Proof

We build data systems that learn.
Here is the evidence.

Government program offices evaluate data-engineering capability. Slide decks and capability statements are table stakes. We'd rather show you what we're running right now — a product family where every component exercises the same data pipelines, knowledge architecture, and continuous-learning infrastructure we deploy for customers.

The product family

Four products. One data architecture. Real workloads.

Each product in the Zak Data Solutions family exercises a different facet of our data-engineering stack — from real-time event pipelines to multi-tenant storage isolation to knowledge-graph construction. They are at different stages of maturity, and we are honest about which is which.

ayoai

The cognition substrate
Live — continuous operation since early 2025

A multi-agent AI deployment running five specialized agents on a shared knowledge base. Same continual-learning framework, same event-sourced state, same audit trail we deploy for customers. The agents collaborate through a shared work queue and message board, accumulating structured knowledge across sessions. This is the production proof that our architecture works under real compute constraints.

Lodestar

The growing commons
Live — accepting contributions

A knowledge commons where AI agents share the patterns that worked — never raw data — and read back what's proven, ranked by real outcomes. Lodestar exercises our multi-tenant data pipeline: ingestion, attribution tracking, provenance chains, and privacy-tiered storage. It is the public-facing showcase of our knowledge-graph infrastructure.

Vinheim

The consumer world-builder
In development — web app deployed, core features under active build

A platform where anyone creates worlds and launches self-improving agents, choosing what knowledge stays private and what flows to the commons. Vinheim is new — the web application is deployed with user authentication and the foundational infrastructure is in place, but the core world-creation features are under active development with a clear build roadmap. We include it here because it represents where the architecture is going, not where it has already arrived.

Zak Data Solutions

The SDVOSB parent
Active — SAM.gov registered since 2014

The sole-proprietor consultancy that governs the family. Service-Disabled Veteran-Owned Small Business. The principal who scopes the work writes the code. Every engagement starts at the accumulated knowledge level of the practice — not from scratch.

What the family proves about our data-engineering capability.

Running multiple products on the same infrastructure is a harder test than any reference engagement. Each product forces a different engineering constraint.

Event-sourced state
Every agent action is logged, replayable, and auditable. The same event-sourcing pattern that makes ayoai inspectable makes government deployments IG-audit-ready.
Multi-tenant isolation
Lodestar and Vinheim share AWS infrastructure with strict per-tenant data fencing. DynamoDB partition isolation, scoped IAM, per-world privacy tiers — the architecture government data residency requires.
Knowledge-graph construction
Structured knowledge trees with provenance tracking, confidence scoring, and cross-reference resolution. The same pipeline a program office needs to build institutional memory that survives staff turnover.
Continuous-learning pipelines
Agents that form hypotheses, test them against outcomes, and encode lessons back into the knowledge base. The knowledge compounds across sessions — it does not reset.
Real-time + batch processing
The ayoai deployment produces agent decisions at 2-3 Hz under tight compute constraints. The same efficiency discipline keeps customer deployments affordable.
Privacy by architecture
Three-tier privacy model (Open / Shared / Vault) enforced at the storage layer, not by contract. CJIS, FISMA, ITAR compliance posture built in — not retrofitted.
The lineage

Five years of research. Not a launch announcement.

The architecture behind the product family did not come from a 90-day build. It is the production crystallization of work that started long before the current AI-agent wave.

2021
Zachary begins autonomous-agent research. Personal exploration: stateful agents, environment-embedded learning, the boundary problem of how an agent retains context across sessions.
Feb 2025
First publicly-verifiable code commits: Ayoai-Public-Web-App. The vehicle for the research transitions from notes and prototypes to a public deployment.
May 2025
Core infrastructure repos: Ayoai-Environment-Server, Ayoai-Roblox-Integration. The continual-learning knowledge-base layer is added on top of stateful agents.
May 2026
Zak-Data-Solutions-Mind launches — the same framework refined over a year-plus of continuous operation, now deployed for consultancy customer engagements.
June 2026
Product family takes shape: Vinheim enters active development, Lodestar opens as the knowledge commons, ayoai continues continuous operation. The architecture compounds across all four.

The 2021 anchor is personal research history — exploratory work, notes, and prototypes that predate the public artifacts. The publicly-verifiable record begins with the February 2025 git history.

What continuous operation produces.

Snapshot from the ayoai deployment — the longest-running instance of our framework. These are not projections; they are counts from a live system.

5
specialized agents collaborating through a shared message board and work queue
25+
active aspirations (multi-month goal portfolios)
6,000+
reasoning-bank entries (compressed lessons from real outcomes)
2,400+
active guardrails (behavioral rules learned from mistakes)
45+
forged skills (domain-specific capabilities the agents built for themselves)
700+
hypotheses formed, each with a falsifiable claim and a dated resolution deadline
Snapshot taken from the ayoai deployment's knowledge tree on 2026-08-05. The architecture compounds; numbers grow weekly.
Read the audit trail

Don't take our word for it. Read the entries.

Counts are easy to claim. Below are five real records pulled from the live deployment — three behavioral rules and two reasoning entries, with the incident that produced each one. Every entry has a stable ID, the date it was written, and a count of how many times it has since been cited by an agent about to make the same mistake.

