Evidence & Evolution

DG-OS is a record of work in motion. This panel traces how Dessi's ideas, systems, and questions change over time: what prompted a revision, which evidence supports it, and what remains open.

DG-OS is the public expression product within Human Systems Platform. Behind it, Dessi Space preserves selected experience and owner control, while Learning Foundry develops human understanding and separately governed agent capabilities.

Human Systems Platform carries only reviewed evidence across those boundaries. Approved entries can reach DG-OS and the System Map, where they may support a new opportunity, collaboration, research question, or learning cycle.

Only reviewed, public-safe entries appear here. Private sources and repository activity remain private.

How the loop works

Human Systems Platform / private observation → public projection

01
Observe
Dessi Space records bounded evidence from approved projects and learning sources.
02
Understand
Learning Foundry develops human understanding and agent capabilities without treating them as the same achievement.
03
Project
Dessi reviews what can become public. Approved entries enter DG-OS and the System Map.

Ideas in motion

Newest first

01
revision
2026-08-28
Production and public evidence became separate proof planes
Employer work now demonstrates production agent, data, and multi-tenant constraints at a confidentiality-safe level, while independent systems provide inspectable evidence of the corresponding authority, evaluation, and recovery patterns.
Inspect supporting claims
- production-agent-platformI architect and build the Programmatic plugin and agent harness that turns ambiguous user requests into tenant-bound execution across skills, a typed CLI, backend services, analytical data, and advertising-platform APIs.
- production-data-platformI build backend ingestion and serving workflows for heterogeneous advertising data across provider hierarchies and analytical grains, and evaluate storage architecture against query shape, aggregation, latency, reliability, and cost.
- gateplane-control-planeI developed Gateplane independently to explore how authenticated human or agent identity becomes bounded, tenant-aware authority for tools and external effects.
- agent-runtimeI built Agentic Commerce to help brands test and improve how they describe products for paid placements and organic agent-led discovery, without giving an AI system unchecked control over business actions.
2026-08-28
Reviewed revision
02
revision
2026-08-23
The founder product became the orienting system
Human Systems Platform now provides the product frame for Dessi Space, Learning Foundry, DG-OS, and the planned Organization Foundry. Each remains useful on its own while contributing to one owner-controlled evidence and learning loop.
Inspect supporting claims
- human-systems-platformI am developing Human Systems Platform as a founder-led product for people and organisations that need credible evidence of capability in AI-mediated work. It turns selected experience into private learning, owner-approved public evidence, and testable hypotheses about where that capability may create value.
- codex-capabilityI built Learning Foundry as a stand-alone learning product for people who want to learn with AI without treating an agent's successful output as proof of their own understanding. It helps them explain, test, apply, and revise what they learn while separately developing evaluated agent capabilities.
- provider-runtimeI built DG-OS as a stand-alone public profile and discovery product where visitors can inspect a person's systems, evidence, writing, and development or ask questions grounded in reviewed public sources.
2026-08-23
Reviewed revision
03
revision
2026-08-23
Research and implementation platforms became first-class systems
The AI News Hub now appears as the shared research product, while AI Skills Platform appears as its practical capability layer for turning selected ideas into reusable packages.
Inspect supporting claims
- ai-news-platformBuilt and maintains the open-source AI News Hub as a shared research platform for applied AI in marketing, connecting news, deep analysis, build sessions, and public prototypes.
- ai-news-communityCreated the platform to support an internal community of thinkers, builders, and innovators that has grown to about 400 company members.
- ai-skills-platformBuilt AI Skills Platform to turn applied AI research into reusable capabilities that practitioners can inspect, install, test, and adapt across agent runtimes.
2026-08-23
Reviewed revision
04
revision
2026-08-22
Current projects became one system map
Dessi Space, Learning Foundry, DG-OS, and the shared Human Systems Platform are now described as separate authority planes with explicit dependencies, maturity, and publication boundaries.
Inspect supporting claims
- codex-capabilityI built Learning Foundry as a stand-alone learning product for people who want to learn with AI without treating an agent's successful output as proof of their own understanding. It helps them explain, test, apply, and revise what they learn while separately developing evaluated agent capabilities.
- provider-runtimeI built DG-OS as a stand-alone public profile and discovery product where visitors can inspect a person's systems, evidence, writing, and development or ask questions grounded in reviewed public sources.
