy and authorizationDefines what each human, agent or service may read, produce, change, approve or releaseThe rulebook for who and what may do which part of the work
Production and validationCombines deterministic services, structured data processing and bounded agentsThe machinery that performs recurring work and checks it as it goes
Evidence ledgerBinds inputs, versions, checks, findings, overrides and approvals to the artifactThe durable record that shows what happened and why a result was accepted
Human finality gateRequires an authorized professional decision where requiredThe point at which qualified human judgment makes the result real

Work graph

For a NAV, the graph may include source-document intake, data extraction, cash and position reconciliation, valuation inputs, ledger posting, allocation logic, variance analysis, exception resolution, reviewer queries, approval and distribution. A filing may depend on calculations, document versions, disclosure checks, approvals and controlled submission.

The graph prevents a dangerous shortcut: treating a plausible final document as evidence that the preceding work happened correctly. Finality is the result of a completed chain of evidence, not fluent output.

Authority boundaries

The relevant question is not whether an agent is “autonomous.” It is what authority it holds, on which task, over which data, in which workflow state and with what consequences.

An agent may be allowed to claim a policy-approved task, read task-scoped inputs, produce a draft or proposed calculation, run an approved validation, request information, raise an exception or propose a handoff. It should not be able to grant itself authority, redefine acceptance criteria, self-approve, self-sign, override a failed control without authorized human action, obtain standing privileged credentials or edit its own audit record.

The practical implementation can include least-privilege access, short-lived scoped authorization, platform-mediated privileged actions, separation between production and release authority, outbound controls and immutable server-side audit events.

Production and validation

Infra One combines deterministic logic, structured data transformations and model-assisted agents. They are not one opaque “AI layer.”

Deterministic logic handles calculations, validations, routing rules and reconciliations where inputs and rules are defined. Models assist with unstructured extraction, classification, retrieval, drafting, explanation and routing. Qualified humans address novel facts, ambiguous terms, materiality, valuation judgment, policy interpretation and decisions reserved to accountable professionals.

Every material artifact should retain enough provenance to reconstruct production: source versions, data lineage, ruleset and policy versions, validation results, relevant model or service identity, execution time and actor identity.

Evidence ledger and finality

Every output receives a version identity, such as a content hash combined with lineage metadata. Review findings, validation outcomes, exceptions and approvals bind to that exact version.

The central rule is:

A material change produces a new version. A prior approval applies only to the version approved, unless an explicit policy records why the change is immaterial.

The ledger records artifact version history; inputs and provenance; validation evidence; reviewer findings; resolution and dismissal reasoning; authority evaluations; approvals; state changes; and retention and access events relevant to the record.

The human finality gate is not a ceremonial signature. It is an authorized decision on a specific evidence-complete version. The platform should compute whether the evidence conditions for finality are satisfied; the accountable human makes the professional judgment that only they are entitled to make.

10. Measuring the firm

The inversion is an operating-economic hypothesis. It should be measured in ways that reveal genuine leverage rather than hidden manual work, under-resourced review or transferred client risk.

MetricWorking definitionGuardrail
Cost per completed production unitLoaded human time, attributable model/compute spend and platform/operations cost per unitSegment by complexity, jurisdiction, asset class, fund structure and reporting cycle
System-performed shareShare of workflow steps completed by deterministic or agentic services without discretionary human executionSeparate system completion from mere model suggestion; mandatory sign-off is not a failure
Human intervention rateHuman interventions beyond mandatory controls per completed unitClassify as required control, material judgment, source-data remediation, exception or capability gap
Review qualityFindings, dismissals, overrides, approval time and post-approval defects by reviewer and risk classHigh reviewer throughput is a risk signal unless quality indicators support it
Reuse rateShare of rules, validations and workflows reused across comparable workDo not mislabel bespoke client work as standardisation

The metrics become the engineering roadmap. Every manual correction, escalation and reviewer intervention is a signal. Sorted by frequency, risk and cost, those signals identify which rule, test, validation or workflow should be built next.

11. Failure is designed for

The main risk is not an agent making an obvious error. Obvious errors are often caught. The more dangerous failure is a plausible error that propagates, escapes a weak review or cannot be reconstructed later.

Failure modeExampleDesign response
Incorrect source dataA statement is incomplete, stale or incorrectly parsedData lineage, completeness checks, source-to-output reconciliation and exception routing
Ruleset or policy driftA fund document, tax rule or regulatory requirement changes while old logic remains activeVersioned policies, change control, effective dates, regression suites and named policy ownership
Model errorA model invents a rationale or misclassifies a documentBounded use cases, structured outputs, retrieval controls, independent validation and escalation thresholds
Correlated system failureA faulty rule affects many fundsTenant-aware isolation, impact analysis, canary release, rollback and targeted reprocessing
Separation-of-duties failureOne actor changes a rule, produces output and approves itSegregated roles, independent approval paths and auditable authority checks
Privilege failureAn agent accesses more data or performs a broader external action than permittedLeast privilege, scoped authorization, platform-mediated actions and immutable audit events
Rubber-stampingA reviewer approves high-volume output without meaningful scrutinyWorkload analytics, risk-based QA, reviewer-quality indicators, escalation and accountability
Non-reproducible historyThe basis for a prior conclusion cannot be reconstructedRetained inputs, versioned rules, execution provenance and controlled reference corpora
Confidentiality or residency breachSensitive investor data is processed or retained contrary to applicable requirementsData classification, vendor and model governance, access controls, encryption and retention policy

The objective is not to claim that the system cannot fail. It is to make failure observable, attributable, recoverable and systematically less likely over time.

12. Build sequence

Fund production is not yet running through Harness. The path from live engineering primitives to regulated production is a build sequence and must be proved in production.

  1. Define the production units. Represent NAVs, reconciliations, filings, KYC refreshes, capital calls, distributions, audit requests and handovers as explicit workflows.
  2. Map authority and obligations. Identify, for each entity, jurisdiction and service, what may be automated, what must be reviewed, who may decide, and what recordkeeping and outsourcing constraints apply.
  3. Generalise the evidence ledger. Bind all material financial artifacts, validations, exceptions and approvals to a versioned identity.
  4. Automate bounded tasks first. Begin with deterministic, high-volume and evidence-rich work: data checks, extraction with review, reconciliations, completeness controls, exception routing and controlled calculations.
  5. Instrument intervention. Record every human correction, escalation and override; classify the cause and feed the product roadmap from observed work.
  6. Validate the gate. Measure review capacity, reviewer findings, re-open rates, overrides and post-approval defects before increasing agent throughput.
  7. Publish evidence, not slogans. Report production metrics only once there is a defined baseline and enough segmentation to make comparison meaningful.

The first meaningful proof point is not an agent producing a plausible output. It is a live regulated workflow with traceable inputs, versioned rules, visible validation, attributable human-and-agent contributions, accountable approval and a reproducible audit trail.

About this text

From the September 2026 combined draft. Engineering observations and implementation status are founder-reported as of that draft; they are not independently verified fund-production results.

From thesis to assumptions

Put the ideas to the test.

Explore the investment case, or change the assumptions in the illustrative economics model.