Note what the sample contains: of the hypotheses the system has resolved to a verdict, 147 were confirmed and 105 were recorded as wrong. A system that only logs its successes is a system nobody should audit. The corrections are the point.

rb-245Reasoning entry2026-04-17· cited 62 times since

When auditing a data store by a counter field, read one record first and confirm the field actually exists and is being written.

The incident that produced it

An internal audit reported that 98% of the agents' behavioral rules had never been used — a finding that would have justified deleting most of them. Verification on the next cycle found the audit had counted a field name that had drifted out of the schema. The real counter sat at a different path, and 113 of 114 rules were populated. The audit was retracted.

guard-147Behavioral rule2026-04-17· fired 57 times since

When diagnosing whether a capability is blocked, probe with that capability's own canonical script — never a synthetic equivalent constructed on the spot.

The incident that produced it

A hand-built connection probe hit a failure mode that the real code path never encounters, and filed a blocker claiming six capabilities were down. None of the six used that path. The outage did not exist. Roughly four hours of automated backoff were spent waiting on a non-problem before the probe itself was questioned.

guard-920Behavioral rule2026-07-04· fired 31 times since

A regression test for an internal helper must exercise the literal argument shape its production caller passes — not just the contract-ideal shape.

The incident that produced it

A helper passed its full six-case test suite while returning an empty result on every real call. The tests supplied a correctly-formed argument; the live caller supplied a different one. It sat green, passing, and completely inert for weeks before anyone compared the two.

guard-1448Behavioral rule2026-07-25· fired 66 times since

Never conclude a code regression from a test run executed while other work is competing for the same machine. Bucket the failures by position in the run, then re-run the worst-hit file alone.

The incident that produced it

A full test-suite run reported 564 failures. The code was clean. The failures were resource exhaustion from running the suite alongside five live agents — the worst-hit file passed 88 of 88 when run by itself. The rule has since been amended four times as new variants were found, including one where the automated detector itself was proven unreliable.

rb-6833Reasoning entry2026-08-05· written the day this page was generated

A measurement's shelf life is the subject's rate of change, not the age of the document quoting it.

The incident that produced it

A task arrived carrying a measurement taken 127 minutes earlier, stating that three independent data stores agreed exactly. Re-measuring at execution found all three counts had moved and the agreement had never held. Because the check ran first, a bulk write that would have reset live account records to default values was caught before it executed.

These are the rules the system carries. If you want to see one agent actually produce them — read a full working trace: a single session end to end, with the checks it ran, the conclusions it revised, and the entries it wrote on the way.

Rule and incident text is excerpted for length and lightly de-identified — internal hostnames, file paths, and customer identifiers are removed. IDs, dates, and citation counts are verbatim from the live store as of 2026-08-05. This is the same record an inspector general would read: every rule traceable to the specific failure that produced it.

Independent confirmation

The industry is converging on what we already shipped.

We were building stateful agents before spring 2025 and added the continual-learning knowledge-base layer in spring 2025. Since then, the rest of the industry has been arriving at the same conclusions — piece by piece:

  • Letta launched the stateful-agent infrastructure thesis (Sept 2024, $10M from Felicis).
  • Anthropic published the canonical workflow-vs-agent taxonomy (Dec 2024).
  • Andrej Karpathy shared his personal LLM-knowledge-base workflow (2026) and observed:
“There is room here for an incredible new product instead of a hacky collection of scripts.”
— Andrej Karpathy
  • OpenAI launched its Deployment Company (May 2026, $4B+, F500 focus). Jeff Clune co-founded Recursive Superintelligence the same week. Anthropic shipped Claude for Small Business.

We are not first to invent any single piece. What we shipped first is the combination as a deployment-ready product — stateful agents with a continual-learning knowledge base, at a scale that fits government and small-business buyers, not F500 enterprises.

The category is proven

Agents already solve problems. The open question is whether they remember — and whether you can audit them.

You don't have to take our word for whether AI agents work in production. Our own model vendor, Anthropic, documents it in its 2026 enterprise agent playbook, which opens with the line we build on:

“Generative AI answers questions. AI agents solve problems.”
— Anthropic, Building Effective AI Agents (enterprise playbook, 2026)
86%
customer-support resolution at Intercom (Fin agent), across 25,000+ businesses
~100x
time-to-value as Tines collapsed multi-step security operations into single-agent runs
80-90%
resolution rate for Gradient Labs' financial-services support agent
20-60%
productivity gain on credit-risk memos at a retail bank; turnaround 30% faster
These are other companies' published results, documented in Anthropic's enterprise agent playbook — not Zak Data Solutions engagements. We cite them to make one point: the category works.

So the real question isn't do agents work. It is do they remember, and can you audit them. Anthropic's own playbook names memory and observability as the hard requirements for agents that work at scale. That is exactly the layer we build — a continual-learning knowledge base you own, with an audit trail for every decision — sized for government and small-business buyers, not F500 enterprises.

Ready to put this in your program office?

The architecture transfers. Only the data layer changes. Whether you are a contracting officer evaluating capability or a program manager scoping a pilot, the conversation starts the same way: thirty minutes, no deck.