2026-08-22
Reviewed revision
05
observation
2026-08-22
Models propose; validated systems decide
Across Gateplane and Agentic Commerce, improving intelligence remains inside deterministic controls for identity, permissions, evidence, state transitions, effects, and rollback.
Inspect supporting claims
- gateplane-control-planeI developed Gateplane independently to explore how authenticated human or agent identity becomes bounded, tenant-aware authority for tools and external effects.
- agent-runtimeI built Agentic Commerce to help brands test and improve how they describe products for paid placements and organic agent-led discovery, without giving an AI system unchecked control over business actions.
- feedback-loopI designed a Bayesian-style learning loop that updates brand- and product-scoped beliefs as evidence arrives and carries supported patterns into later query and copy generation. It recommends whether to promote, revise, or reject each variant, while the supervised runtime keeps tools, evidence, memory, approvals, and recovery under explicit control.
2026-08-22
Observed
06
revision
2026-07-26
Claims became typed evidence
DG-OS replaced inherited profile content and broad self-description with claims that carry visibility, confidence, provenance, and an explicit boundary.
Inspect supporting claims
- agent-runtimeI built Agentic Commerce to help brands test and improve how they describe products for paid placements and organic agent-led discovery, without giving an AI system unchecked control over business actions.
- feedback-loopI designed a Bayesian-style learning loop that updates brand- and product-scoped beliefs as evidence arrives and carries supported patterns into later query and copy generation. It recommends whether to promote, revise, or reject each variant, while the supervised runtime keeps tools, evidence, memory, approvals, and recovery under explicit control.
- codex-capabilityI built Learning Foundry as a stand-alone learning product for people who want to learn with AI without treating an agent's successful output as proof of their own understanding. It helps them explain, test, apply, and revise what they learn while separately developing evaluated agent capabilities.
- provider-runtimeI built DG-OS as a stand-alone public profile and discovery product where visitors can inspect a person's systems, evidence, writing, and development or ask questions grounded in reviewed public sources.
2026-07-26
Reviewed revision
07
observation
2026-07-26
Reliability is a product surface
Across Agentic Commerce, Learning Foundry, and DG-OS, the recurring work is making agent plans, evidence, failures, and human decisions inspectable.
Inspect supporting claims
- agent-runtimeI built Agentic Commerce to help brands test and improve how they describe products for paid placements and organic agent-led discovery, without giving an AI system unchecked control over business actions.
- codex-capabilityI built Learning Foundry as a stand-alone learning product for people who want to learn with AI without treating an agent's successful output as proof of their own understanding. It helps them explain, test, apply, and revise what they learn while separately developing evaluated agent capabilities.
- provider-runtimeI built DG-OS as a stand-alone public profile and discovery product where visitors can inspect a person's systems, evidence, writing, and development or ask questions grounded in reviewed public sources.
2026-07-26
Observed
08
question
2026-07-26
Can reliability become measurable across real coding tasks?
The next research step is a reproducible task suite that records solve rate, regression, latency, token use, failure class, and intervention effect.
Inspect supporting claims
- agent-runtimeI built Agentic Commerce to help brands test and improve how they describe products for paid placements and organic agent-led discovery, without giving an AI system unchecked control over business actions.
- provider-runtimeI built DG-OS as a stand-alone public profile and discovery product where visitors can inspect a person's systems, evidence, writing, and development or ask questions grounded in reviewed public sources.
2026-07-26
Active question
09
experiment
2026-07-26
Private evidence, deliberate publication
Dessi Space now observes approved repositories read-only and records private review events. Public DG-OS receives only separately approved projections.
Inspect supporting claims
- provider-runtimeI built DG-OS as a stand-alone public profile and discovery product where visitors can inspect a person's systems, evidence, writing, and development or ask questions grounded in reviewed public sources.
2026-07-26
Active question

Current boundaries

01No public coding-task solve-rate benchmark yet.
02No claim of model fine-tuning experience.
03No public production measurements for token cost, latency, or capacity.
04Employer systems are described at outcome level; private code, logs, clients, and infrastructure remain private.
05Human Systems Platform is a founder product in private active development. Its components are functional at different levels, but the complete joined workflow and commercial demand are not yet proven.
06Current learning updates evidence, beliefs, memory, policy, and versioned harness configuration; it does not retrain a foundation model or permit silent self-modification.

Open Systems & Evidence →